Unified multimodal models (UMMs) have recently emerged as a promising paradigm for integrating multimodal understanding and generation within a single autoregressive transformer. However, during multimodal instruction tuning, these models often exhibit pronounced modality imbalance: language gradients dominate optimization, thus leading to lower image generation quality, especially under parameter-efficient fine-tuning such as LoRA. In this work, we systematically analyze modality imbalance in LoRA-based fine-tuning of UMMs for interleaved text-image generation. We show that vision modality performance degrades substantially more than text modality performance when compared to unimodal counterparts, and that modality-specific gradients can differ by orders of magnitude across various tasks and layers. Motivated by this observation, we reformulate the multimodal instruction tuning as a bi-objective optimization problem and propose Pareto LoRA, a Pareto-optimal gradient integration strategy that balances the text and image objectives by modulating the gradient direction and strength. Experiments on the CoMM benchmark with Emu2 demonstrate that Pareto LoRA consistently improves multimodal generation balance, achieving up to 44.9% gains in perceptual image quality over vanilla LoRA while maintaining comparable text performance.

Multimodal Foundation Models are increasingly used as reasoning agents, making reliability, knowing when a model may hallucinate, critical. A common intuition, which we call the Attention-Confidence Assumption, holds that reliability follows from "structural" visual perception: tight attention on relevant regions should signal a trustworthy answer, while scattered attention signals confusion. We challenge this through the VLM Reliability Probe (VRP), a systematic cross-family study of reliability signals in contemporary Vision-Language Models (VLMs). We introduce structural-attention metrics, cluster counts (C_k) and spatial entropy (H_s), to quantify the visual encoder's gaze, and track its evolution (Delta H_s) across layers. This reveals a "Symbolic Detachment": models often "Early Lock" visual features only to diffuse attention later, severing early perception from final generation. Contrary to the grounding hypothesis, we find a "Cluster Failure": spatial attention has near-zero correlation (R approx 0.001) with accuracy. Instead, reliability is a phenomenon of generation dynamics and internal-state distributions. Self-Consistency, the agreement rate across sampled reasoning paths, is the dominant predictor of truth (R = 0.429). Scaling causal interventions exposes a sharp architectural divergence: LLaVA locks its prediction in a fragile late-stage bottleneck, whereas PaliGemma and Qwen2-VL distribute reliability globally, staying resilient even when ~50% or more of their most predictive layer is destroyed. For current VLMs, reliability signals are detached from visual grounding maps and are best inferred from generation-time dynamics and hidden-state probes.

Visual perception depends on top-down goals and bottom-up sensory mechanisms. Vision-language models implement both, allowing us to treat each component as a separable hypothesis about what drives where we look. We compared spatial attention maps from six vision-language models against human fixation heatmaps recorded on 200 images during two tasks (general description and social captioning). The six models spanned a 2$\times$2 factorial of CNN vs.\ ViT encoders crossed with LSTM vs.\ Transformer decoders, plus Molmo 7B-D and Qwen3.5 9B. We found that both decoder and encoder architecture shaped alignment, but decoder choice dominated. LSTM vs.\ Transformer decoders increased alignment by 40--50 percentage points (80--87\% vs.\ 40--59\% of the human noise ceiling). In contrast, CNN vs.\ ViT encoders contributed a secondary 5--20 point advantage depending on decoder family, with CNN-LSTM the most aligned model overall (85--87\%). Despite their alignment advantage, LSTM-decoder attention maps were spatially diffuse and minimally task-differentiated; ViT-Transformer, the weakest in alignment, showed the sharpest spatial concentration and strongest task differentiation. A hemispatial-neglect simulation confirmed that ablating attention impacted LSTM decoders more than Transformer decoders. In an exploratory extension using TRIBE-simulated synthetic neural responses, fixation alignment and neural relevance dissociate: CNN-Transformer attention maps better predicted synthetic brain activity despite lower fixation alignment, with attention maps best predicting early visual cortex. Together, top-down and bottom-up components trade off what they predict in behavioral and synthetic neural data.

Event-enriched image captioning describes not only visible content but also the broader context of events, including timing, location, and participants, capabilities missing in most pixel-bound models. We propose the Contextual Image-Article Narrator (CIAN), a multi-stage framework that enriches captions with external narratives. CIAN retrieves relevant articles using SigLIP, summarizes them to guide a Narrative Generation stage with a LoRA-fine-tuned Qwen model, and applies N-Gram-based Refinement for fluency and coherence. On the OpenEvents-V1 benchmark, CIAN achieves high retrieval performance (mAP 0.979) and improves caption quality, increasing CIDEr from 0.030 to 0.094. These results highlight the effectiveness of retrieval-augmented reasoning combined with linguistic refinement for generating context-aware, human-like captions.

Spatial VLMs have made substantial progress in geometric perception, yet complex spatial reasoning requiring multi-step inference over depth, distance, and scene relations remains challenging. Moreover, different spatial queries call for fundamentally different strategies: some are best addressed through purely linguistic, step-by-step deduction, while others require explicit 3D grounding before quantitative inference. We present Dual-Path Spatial Reasoning via Reinforcement Learning for Spatial VLMs (SR-REAL), a unified framework that equips a spatial VLM with two complementary reasoning paths: Language-Only Reasoning (LOR), which performs step-by-step linguistic deduction, and Detect-Then-Reason (DTR), which detects 3D geometric cues (e.g., centers or bounding boxes) via region tokens before explicit geometric inference. SR-REAL begins with a cold-start supervised fine-tuning stage that constructs LOR and DTR chain-of-thought supervision and exposes a region-to-3D interface, followed by RL that optimizes the policy model with accuracy and format rewards; for DTR, a discrete center-based detection reward further refines geometric alignment. Across diverse spatial benchmarks, SR-REAL significantly outperforms spatial VLM baselines: (i) a single RL-trained model supports both reasoning paths, with DTR excelling in region-aware tasks through precise 3D localization and LOR enhancing general spatial reasoning; (ii) jointly training both paths fosters mutual reinforcement; (iii) high-quality, blended cold-start data is crucial for stable RL optimization; and (iv) the model generalizes across datasets and domains without per-task tuning, demonstrating positive transfer between LOR and DTR.

Multimodal large language models (MLLMs) integrate strong text reasoning with visual inputs, yet their responses can be inconsistent with the underlying images, indicating ineffective utilization of visual evidence during inference. The prevailing training paradigm relies on large-scale caption-based pretraining for general alignment, followed by supervised fine-tuning and reinforcement learning to enable instruction following and complex reasoning. However, such pretraining provides only weak visual grounding: short, coarse captions bias models toward salient objects while neglecting fine-grained visual evidence. In this paper, we introduce Visual Evidence Pre-Alignment (VEPA), an intermediate stage between pretraining and post-training that explores a novel sufficiency-driven objective with Group Relative Policy Optimization (GRPO) to optimize question-conditioned visual evidence descriptions. Extensive experiments across diverse benchmarks show that our VEPA consistently enhances performance on visually demanding evaluations and complements standard supervised post-training. Further analyses show that the income stems from strengthened, transferable visual grounding, rather than from additional task-specific training.

Visual information helps resolve ambiguity in coreference resolution, leading to notable performance gains. However, existing Multi-modal Coreference Resolution (MCR) methods require training with (partially) annotated data from the target dataset before they can be applied, preventing their direct usability and raising concerns about generalization. While Vision-Language Large Models (VLLMs) with billions of parameters offer promising zero-shot capabilities, they remain largely inaccessible. Their massive size limits deployability, and many are only accessible through paid APIs. In this paper, we propose a plug-and-adapt method that strategically adapts a carefully pre-trained \emph{alignment model} for immediate use in MCR tasks, designed to eliminate the need for training on scarce benchmark datasets or relying on resource-intensive VLLMs. Specifically, we first pre-train a fine-grained alignment model between textual and visual contextual information using vision-language alignment datasets. We then repurpose the alignment model to MCR through similarity aggregation by fusing visual and categorical cues with evidence theory, thereby enhancing effectiveness. Experiments on the Coreference Image Narratives (CIN) benchmark dataset demonstrate the effectiveness of our method, achieving a 5.31\% and 2.12\% improvement in CoNLL F1 over SOTA dedicated methods and popular VLLMs, respectively. We further evaluate our method on a masked CIN dataset for robustness testing and on a specially constructed VCR-MCR dataset for generalization assessment, with results confirming both capabilities.

Unified Multimodal Modeling aims to integrate visual understanding and generation within a single system. However, existing approaches typically rely on two disparate visual tokenizers, which splits the representation space and hinders truly unified modeling. We propose UniAR, a unified autoregressive framework where a single discrete visual tokenizer serves as the key bridge between understanding and generation, enabling a shared context in which the model can directly interpret its own generated visual tokens without additional re-encoding. UniAR adapts a pretrained vision encoder with multi-level feature fusion and a lookup-free bitwise quantization scheme, preserving both high-level semantics and low-level details while scaling the effective visual vocabulary at minimal cost. Building on this, the unified autoregressive model adopts parallel-bitwise-prediction to jointly predict spatially grouped, multi-level visual codes, substantially reducing visual sequence length and accelerating generation. Finally, a diffusion-based visual decoder operates on discrete visual tokens to decode high-fidelity images. Through large-scale pre-training, followed by supervised fine-tuning and reinforcement learning, UniAR achieves state-of-the-art performance on image generation and image editing while remaining competitive on multimodal understanding benchmarks. The project page is available at https://sharelab-sii.github.io/uniar-web.

While Multimodal Retrieval-Augmented Generation (M-RAG) enhances Large Vision-Language Models, it remains highly susceptible to cross-modal hallucinations, causal fabrications, and sycophancy. Furthermore, existing mitigation pipelines often face an intervention paradox: static rules tend to unnecessarily disrupt accurate generations, whereas leaving the multi-modal reasoning completely unguided allows existing mismatches to cascade into severe logical fabrications. To quantify and mitigate these hallucinations, we propose a Multi-Agent system, MODE-RAG, driven by Variational Free Energy (VFE) and internal attention states to dynamically gate interventions. High-risk queries are routed to five stage-specific agents, integrating Monte Carlo Tree Search (MCTS) for rigorous causal derivation and logit perturbations to penalize sycophancy. Dedicated Correction and Overseer agents ensure formatting stability and perform post-hoc factual verification. To objectively evaluate our approach, we introduce ModeVent, a challenging subset derived from the MultiVent dataset. Extensive experiments indicate that our system effectively reduces hallucination rates and logical fabrication, significantly improving the robustness of M-RAG systems.

Reinforcement learning with verifiable rewards has driven major gains in LLM reasoning, and it is intuitive to assume this recipe will transfer well to multimodal models. However, multimodal models do two things: first, perceive what is in an image, then reason about what it implies. Because these stages are graded jointly, it is hard to tell how much room reasoning alone has to grow. We study this on algorithmic visual puzzles, where both components are necessary and show that perception, not reasoning, is the binding constraint. Replacing images with simple textual descriptions raises performance by over 20 points on average for Claude models. We then evaluate six reward designs aimed at inducing visual grounding during reasoning without chain-of-thought supervision. Training Qwen-2.5-VL-7B with GRPO, reward design induces long, structured reasoning with self-reflection and visual references, yielding a 5.56-point gain over the base model. These gains are, however, uneven; no single reward improves all categories, and rewards with verifiable accuracy signals trade out-of-domain transfer for in-domain accuracy. These results point to perception-aware reward design as a path forward, so that signals correct perception at its source rather than the reasoning that inherits its errors.

In the era of Vision-Language Models (VLMs), enhancing multimodal reasoning capabilities remains a critical challenge, particularly in handling ambiguous or complex visual inputs, where initial inferences often lead to hallucinations or logic errors. Existing VLMs often produce plausible yet ungrounded answers, and even when prompted to "reflect", their corrections may remain detached from the image evidence. To address this, we propose the MIRROR framework for Multimodal Iterative Reasoning via Reflection On visual Regions. By embedding visual reflection as a core mechanism, MIRROR is formulated as a closed-loop process comprising draft, critique, region-based verification, and revision, which are repeated until the output is visually grounded. To facilitate training of this model, we construct **ReflectV**, a visual reflective dataset for multi-turn supervision that explicitly contains reflection triggers, region-based verification actions, and answer revision grounded in visual evidence. Experiments on both general vision-language benchmarks and representative vision-language reasoning benchmarks show that MIRROR improves correctness and reduces visual hallucinations, demonstrating the value of training reflection as an evidence-seeking, region-aware verification process rather than a purely textual revision step.

Multimodal Large Language Models (MLLMs) achieve strong vision-language reasoning, but long visual contexts enlarge the KV cache and increase decoding latency. Existing compression methods rely on observation window attention for stable token-importance estimation, yet this aggregation can dilute sparse visual evidence and discard answer-critical tokens under aggressive compression. Therefore, we identify last-query attention as a complementary source for recovering such evidence, but its answer-irrelevant signals can mislead retention. We propose BACON, a plug-and-play method that calibrates observation window attention with last-query evidence and suppresses isolated noise via intra-layer coherence and inter-layer persistence. Across diverse benchmarks, models, budgets, and compression methods, BACON improves multimodal KV compression by 7.5% on average under the most aggressive budget, with gains up to 30.9%. Our project page is available at https://ryu1ion.github.io/official_BACON/

Continuous AI inference on resource-constrained edge hardware introduces deployment effects that are largely invisible to conventional benchmark evaluation, including temporal instability in streaming video, thermal throttling under sustained load, and workload-dependent performance variability. We present Edge-TSR, a deployment-oriented continuous edge inference system for sustained roadside perception on the NVIDIA Jetson Orin Nano. Edge-TSR integrates detection, tracking, fine-grained classification, and a lightweight track-aware temporal stabilization mechanism that improves streaming inference consistency with negligible computational overhead. Our central finding is that benchmark-centric evaluation systematically overstates deployed edge inference performance. Across three state-of-the-art baselines, we observe consistent 20-30% relative degradation when transitioning from static-image evaluation to real-world streaming deployment. Edge-TSR addresses this gap through temporal inference stabilization, recovering up to 10.16% classification accuracy over per-frame inference baselines while maintaining sustained real-time performance under continuous operation. We evaluate the complete system under diverse real-world deployment conditions, jointly characterizing inference quality, latency, throughput, and thermal behavior during long-duration operation. A 55-minute vehicular deployment over a 26 km route demonstrates sustained operation at 16.18 FPS within safe thermal limits on a single embedded device without cloud offload. Our findings show that deployment-aware evaluation and temporal inference stabilization are necessary components of continuously operating edge AI systems intended for real-world sensing deployments. We release a sample annotated streaming video evaluation dataset and full system implementation to support reproducible deployment-centric evaluation.

Autonomous driving has shifted towards end-to-end policy learning, where reliable, interpretable policy evaluation is a fundamental challenge as driving quality is highly context-dependent. Commonly used rule-based driving metrics like EPDMS are interpretable but lack context-awareness, while recent VLMbased evaluations are context-aware but limited by ambiguous VLM outputs and weak physical grounding. To evaluate driving in a manner that is both interpretable and context-aware, we introduce DriveJudge. DriveJudge is a driving evaluation agent that combines rule-grounded evaluation with Vision-Language Model (VLM) reasoning and selectively invokes physically-grounded deterministic rule functions after interpreting the environmental context. To train and evaluate DriveJudge, we curate a large-scale dataset of 33,577 challenging driving samples with human annotations on whether the driving behavior is reasonable in the given scenario. With this dataset, we address the underexplored problem of driving metric evaluation, and introduce two human-aligned benchmark tasks: Driving Quality Classification and Trajectory Preference Selection. DriveJudge outperforms EPDMS for driving quality classification by 21.23 AUC, and the recent VLM-based DriveCritic for trajectory preference selection by 6.5%, setting a new standard for interpretable and precise driving evaluation.

End-to-end autonomous driving has achieved state-of-the-art performance on benchmarks and real-world deployments. Its standard training recipe, however, is expensive across all stages: collecting and labeling millions of driving frames is costly, and closed-loop RL on images is bottlenecked by the per-step cost of photorealistic rendering plus a forward pass through a large vision backbone. Self-play in vectorized simulators changes the economics: millions of rollout steps per second, and a state distribution naturally rich in collisions, near-misses, and recoveries that no driving log contains. Our approach exploits this asymmetry by decoupling learning to drive from learning to see. We pretrain a single policy by self-play, then align its latent space with a pretrained vision backbone, through the action KL divergence and a batch-relational low-rank structural loss. The action target comes from the self-play policy, so alignment never supervises against a logged trajectory: a paired dataset of (image, scene-state) frames suffices, with no need for the curated expert demonstrations that imitation pretraining is built on. On photorealistic 3D Gaussian splatting closed-loop scenarios, the resulting end-to-end policy matches or exceeds prior end-to-end methods.

Vision-Language-Action (VLA) policies have achieved remarkable single-step manipulation, yet they remain brittle precisely where each stage depends on what was just completed. The core issue is structural: short-window VLAs lack an explicit channel for rouxting information across sub-task boundaries, and existing memory-augmented variants either write at every frame, retrieve from demonstration-time stages, or fire at sub-goal events without performing an explicit sub-task-to-sub-task hand-off into the action expert. We identify the sub-goal completion event as the natural temporal unit for cross-subtask memory hand-off, and present WeaveLA (Weave Latent memory for Vision-Language-Action policies), a cross-subtask memory interface that, on top of a frozen VLA backbone, compresses each completed segment into latent tokens via query-driven attention pooling and routes them directly into the action-generation path of the next sub-task. This event-triggered, action-side design preserves the base policy's short-window interface while adding a lightweight cross-subtask channel. Through stratified evaluation on RoboMME with a $π_{0.5}$ backbone, WeaveLA's gains land exactly where the channel is needed: on the hardest repetition slice (SwingXtimes, $N{=}3$), success rises from $0\%$ to $47.8\%$, while single-execution episodes remain unchanged. Per-episode paired analysis confirms the gains are confined to tasks whose causal structure requires cross-subtask information.

Generalist vision-language-action systems need object-centric 3D evidence and reusable manipulation experience to plan reliable robot trajectories. GeneralVLA provides a hierarchical interface for converting language and RGB-D observations into 3D end-effector paths, but two bottlenecks remain. First, monocular SAM3D-style object reconstruction can hallucinate pose and unseen geometry, while manipulation benefits from stable object shape when calibrated multi-view observations are available. Second, the original KnowledgeBank mainly retrieves semantically similar snippets and appends new knowledge, which makes it difficult to control memory quality, conflicts, confidence, and geometric relevance. To address the first challenge, we introduce GeoFuse-MV3D, a geometry-prior-guided MV-SAM3D reconstruction branch that verifies external geometry cues with input-view masks, applies soft visual-hull support, performs axis-wise refinement, and fuses only geometry while preserving appearance. To address the second challenge, we upgrade KnowledgeBank into a governed long-term memory system with explicit quality, confidence, lifecycle, verifier, and conflict metadata, together with precision-oriented retrieval. Finally, we evaluate the reconstruction branch on GSO-30 and the memory module on Terminal-Bench 2.0 and SWE-Bench Verified; GeoFuse-MV3D improves over the MV-SAM3D baseline by reducing CD and LPIPS by 2.20% and 2.02% while increasing PSNR and SSIM by 2.36% and 1.03%, and KnowledgeBank improves over ReasoningBank by 4.53% on Terminal-Bench SR and 3.73% on SWE-Bench resolve rate, while reducing AS by 4.95% and 5.65%, respectively. Code: https://github.com/AIGeeksGroup/GeneralVLA-2. Website: https://aigeeksgroup.github.io/GeneralVLA-2.

Generating adversarial driving scenarios is critical for evaluating and improving autonomous vehicle decision-making systems in simulation. Recent approaches, such as ChatScene and LLM-Attacker, rely primarily on the prior knowledge of Large Language Models and Vision-Language Models to generate driving scenarios procedurally. We argue that adversarial scenes should be generated based on the failure diagnosis (e.g., indecisiveness, multi-frame inconsistency) of the driving policy to specifically address the policy's weaknesses instead of relying on prior assumptions. In this paper, we propose SPHINX, a closed-loop framework for adversarial scenario synthesis guided by a simple principle: first explain, then explore. Beyond blindly exploring the scenario space, SPHINX leverages explainable artificial intelligence methods to analyze the policy, identifying key visual concepts and their influence on policy outputs, and the uncertainty of the decisions. Given the interpretable evidence extracted from the policy's own decision process, we use a vision language model to rationalize and criticize failure modes of the current policy. These critics are then used to generate targeted adversarial scenarios for policy retraining and improvement. We demonstrate that SPHINX can highlight an interpretable account of policy failures while other adversarial scene generation cannot. Across the evaluated benchmarks and test suites, SPHINX can be applied to diverse state-of-the-art autonomous vehicle architectures and yields consistent robustness improvements over existing scenario-generation methods.

Generative world models for autonomous driving face two unresolved tensions: heterogeneous control injection, where free-form language, HD-maps, trajectories, and camera poses reside in incompatible representational spaces, and post-hoc cross-view fusion, where per-camera latents fail to encode global 3-D geometry. We trace both to a single root cause: the absence of a shared symbolic interlingua aligning language, geometry, and pixels at the latent-token level. We present DRIVE-CHOREO, an LLM-choreographed multi-agent world model that recasts controllable multi-view video generation as latent choreography. Three Qwen2.5-VL agents - a Director parsing user intent into a structured WorldScript, a Cartographer grounding it into spatially-anchored layout tokens, and an Auditor feeding cross-view critiques back as auxiliary supervision - jointly author a single position-aware token sequence. This sequence is co-compressed with the multi-view video via a view-time permutation that enforces inter-camera geometry within the convolutional receptive field of a 3-D VAE. On nuScenes, DRIVE-CHOREO sets new state-of-the-art multi-view consistency and BEV mAP (21.6) with competitive FVD (45.7); a detector trained purely on our synthetic data gains +2.4 NDS on the real validation split, validating downstream utility.

Interactive world models aim to simulate environment dynamics under real-time user actions. However, their action vocabulary is largely confined to navigation: most actions correspond to motion (e.g., walk, turn, look around), while interaction with objects in the scene (e.g., pick up plates, open doors, or trigger physical responses) is either absent, restricted to game domains, or relegated to prompt-to-full-video scenarios. The resulting worlds are visually explorable but not truly actionable. In this work, we present ActWorld, an interactive world model that extends prior navigation-centric generators to support mid-rollout object interaction within a chunk-autoregressive framework. We argue that the navigation-interaction gap stems from two bottlenecks. First, a data bottleneck: the lack of human-object interaction data with accurate, dense labels. Second, a memory bottleneck: recency-biased history compression in existing world models discards the event-transition frames that causally determine subsequent object states, leading to an action-forgetting pathology. On the data side, we construct a 100K interaction video dataset, each annotated with per-chunk captions via chain-of-thought reasoning. On the model side, we introduce a hierarchical action-aware memory design that routes history compression by interaction importance, complemented by a persistent memory bank that maintains event-update and object-identity tokens across long rollouts. Experiments show that ActWorld supports both flexible navigation and rich object interaction within a single model, substantially improving interaction fidelity over navigation-only baselines without sacrificing viewpoint control. Project page is available at https://interactwm.github.io/ActWorld.

Event cameras sense the world through asynchronous brightness changes with microsecond latency and high dynamic range, offering motion fidelity far beyond frame-based sensors and capturing temporal structure that conventional exposures often miss. These properties make events a powerful complement to RGB in autonomous driving, especially under blur, glare, and rapid motion, where frame-based perception can become unreliable. However, existing event-aware vision-language models remain limited to generic perception and do not reveal how event sensing contributes to reasoning and decision-making across the full driving loop. We present EventDrive, a large-scale benchmark and model suite that unifies event streams, RGB frames, and language supervision across four core dimensions: Perception, Understanding, Prediction, and Planning, covering captions, structured QA, grounding, motion-state recognition, trajectory forecasting, and planning tasks. Building on this foundation, EventDrive-VLM introduces a multi-horizon event pyramid and a temporal-horizon mixture-of-experts module to adaptively encode and fuse asynchronous and frame-based information for downstream reasoning. Comprehensive evaluation across diverse tasks shows that event streams provide substantial gains in temporal precision, motion awareness, and robustness, bringing event sensing into the center of driving intelligence.

Collaborative human-object interaction shows dynamic and complex movements that require mutual anticipation and continuous adjustment between participants and the shared object. Modeling such collaborative multi-human object interaction (MHOI) scenarios requires high-quality data acquisition as a foundational step; however, this is challenging due to the inherent complexity of MHOI where human-human and human-object interactions occur simultaneously. Such complexity leads to noisy MHOI captures characterized by several artifacts: contact misalignment between hands and objects, motion jitter and temporal inconsistencies in the captured sequences, and missing or incomplete finger-level articulation details. To address these challenges, we present MOCHI (MOtion Enhancement of Collaborative Human-object Interactions), a two-stage framework for enhancing noisy MHOI data. Our approach first generates physically plausible hand grasps through optimization from noisy body input, producing grasps that are both physically plausible and semantically consistent with the body pose, where these optimized grasps are extended into complete hand-object interaction sequences. Consequently, the full-body motion for all participants are refined through a diffusion-based noise optimization framework that uses single-person motion priors. During the optimization process, we introduce optimization objectives to encode human-object and human-human interaction information within these single-person priors. Experimental results demonstrate the effectiveness of our pipeline across diverse MHOI data, either acquired by existing capture methods or synthesized by generative models. We further show robustness of our system across varying numbers of participants and types of interactions, and demonstrate various applications including keyframe-based MHOI creation and data augmentation through varying object geometries.

Forecasting the evolution of dynamic environments is crucial for autonomous agents. While generative world models have recently achieved high photorealism in 2D video synthesis by mixing ego-motion and environmental dynamics within the image plane, they exhibit physical inconsistencies, such as morphing or vanishing objects, especially over long time horizons. In this paper, we propose FR3D, a world model that predicts a persistent 3D latent representation for future dynamic 3D reconstruction. Unlike prior works that treat the world as a sequence of image-based features, FR3D explicitly decouples the 3D evolution of the scene from the agent's trajectory, treating the inferred ego-motion as a latent proxy for action. This disentanglement resolves the ambiguities between self-motion and world-motion, ensuring geometric consistency into the future. Furthermore, we introduce a teacher-student distillation strategy that leverages the spatial "common sense" of off-the-shelf foundation models, leading to robust zero-shot generalization. Extensive experiments demonstrate FR3D's strong performance for future dynamic 3D reconstruction from monocular observations across multiple datasets, even 2 seconds into the future. Project page: https://fr3d-wm.github.io.

Existing vision encoders for robotics face a fundamental bottleneck: robotic datasets lack the scale necessary for large-scale pre-training. Prior work circumvents this data scarcity by turning to internet-scale image and language data or egocentric human video. While these models show promise, neither paradigm learns from paired vision and action data, which downstream visuomotor control policies require. However, robot trajectories, the most direct source of this paired signal, are not available at pre-training scale, motivating us to extract action signals from abundant human video instead. To this end, we introduce CAIP (Contrastive Action-Image Pre-training), a vision encoder that treats human hand poses from large-scale egocentric video as a proxy for end-effector actions. By extracting 3D hand keypoints, a representation that aligns naturally with downstream robot action spaces, CAIP learns a unified action-image representation through a contrastive objective. Leveraging 32,041 hours of egocentric human video and only 88 hours of robotic manipulation data, CAIP outperforms state-of-the-art vision encoders including DINOv2, SigLIP, MVP, and R3M. Evaluated on a challenging real-world dexterous manipulation setup using Dexmate Vega and Sharpa Wave hands, CAIP yields performance gains of more than 30% on tasks involving folding, pouring, and fine-grained manipulation. Our results show that our method of contrastive action-centric pre-training yields a scalable path to achieving robust visual representations better suited for physical interaction.

Respiratory-rate (RR) monitoring is a critical component of remote triage and victim assessment in emergency response, disaster recovery, and infectious-disease scenarios, where minimizing physical contact can reduce responder risk and improve operational safety. However, field deployment of contactless RR monitoring remains challenging due to variable illumination, posture changes, platform heterogeneity, and the impracticality of wearable sensors in hazardous environments. In this paper, we present a modality-adaptive contactless RR monitoring framework for heterogeneous mobile robots with onboard edge computing. The proposed system combines brightness-adaptive sensor selection across RGB, thermal, near-infrared (NIR), and low-light cameras, keypoint-guided chest ROI extraction for posture-robust monitoring, and a signal-quality-index (SQI)-based filtering mechanism for reliable respiratory estimation. We implement and evaluate the framework on three robotic platforms spanning quadruped and wheeled locomotion and multiple edge-computing architectures. Experiments conducted across diverse lighting conditions, subject poses, and robot-to-subject distances demonstrate that the framework generalizes across platforms without per-platform algorithmic retuning, while revealing modality-specific operational boundaries. RGB provides the broadest coverage up to 8m, NIR remains effective up to 6m, thermal is reliable only at short range, and low-light sensing supports monitoring in complete darkness up to 8m. Overall, the results demonstrate the feasibility of multimodal contactless RR monitoring on mobile robots and support its use as a foundation for autonomous triage and victim assessment in hazardous search-and-rescue settings.

Generative robot policies typically begin action generation from an observation-independent standard Gaussian distribution, leaving the choice of source distribution underexplored. This work asks a simple question: where should action generation begin? We propose LeaP, a Learnable source Prior that replaces the standard Gaussian with a proprioception-conditioned diagonal Gaussian over action chunks. Parameterized by a lightweight MLP, LeaP jointly predicts the mean and state-adaptive variance of the source distribution, while keeping the downstream generator architecture and inference solver unchanged. This design provides an observation-informed yet stochastic initialization, allowing the generator to focus on precise action refinement rather than transporting samples from an uninformed noise source. On 15 RoboTwin manipulation tasks, LeaP achieves an average success rate of 81.6%, outperforming four representative baselines -- including deterministic-source methods, a no-prior counterpart, and a diffusion-bridge policy -- by 6.5 to 25.5 percentage points. The same prior consistently improves both flow-matching and diffusion-bridge generators, while using fewer parameters and converging faster. The advantage carries over to real-world deployment, where LeaP attains the best performance. These results suggest that the source distribution is an independent and reusable design axis for generative robot policies, complementary to the choice of generative dynamics.

Simulation enables scalable robot data collection, but raw 3D assets provide only geometry, lacking the semantic, interactive, and physical knowledge needed to specify where and how robots should act. In this work, we present AnnotateAnything, a general automatic annotation framework that converts passive 3D assets into manipulation-ready assets with structured, diverse, and executable manipulation labels. AnnotateAnything is built around two complementary pipelines. First, a unified visual-language annotation pipeline using vision-language reasoning to infer object semantics, interaction constraints, and 3D-grounded cues, providing human-prior guidance for identifying meaningful interaction regions. Second, a fully automatic and massively parallel physics annotation pipeline grounds these priors in each asset's geometry and physical constraints through candidate generation, geometry optimization and trajectory generation. This pipeline produces diverse and executable action annotations, including grasp poses, dexterous contacts, articulation waypoints, insertion directions, hanging affordances, and navigation targets. Using the generated annotations, we further build an asynchronous parallel simulation data-collection system across diverse objects, tasks, and robot embodiments. Experiments demonstrate that AnnotateAnything achieves superior annotation efficiency, data-collection efficiency, and task success rates over existing annotation and data-generation pipelines, while also supporting downstream tasks such as affordance detection, robotic VQA, and visual instruction finetuning. We provide project materials on the project page and plan to release the full code, annotations, and benchmark to facilitate future research. Videos, code, demo assets, and annotations are provided in supplementary materials Project page: https://tourmaline-caramel-169490.netlify.app.

Robot learning and embodied agents now require simulation to serve as a shared execution substrate linking control, skills, and planning, not only as a renderer, controller testbed, or fixed task environment. Existing pipelines split these layers with "magic" actions, disconnected training environments, or forward-only renders that cannot reproduce, evaluate, and annotate the same episode. We present MagicSim, an embodied interaction infrastructure built around one deterministic batched runtime and a shared Markov decision process (MDP). From YAML-first specifications that decouple contents, placement, behavior, and agent exposure, MagicSim constructs diverse executable worlds spanning task families, interaction regimes, physics, layouts, sensors, avatars, and robot embodiments in one reset-and-step loop. A common execution interface grounds high-level commands through controllers, atomicskills, planner primitives, and asynchronous planning, realizing them as robot actions rather than simulator-side state edits. One task definition supports three capabilities: benchmark and RL evaluation, an autocollect interface that automatically turns commands into grounded trajectories, and agent/VLM-facing interaction. For automatic execution, commands flow through a Command->Skill->Planner->Robot->Record pipeline, while per-environment command, skill, planning, retry, annotation, and episode states advance independently above the shared physics tick. Successful rollouts are saved as structured multimodal trajectories aligning language supervision, action representations, visual/geometric representations, and task-level status with the executed episode. MagicSim thus unifies diverse world construction, embodied execution, task evaluation, automatic rollout generation, and interactive agent interfaces in one planner-in-the-loop runtime.

Training embodied agents in the real world requires skilled operators and expensive hardware. Simulation environments offer a compelling alternative by enabling large-scale, cost-effective data augmentation. Consequently, rapidly constructing high-fidelity simulation scenes with a minimal sim-to-real gap has become a critical objective in robot learning. While reconstruction-based methods provide superior visual quality, current workflows are hindered by inefficient data acquisition and subpar foreground object extraction. We thus propose GASE, a highly automated system for simulation scene construction. GASE leverages multi-view video streams from panoramic camera arrays to enable rapid environment scanning. To ensure high-quality asset generation, our pipeline introduces a camera-pose-based strategy that robustly extracts objects across frames in the 2D domain, followed by high-fidelity scene inpainting. Foreground objects and the static background are then reconstructed independently and seamlessly imported into physics simulators for policy training. Extensive experiments demonstrate that GASE outperforms existing 3D Gaussian-based methods in segmentation accuracy by over 10\% while achieving state-of-the-art inpainting quality. Furthermore, real-robot deployments across manipulation and navigation tasks maintains a performance gap of less than 10\% compared to policies trained purely on real-world data. These results confirm that GASE provides an efficient and highly effective solution for bridging the sim-to-real gap. Code will be released.

Humans naturally leverage diverse sensing modalities to interact with the physical world, while most Vision-Language-Action (VLA) models for robotics rely solely on RGB observations. This limits their ability to perceive physical properties that are difficult or impossible to infer from RGB cameras, such as temperature, sound, or radar response. We present MuseVLA, an adaptive multimodal sensing VLA model that integrates novel sensors as on-demand tools for robotic manipulation. Given a task instruction and visual context, MuseVLA first generates a sensor token and target description that select the sensing modality to invoke and what to attend to, analogous to a tool call with arguments. It then converts the selected sensor measurement into a grounded sensor image, a unified intermediate representation that encodes heterogeneous readings for multimodal fusion and action generation. This design decouples sensor-specific processing from the VLA backbone, enabling efficient integration of diverse modalities. To reduce the need for expensive multisensory robot datasets, we further introduce a data synthesis pipeline that augments existing RGB video datasets with grounded sensor images, enabling generalization to unseen sensor-guided tasks. We evaluate MuseVLA on a real-world robot across challenging dexterous hand manipulation tasks that require multimodal sensing inputs, including temperature-guided pick-and-place, audio-driven object search, and radar-assisted hidden object retrieval. MuseVLA achieves 80.6% success rate on average, outperforming RGB-only and multisensory VLA baselines significantly, and exhibits strong zero-shot capabilities on unseen tasks.

Robotics are expected to support environmental monitoring and natural disaster management, where decisions must be made under uncertainty, resource limitations, and strict operational constraints. In critical missions, such as wildfires, robotic agents must not only identify hazardous events with sufficient confidence, but also manage the energy cost and time until detection. This paper introduces ED3R, an energy-aware distributed framework for wildfire detection under uncertainty. ED3R enables hierarchical cooperative decision-making between a robot and a remote controller. The remote controller decides upon the robot's motion, while the robot senses the environment and decides where to execute the wildfire detection (onboard or remotely) and how. The common goal is to detect wildfires with a required confidence while minimizing the energy consumed by any robot operation. ED3R further integrates mechanisms to avoid nearby obstacles, prevent redundant exploration, enable adaptive early mission completion, and ensure feasibility through a custom penalty function. ED3R also introduces a forward-looking capability, enabled through distributed neural regression models that allow the agents to anticipate the future by evaluating candidate strategies before execution. The framework is evaluated through realistic robotics simulations, ablation studies, and baseline comparisons. Overall, ED3R achieves a mission success rate of up to 97.18%. Especially in the most demanding missions, it reduces energy consumption by up to 36.4% and detects wildfires up to 41% faster than baselines.

Agentic navigation systems require a base navigation model whose observation strategy can be externally reconfigured at inference time, because instruction following, object search, target tracking, and autonomous driving share the same perception-planning backbone yet demand fundamentally different strategies for consuming the visual stream. We present Qwen-RobotNav, a scalable navigation model built on Qwen-RobotNav that addresses it through a parameterised interface with two complementary dimensions: multiple task modes that select the navigation behaviour, and controllable observation parameters (e.g., token budget, per-camera weights) that govern how visual history is encoded. With training-time randomization over all parameters, Qwen-RobotNav is robust to any inference-time configuration requiring zero architectural modification to the Qwen-RobotNav backbone. We train Qwen-RobotNav on 15.6M samples; co-training with vision-language data prevents the collapse into reactive action-sequence mappers observed in trajectory-only training. The parameterised interface also makes Qwen-RobotNav a natural building block for agentic systems: for long-horizon scenarios, an upper-level planner decomposes goals into sub-tasks and dynamically switches Qwen-RobotNav's task mode and context strategy mid-episode, composing complex behaviours from repeated calls to the same model. Extensive experiments show that Qwen-RobotNav sets new state-of-the-art results across major navigation benchmarks. The model exhibits favourable scaling from 2B to 8B parameters, with joint multi-task training developing a shared spatial-planning substrate that transfers across task families, and demonstrates strong zero-shot generalisation to real-world robots across diverse environments.

Drivers' visual attention provides critical cues for anticipating latent hazards and directly shapes decision-making and control maneuvers, where its absence can compromise traffic safety. To emulate drivers' perception patterns and advance visual attention prediction for intelligent vehicles, we propose DiffAttn, a diffusion-based framework that formulates this task as a conditional diffusion-denoising process, enabling more accurate modeling of drivers' attention. To capture both local and global scene features, we adopt Swin Transformer as encoder and design a decoder that combines a Feature Fusion Pyramid for cross-layer interaction with dense, multi-scale conditional diffusion to jointly enhance denoising learning and model fine-grained local and global scene contexts. Additionally, a large language model (LLM) layer is incorporated to enhance top-down semantic reasoning and improve sensitivity to safety-critical cues. Extensive experiments on four public datasets demonstrate that DiffAttn achieves state-of-the-art (SoTA) performance, surpassing most video-based, top-down-feature-driven, and LLM-enhanced baselines. Our framework further supports interpretable driver-centric scene understanding and has the potential to improve in-cabin human-machine interaction, risk perception, and drivers' state measurement in intelligent vehicles.

Cross-modal Thermal Geo-localization (TG) provides a robust, all-weather solution for Unmanned Aerial Vehicles (UAVs) in Global Navigation Satellite System (GNSS)-denied environments. However, profound thermal-visible modality gaps introduce severe feature ambiguity, systematically corrupting conventional coarse-to-fine registration. To dismantle this bottleneck, we propose SCC-Loc, a unified Semantic-Cascade-Consensus localization framework. By sharing a single DINOv2 backbone across global retrieval and MINIMA$_{\text{RoMa}}$ matching, it minimizes memory footprint and achieves zero-shot, highly accurate absolute position estimation. Specifically, we tackle modality ambiguity by introducing three cohesive components. First, we design the Semantic-Guided Viewport Alignment (SGVA) module to adaptively optimize satellite crop regions, effectively correcting initial spatial deviations. Second, we develop the Cascaded Spatial-Adaptive Texture-Structure Filtering (C-SATSF) mechanism to explicitly enforce geometric consistency, thereby eradicating dense cross-modal outliers. Finally, we propose the Consensus-Driven Reliability-Aware Position Selection (CD-RAPS) strategy to derive the optimal solution through a synergy of physically constrained pose optimization. To address data scarcity, we construct Thermal-UAV, a comprehensive dataset providing 11,890 diverse thermal queries referenced against a large-scale satellite ortho-photo and corresponding spatially aligned Digital Surface Model (DSM). Extensive experiments demonstrate that SCC-Loc establishes a new state-of-the-art, suppressing the mean localization error to 9.37 m and providing a 7.6-fold accuracy improvement within a strict 5-m threshold over the strongest baseline. Code and dataset are available at https://github.com/FloralHercules/SCC-Loc.

Robotic practices on the construction site emerge as an attention-attracting manner owing to their capability of tackling complex challenges, especially in the rebar-involved scenarios. Most of existing products and research are mainly focused on the collection of large amounts of data with model training demands. To fulfill this gap, we propose OpenTie, a 3D training-free rebar tying framework utilizing a RGB-to-point-cloud generation and an open-vocabulary rebar detection on the real-world test. We implement the OpenTie via a robotic arm with a binocular camera and guarantee a high accuracy by applying the prompt-based object detection method on the image filtered by our proposed post-processing procedure for the image-to-point-cloud generation framework. Our pipeline requires no training efforts and outperforms the training-based object detection, i.e., YOLO-based method, with the verification on the real-world sequential rebar tying test. The system is flexible for horizontal and vertical rebar tying tasks and holds the potential application to the real construction site with possibility of commercialization.

Practical autonomous driving requires models that generalize by reasoning through spatial-temporal possibilities to exclude unsafe outcomes. While state-of-the-art (SOTA) methods use parallel planning architectures, they fail to explicitly couple speed decisions with agent behavior along the driving path, leading to suboptimal coordination. To address this, we propose a cascaded framework that transforms longitudinal planning from an independent prediction task into a path-conditioned reasoning process. On the model side, we introduce an anchor-based regression design that conditions longitudinal prediction on the lateral drive path, and reformulate longitudinal planning as 1D displacement prediction along the path. This reduces geometric uncertainty and sharpens the model's focus on interaction-driven dynamics. On the data side, we introduce a planning-oriented data augmentation strategy that simulates rare safety-critical events by programmatically inserting agents and relabeling longitudinal targets to enforce collision avoidance. Evaluated on the challenging Bench2Drive benchmark, our method achieves SOTA performance with a driving score of 89.07 and a success rate of 73.18%, demonstrating significantly improved coordination and safety. Further evaluation on Fail2Drive confirms strong generalization to rare edge cases where parallel formulations typically fail. Project page:https://yanhaowu.github.io/AlignDrive/.

Can VLMs predict how each camera move changes the view, and plan many such moves ahead? We call this capability view planning, requiring (1)understanding how a single action transforms the view, and (2)composing many such transformations across multi-turn plans to identify a target view. We probe both abilities in our proposed ViewSuite, a 3D point-cloud environment on real ScanNet scenes. Across 13 frontier VLMs, a critical planning gap emerges: they possess basic view-action knowledge but fail to compose it across multi-turn plans, with the gap widening as viewpoint distance grows. To close this gap, we propose an iterative framework that alternates self-exploration with view graph distillation. The key insight is that all exploration trajectories, regardless of their outcome, collectively form a view graph that compactly captures how viewpoints connect across a scene. Distilling this graph into diverse supervised tasks reshapes the policy distribution and overcomes the sparse rewards that stall pure RL. This improves Qwen2.5-VL-7B from 2.5% to 47.8% on interactive view planning, surpassing GPT-5.4 Pro (18.5%) and Gemini 3.1 Pro (21.4%). Self-exploration emerges as a promising path toward VLMs that can actively reason and plan in 3D space. Code and Data are at https://viewsuite.github.io.

World models are transitioning from passive visual generators to foundational, operational infrastructure for Physical AI: they must natively acquire world knowledge from heterogeneous experience, maintain persistent states over long horizons, and execute efficiently within real deployment constraints. We introduce Kairos, a native world model stack designed around these requirements. (1) Kairos learns the world by pioneering a Native Pre-training Paradigm governed by a Cross-Embodiment Data Curriculum, which organizes open-world videos, human behavioral data, and robot interactions into a progressive developmental pathway. (2) Kairos maintains the world by unified world understanding, generation, and prediction within a Native Unified Architecture equipped with Hybrid Linear Temporal Attention, where sliding-window attention captures local dynamics, dilated sliding windows capture mid-range dependencies, and gated linear attention maintains persistent global memory. We establish formal theoretical bounds demonstrating that this temporal factorization strictly limits error accumulation, mathematically guaranteeing state propagation across extended horizons. (3) Kairos runs the world by incorporating a Deployment-Aware System Co-Design to support low-latency rollout generation on server and consumer-grade hardware for real-world observation-action-feedback loops. Experiments on embodied world-model, long-horizon, and action-policy benchmarks show that Kairos achieves top level performance while offering a strong efficiency-capability trade-off. Together, these results position Kairos as a cohesive operational foundation for future self-evolving physical intelligence.

Hyperspectral image (HSI) crop analysis is essential for precision agriculture because it captures rich spectral and spatial information for accurate crop monitoring and assessment. However, HSI classification remains challenging due to high spectral dimensionality, spatial complexity, class imbalance, and limited labeled samples. To address these challenges, this paper proposes a BiSpectral Mamba-based framework that combines multi-scale convolutional feature extraction, spectral attention, bidirectional state-space modeling, and quantum-inspired learning. A multi-scale CNN backbone first extracts hierarchical spatial-spectral representations through feature fusion across multiple resolutions. A spectral attention mechanism then emphasizes informative bands while suppressing redundant and noisy channels. The refined features are processed by a BiSpectral Mamba module that captures long-range dependencies in both forward and backward directions by modeling hyperspectral feature maps as sequential tokens. In addition, class-weighted optimization and feature fusion strategies are incorporated to improve training stability and mitigate class imbalance. Experimental evaluation on the UAVHSI-Crop dataset demonstrates the effectiveness of the proposed framework, achieving an overall accuracy of 84.83%. The results show that integrating convolutional, attention-based, and state-space modeling components enables robust spatial-spectral feature learning for crop classification. The proposed framework also shows potential for broader agricultural and remote sensing applications, including crop disease detection, yield prediction, and soil moisture estimation, while highlighting the effectiveness of structured state-space and quantum-inspired architectures for hyperspectral image analysis.

Coastal algal bloom monitoring requires frequent, spatially detailed, and globally consistent observations, provided by Landsat-8/9 and Sentinel-2 A/B/C. Together, these missions offer over a decade of medium-resolution multispectral imagery with near-global coverage every 2-3 days, enabling the detection of fragmented bloom structures not resolvable by coarse ocean-color sensors. However, their use in aquatic environments remains challenging due to limited spectral coverage and a lack of harmonized reflectance products. As an alternative to traditional bio-optical methods, deep learning-based image classification offers a data-driven approach that can overcome many of these limitations. This study presents the first successful implementation of vision transformer-based coastal algal bloom mapping using 30-m Landsat-Sentinel-2 images. A globally distributed bloom patch dataset was generated across bloom-prone coastal hotspots worldwide. Four transformer-based architectures were compared against a standard convolutional baseline for fine-scale bloom detection, and assessed under different optical water types and atmospheric and surface conditions. All deep learning models showed strong capabilities in detecting floating bloom areas, with omission and commission errors of 8-65%. Under cloud and glint stress in a time series, the Swin Transformer outperformed traditional spectral-index approaches, which produced widespread false positives, effectively avoiding cloud- and glint-affected pixels. Comparisons with MODIS-derived products further highlighted the benefits of higher spatial resolution in detecting fragmented and irregularly affected blooms. Our findings support deep learning as a reliable tool for medium-resolution, consistent monitoring of floating algal blooms in dynamic coastal environments.

Feature extraction involves the identification and extraction of salient characteristics or patterns, including edges, textures, shapes, and color attributes. Contemporary feature extractors predominantly leverage deep learning architectures, such as Convolutional Neural Networks (CNNs) and Vision Transformers (VITs). The availability of diverse feature extractors in the literature provides a wide range of feature representations. Features extracted from an image depend on the specific application, the chosen extractor, and its configuration. Therefore, integrating complementary information by combining distinct extractors offers a promising way to enhance performance. Graph Neural Networks (GNNs), particularly Graph Convolutional Networks (GCNs), have emerged as powerful and widely adopted approaches for semi-supervised image classification, as they effectively leverage both labeled and unlabeled data while exploiting the underlying graph structures that capture relationships among samples. This study proposes a novel approach for GNNs in scenarios where labeled data is scarce, by integrating diverse sets of feature and graph representations derived from various extractors in classification scenarios. Experimental investigations were conducted, encompassing combinations of distinct feature and graph extractors, as well as rank aggregation strategies. The primary contributions of this work are underscored by the experimental findings, which demonstrate that the strategic combination of feature and graph representations, coupled with the application of manifold learning for graph processing, leads to significant improvements in classification accuracy across the majority of experimental conditions. Furthermore, the utilization of rank aggregation techniques to integrate features from different extractors was shown to enhance classification accuracy.

Fingerprint recognition is still dominated by task-specific pipelines, where enhancement, structural parsing, alignment, and matching are optimized in isolation. Although effective in narrow settings, this design limits representation reuse across sensors, qualities, and downstream applications. We therefore present UoU, short for ``a \textbf{U}niversal fingerprint foundation model based \textbf{o}n large-scale \textbf{U}nsupervised learning,'' which reframes fingerprint feature extraction as a domain-specific foundation-model problem. UoU is organized around a multi-level representation hierarchy spanning image restoration, structural fields, semantic tokens, point-level biometric entities, and compact global descriptors. Its training recipe combines a supervised cold start on precise annotations, large-scale weakly supervised refinement, and large-scale unsupervised consolidation, with the latter two stages iterated during large-scale training so that weak supervision broadens semantic coverage while unsupervised learning stabilizes correspondences, invariances, and representation geometry. Rather than treating fingerprint imagery as generic texture, UoU exploits domain-specific symmetries and intermediate structure, including orientation flow, periodic ridge patterns, sparse biometric entities, and spatial equivariance. The framework is intentionally architecture-agnostic: while the present study includes an initial transformer-based structured-prediction instantiation, the broader design supports multi-task learning, scalable model configurations, and downstream specialization for matching, alignment, enhancement, registration, and related fingerprint applications. This paper presents the technical motivation, system design, and validation protocol of UoU, and part of the baseline implementation is publicly available at https://github.com/XiongjunGuan/UoU.

State Space Models (SSMs) have emerged as efficient alternatives to attention for vision tasks, offering lineartime sequence processing with competitive accuracy. Vision SSMs, however, require serializing 2D images into 1D token sequences along a predefined scan order, a factor often overlooked. We show that scan order critically affects performance by altering spatial adjacency, fracturing object continuity, and amplifying degradation under geometric transformations such as rotation. We present Partial RIng Scan Mamba (PRISMamba), a rotation-robust traversal that partitions an image into concentric rings, performs order-agnostic aggregation within each ring, and propagates context across rings through a set of short radial SSMs. Efficiency is further improved via partial channel filtering, which routes only the most informative channels through the recurrent ring pathway while keeping the rest on a lightweight residual branch. On ImageNet-1K, PRISMamba achieves 84.5% Top-1 with 3.9G FLOPs and 3,054 img/s on A100, outperforming VMamba in both accuracy and throughput while requiring fewer FLOPs. It also maintains performance under rotation, whereas fixed-path scans drop by 1~2%. These results highlight scan-order design, together with channel filtering, as a crucial, underexplored factor for accuracy, efficiency, and rotation robustness in Vision SSMs. Code will be released upon acceptance.

Event cameras are bio-inspired sensors that asynchronously capture logarithmic intensity changes, offering inherent advantages in high-speed and high-dynamic-range scenarios. However, the sparse and asynchronous nature of event streams poses a fundamental challenge for modern deep learning architectures. To enable compatibility with standard models, most existing approaches partition the accumulation window into fixed temporal sub-bins. While effective for spatial processing, this internal discretization discards fine-grained temporal structure and constrains inference to the low temporal frequencies imposed by training supervision. To address this limitation, we propose FATE, a unified framework built upon a novel Pillar Encoding (PE). While operating over discrete macro-accumulation windows dictated by the target frequency, PE avoids internal temporal sub-binning. It organizes events into spatial pillars and approximates their intra-window evolution via projection onto a continuous-time orthogonal polynomial basis. This formulation yields an L2-optimal representation that retains rich temporal dynamics in a dense pseudo-image, mitigating information loss under sparse event conditions. To fully leverage this representation, we introduce Frequency-Aware Training (FAT), a soft mean-teacher curriculum that generates temporally dense pseudo-labels, effectively bridging the mismatch between low-frequency supervision and high-frequency inference. Extensive experiments demonstrate that FATE generalizes across architectural paradigms and consistently outperforms strong baselines. It enables robust object detection at high temporal resolutions up to 200 Hz, while incurring minimal overhead in parameter count and inference latency

Understanding hands and the objects they interact with, both directly and through tools, is a key step for tasks ranging from action perception to 3D reconstruction and robotics. Our paper provides several contributions to the Hand-Object Interaction (HOI) understanding literature: (1) HOI-DETR, a new framework that introduces hand-object and object-object interactions to the Co-DETR architecture to produce a state-of-the-art method; (2) a comprehensive HOI evaluation suite of 4 diverse datasets, including a video benchmark derived from the HD-EPIC dataset and fresh annotations that improve the Hands23 benchmark and (3) a trained checkpoint that significantly improves the state of the art across Hands23, HOIST, FineBio, and HD-EPIC, including mAP gains of over 20 percentage points on Hands23 and FineBio. Our ablations confirm the contributions of each model component.

Stereo matching has advanced through foundation models trained on large-scale datasets, yet this paradigm suffers from a scalability bottleneck: incorporating new data requires costly joint retraining. Model merging offers a scalable post-hoc alternative by integrating knowledge from specialized models after source checkpoints are available. However, existing merging methods typically retain all available models or rely on greedy inclusion, which can preserve harmful task-vector interference. We propose StereoFactory, a coarse-to-fine evolutionary framework for adaptive model merging. Stage~1 employs a genetic algorithm to search the combinatorial space of model subsets, determining which models should participate. Stage~2 addresses module-level knowledge specialization (different functional modules exhibit distinct preferences for knowledge sources) through CMA-ES optimization of architecture-adaptive routing over the selected task vectors, with optional module-level scaling. Experiments across two architectures and four benchmarks demonstrate that StereoFactory consistently achieves the best four-benchmark average under the same checkpoint pool, reducing the average error from 3.80 to 3.30 on NMRF and from 2.88 to 2.19 on FoundationStereo relative to the strongest controlled baseline. The post-hoc search requires only 2.7--3.7\% of the corresponding joint-retraining wall-clock time. Analysis reveals that knowledge contributions are inherently module-specific, and selected subsets can transfer across architectures with minimal degradation. Code will be publicly released upon acceptance at: https://github.com/XiandaGuo/StereoFactory.

Text-guided open-vocabulary object counting (TOOC) aims to count objects belonging to the categories specified by natural language descriptions. Although vision-language pre-trained models have been successful applied to TOOC tasks, they still struggle with fine-grained spatial understanding and real-time inference requirements in counting scenarios. To address these limitations, this paper proposes a real-time TOOC framework, called the Real-Time Counter (RT-Counter), that achieves not only good counting accuracy but also high computational efficiency. RT-Counter designs a novel Visual Prototype Textualization (VPT) module that can project learned visual features into a text feature space and then generate features containing the abstract information that is hard to capture with visual prototypes and the detailed prototype information that is difficult to describe in text, enhancing the object-level visual-language model's counting capabilities. Additionally, RT-Counter incorporates our Weaving Transformer (Weaformer) layers, maintaining high descriptive power at a fraction of the computational cost. The Weaformer layer adopts a novel hybrid attention mechanism that can efficiently weave together local and global visual features. Extensive experiments on three public datasets show that RT-Counter successfully breaks the accuracy-speed trade-off in TOOC. While achieving a competitive MAE of 13.30 on FSC147, RT-Counter operates at 112.48 FPS, making it 7.4x faster and over 4$\times$ more parameter-efficient than the existing leading methods in TOOC. Our work aims at balancing high accuracy and real-time performance in TOOC. Code is available at: https://github.com/Jason-Mar1/RT-Counter.

Text-guided Open-vocabulary Object Counting (TOOC) aims to estimate the number of objects described by text prompts, which is particularly challenging in dense scenes with large scale variations. Existing TOOC approaches predominantly rely on Transformers, whose quadratic complexity with respect to image resolution limits their scalability. Mamba offers a promising alternative due to its linear complexity. However, previous Mamba-based methods have two main limitations. On the one hand, the inherent causal formulation of Mamba constrains the bidirectional spatial dependency modeling required by non-causal vision tasks. On the other hand, existing Mamba-based vision models often overlook the unconstrained high entropy in the spatial token responses, which can weaken local details and high-frequency cues. To address these limitations, we propose MambaCount, an efficient framework built on the Spatial Sparse State Space Duality (S^4D) block. Specifically, we analyze and reconstruct the decay dynamics of hidden states in Mamba to alleviate the dependency constraints introduced by causal modeling. Moreover, we introduce a Spatial Token Selection (STS) sub-block to reduce the unconstrained high entropy in spatial token responses within Mamba. In addition, we design Multi-Granularity Prototypes (MGP) to identify object-like regions at different semantic levels, improving cross-modal alignment and interpretability. Extensive experiments on FSC-147 demonstrate that MambaCount achieves state-of-the-art performance among methods without secondary querying, obtaining a test MAE of 12.23, while retaining linear complexity.

Mamba-based state space models offer linear-time long-range modeling for high-resolution dense prediction, but sequential state-space propagation can attenuate boundary-sensitive and detail-sensitive responses that are critical in multi-class semantic segmentation. We propose Reload-Mamba, a semantic segmentation framework that addresses this propagation-induced response dilution through three segmentation-specific designs: (i) a boundary-supervised local detail prior that is explicitly trained with ground-truth boundary masks to identify regions requiring response restoration; (ii) a class-uncertainty-aware Reload Gate that incorporates per-pixel class entropy from a pre-reload auxiliary head as an additional gating signal, a formulation that is informative only under multi-class dense prediction; and (iii) a hierarchical multi-level Reload mechanism that applies anti-dilution refinement at three decoder levels and fuses the restored representations top-down. Built upon a ConvNeXt-Tiny encoder with a multi-scale decoder and four-directional Mamba scanning with pixel-wise directional attention, Reload-Mamba achieves 47.9% single-scale (48.9% multi-scale) mIoU on ADE20K and 83.2% single-scale mIoU on Cityscapes. With ResNet-101 + COCO pre-training under the standard DeepLab-style protocol, Reload-Mamba reaches 87.8% mIoU on PASCAL VOC 2012 val. Controlled ablations show that each of the three segmentation-specific designs contributes beyond a direct port of the prior anti-dilution architecture proposed for binarization, cumulatively improving over the direct-port baseline by +2.2 mIoU on ADE20K.

The proliferation of floating anthropogenic debris in rivers has emerged as a pressing environmental concern, exerting a detrimental influence on biodiversity, water quality, and human activities such as navigation and recreation. The present study proposes a novel methodological framework for the monitoring the aforementioned waste, utilising fixed, in-situ cameras. This study provides two key contributions: (i) the continuous quantification and monitoring of floating debris using deep learning and (ii) the identification of the most suitable deep learning model in terms of accuracy and inference speed under complex environmental conditions. These models are tested in a range of environmental conditions and learning configurations, including experiments on biases related to data leakage. Furthermore, a geometric model is implemented to estimate the actual size of detected objects from a 2D image. This model takes advantage of both intrinsic and extrinsic characteristics of the camera. The findings of this study underscore the significance of the dataset constitution protocol, particularly with respect to the integration of negative images and the consideration of temporal leakage. In conclusion, the feasibility of metric object estimation using projective geometry coupled with regression corrections is demonstrated. This approach paves the way for the development of robust, low-cost, automated monitoring systems for urban aquatic environments.

Wireframe parsing aims to recover line segments and their junctions to form a structured geometric representation useful for downstream tasks such as Simultaneous Localization and Mapping (SLAM). Existing methods predict lines and junctions separately and reconcile them post-hoc, causing mismatches and reduced robustness. We present Co-PLNet, a point-line collaborative framework that exchanges spatial cues between the two tasks, where early detections are converted into spatial prompts via a Point-Line Prompt Encoder (PLP-Encoder), which encodes geometric attributes into compact and spatially aligned maps. A Cross-Guidance Line Decoder (CGL-Decoder) then refines predictions with sparse attention conditioned on complementary prompts, enforcing point-line consistency and efficiency. Experiments on Wireframe and YorkUrban show consistent improvements in accuracy and robustness, together with favorable real-time efficiency, demonstrating our effectiveness for structured geometry perception. Our code is available at https://github.com/GalacticHogrider/Co-PLNet.

The human visual system tracks objects by integrating current observations with previously observed information, adapting to target and scene changes, and reasoning about occlusion at fine granularity. In contrast, recent generic object trackers are often optimized for training targets, which limits robustness and generalization in unseen scenarios, and their occlusion reasoning remains coarse, lacking detailed modeling of occlusion patterns. To address these limitations in generalization and occlusion perception, we propose GOT-JEPA, a model-predictive pretraining framework that extends JEPA from predicting image features to predicting tracking models. Given identical historical information, a teacher predictor generates pseudo-tracking models from a clean current frame, and a student predictor learns to predict the same pseudo-tracking models from a corrupted version of the current frame. This design provides stable pseudo supervision and explicitly trains the predictor to produce reliable tracking models under occlusions, distractors, and other adverse observations, improving generalization to dynamic environments. Building on GOT-JEPA, we further propose OccuSolver to enhance occlusion perception for object tracking. OccuSolver adapts a point-centric point tracker for object-aware visibility estimation and detailed occlusion-pattern capture. Conditioned on object priors iteratively generated by the tracker, OccuSolver incrementally refines visibility states, strengthens occlusion handling, and produces higher-quality reference labels that progressively improve subsequent model predictions. Extensive evaluations on seven benchmarks show that our method effectively enhances tracker generalization and robustness.

Rapid post-event landslide mapping is essential for disaster response but remains difficult to automate due to extreme class imbalance. This study evaluates whether Clay v1.5, a Geospatial Foundation Model (GFM), can improve pixel-level landslide segmentation on the Landslide4Sense (L4S) benchmark, which contains 3,799 training chips with 14 Sentinel-2 and terrain bands and approximately 2% positive pixels. We compare three strategies: Clay as the primary encoder with multi-scale residual terrain fusion, a U-Net backbone augmented with Clay semantic context at the bottleneck, and a standard U-Net baseline. The hybrid U-Net + Clay model with two-stage Low-Rank Adaptation (LoRA) achieved the best test F1 of 64.5 +/- 1.8% over three seeds, surpassing the Clay-only backbone (55.2 +/- 3.6%) and the U-Net baseline (59.9%). Clay as a standalone encoder underperformed the U-Net due to the absence of multi-scale skip connections, but its pretrained representations consistently improved performance when injected as auxiliary context. These findings suggest that GFMs are most effective for landslide detection when they complement spatially detailed convolutional architectures rather than replace them.

We present GOOSE-M2F, a task-specific adaptation of Mask2Former for the GOOSE 2D Fine-Grained Semantic Segmentation (FGSS) Challenge at ICRA 2026. The GOOSE benchmark spans 64 fine-grained classes across unstructured outdoor terrain with a severely long-tailed distribution, where rare classes occupy fewer than 50 pixels per image. We extend the Swin-Large Mask2Former baseline with three targeted contributions: (1) 200 object queries to eliminate representational saturation; (2) a Feature Refinement Module (FRM) combining ASPP-lite and CBAM dual-attention; and (3) an Auxiliary Supervision Head that delivers direct per-pixel gradients for rare classes. A multi-stage training strategy pairs Distribution-Balanced loss, Rare-Class Copy-Paste augmentation, dynamic IoU-aware re-weighting, and EMA. At inference, a dense sliding-window engine with 2D Gaussian kernel blending and 4-scale TTA adds +10.57%. GOOSE-M2F achieves 70.08% Official Composite mIoU (63.55% fine, 76.61% coarse), placing 3rd on the GOOSE 2D FGSS leaderboard. Code and trained models are publicly available at GitHub: https://github.com/Aditya-Lingam-9000/GOOSE-M2F and Hugging Face: https://huggingface.co/XYZ9843/GOOSE-M2F.

Surgical video question answering requires multi-step reasoning across semantic, spatial, and temporal dimensions. Existing methods architecturally compress videos into discrete token representations and couple visual perception with reasoning. This approach fragments continuous spatial-temporal relationships and has been shown to restrict multi-step reasoning capabilities. We introduce a reinforcement learning (RL) framework that trains large language models (LLMs) to decouple perception from reasoning by operating over digital twin representations constructed from surgical foundation models. Additionally, we introduce hierarchical representations across frame, temporal window, and procedure levels with probabilistic uncertainty estimates. Finally, we propose a novel reward that combines format validation with accuracy assessment through clinical plausibility evaluation and uncertainty-aware calibration for training. To demonstrate the capabilities of this approach, we introduce REAL-Colon-Reason, a colonoscopic benchmark with 2000 question-answer pairs across three complexity levels. We achieve state-of-the-art performance on REAL-Colon-Reason and two existing surgical VideoQA benchmarks REAL-Colon-VQA and EndoVis18-VQA.

Text-to-video retrieval in operating rooms (OR) is an enabling technology for OR safety, as it allows stakeholders to retrieve and inspect recordings of specific events. However, because the most safety-critical events may not follow the common structure, to unlock its full potential text-to-video retrieval must be able to handle implicit queries that require reasoning to identify the right video (e.g., the step right before clipping). However, existing methods rely on global embeddings that cannot reason over such queries. We propose OR3, a text-to-video retrieval method that converts clips into action-driven digital twins (ActDTs), grouping concurrent subject-action-object triplets under non-overlapping temporal intervals. Moreover, rather than cross-modal matching through paired encoders, OR3 performs imagination-based retrieval where an LLM generates hypothetical ActDTs from queries. This enables intra-modal matching via a single encoder trained with ActDT-tailored hard negatives. Finally, evidence-grounded refinement revises imagined ActDTs based on discrepancies with top candidates to capture procedure-specific patterns. We construct a benchmark from MM-OR with 276 implicit queries across four reasoning categories over 386 clips from robotic knee procedures. OR3 achieves 57.6 R@1 and 77.3 R@5, outperforming the strongest baseline. These results demonstrate that OR3 enables fine-grained discrimination between visually similar OR video clips through temporal action reasoning.

Estimating human proficiency from video is a key challenge for automated skill assessment, with applications in sports coaching, music pedagogy, surgical training, and workplace learning. Existing approaches often focus on individual scenarios or rely on shared multi-view aggregation, limiting their ability to adapt to heterogeneous camera viewpoints and activity domains. We introduce SkillMoV, a unified, parameter-efficient framework for multi-scenario proficiency estimation from synchronized multi-view video. At its core, SkillMoV introduces a Mixture-of-View Projector (MoVP), which adapts the mixture-of-experts paradigm to camera-specific view features. MoVP is composed of four stages: (i) a Mixture-of-View soft router with twelve expert MLPs that learns view-dependent expert preferences without camera-identity supervision; (ii) cross-view attention to align synchronized cameras; (iii) learnable prototype anchoring to condition the representation on class-level reference vectors; and (iv) a prototype-conditioned gated projection that produces the final skill embedding. We evaluate SkillMoV on EgoExo4D across six skill domains and three separately trained view configurations: Ego, Exos, and Ego+Exos. SkillMoV reaches 50.17% overall accuracy in the Exos setting with a single model trained jointly across all scenarios, surpassing the strongest reported Exos result among the compared methods by 3.57 percentage points. In Ego+Exos, SkillMoV remains close to the best reported result in that setting (47.63% versus 48.20%). Ablations on the selected Exos configuration validate each component: MoV routing contributes +6.61 pp over attentive aggregation, cross-view attention +4.92 pp, prototype anchoring +4.07 pp, and stochastic view dropout +3.90 pp. Through LoRA adaptation, SkillMoV trains only 23.32% of its parameters and adds limited measured overhead relative to a LoRA-only baseline.

Fine-grained action recognition in egocentric video is challenging for Vision-Language Models (VLMs): actions often differ only in small visual cues, and a single model tends to be biased toward a subset of these cues. We propose Divide, Deliberate, Decide, a fully-local, zero-shot multi-agent framework in which (i) a VLM orchestrator chunks the video and proposes a top-k candidate label list per segment, (ii) an ensemble of heterogeneous VLM specialists, drawn from different open model families, engages in a structured deliberation that includes a peer-consultation round of questions, and (iii) agent rankings are aggregated with a Borda count and the orchestrator re-ranks its own prediction in light of the specialists' evidence. The entire pipeline runs locally with no fine-tuning. Experiments show that our method positively improves zero-shot action recognition performance over the baseline, highlighting the influence of a heterogeneous deliberation step, showing that the gain stems from decorrelated model priors rather than from additional compute.

Despite the remarkable progress of Video Large Language Models (Video-LLMs), current online architectures still struggle to simultaneously process continuous video streams, decide autonomously when to respond, and preserve long-horizon contextual memory. These obstacles undermine real-time responsiveness and cause severe forgetting throughout prolonged interactions. In this work, we introduce LiveStarPro, a live streaming assistant that is designed for proactive video understanding over long-horizon streams. The design of LiveStarPro rests on three complementary components. The first component is Streaming Verification Decoding (SVeD), an inference framework that identifies the appropriate response timing through single-pass perplexity verification, thereby eliminating the dependency on explicit silence tokens. The second component is Streaming Causal Attention Masks (SCAM), a training strategy that enforces incremental video-language alignment over variable-length streams. The third component is Tree-Structured Hierarchical Memory (TSHM), a recursive memory architecture that organizes evicted historical information into event chains and consequently enables efficient retrieval from effectively unbounded video streams. To facilitate a comprehensive evaluation under realistic online conditions, we further present OmniStarPro, a large-scale benchmark that spans 15 diverse real-world scenarios and that extends to hour-scale streams for the assessment of long-term recall. Extensive experiments demonstrate that LiveStarPro consistently surpasses existing methods, attaining a 28.9% improvement in semantic correctness and an 18.2% reduction in timing error, while its streaming key-value cache further yields a 1.58x inference speedup over the same model without caching. The model and the code are publicly available at https://github.com/sotayang/LiveStarPro.

Recent progress in latent world models (e.g., V-JEPA2) has shown promising capability in forecasting future world states from video observations. Nevertheless, dense prediction from a short observation window limits temporal context and can bias predictors toward local, low-level extrapolation, making it difficult to capture long-horizon semantics and reducing downstream utility. Vision--language models (VLMs), in contrast, provide strong semantic grounding and general knowledge by reasoning over uniformly sampled frames, but they are not ideal as standalone dense predictors due to compute-driven sparse sampling, a language-output bottleneck that compresses fine-grained interaction states into text-oriented representations, and a data-regime mismatch when adapting to small action-conditioned datasets. We propose a VLM-guided JEPA-style latent world modeling framework that combines dense-frame dynamics modeling with long-horizon semantic guidance via a dual-temporal pathway: a dense JEPA branch for fine-grained motion and interaction cues, and a uniformly sampled VLM \emph{thinker} branch with a larger temporal stride for knowledge-rich guidance. To transfer the VLM's progressive reasoning signals effectively, we introduce a hierarchical pyramid representation extraction module that aggregates multi-layer VLM representations into guidance features compatible with latent prediction. Experiments on hand-manipulation trajectory prediction show that our method outperforms both a strong VLM-only baseline and a JEPA-predictor baseline, and yields more robust long-horizon rollout behavior.

Open-weight video diffusion models can generate photorealistic unsafe content, from violence to misinformation, yet existing defenses either require expensive safety fine-tuning that degrades general capability, or apply external filters that are trivially bypassed by adversarial prompts. We present REINS (REpresentation-space INference-time Safety steering), a training-free method that aligns video diffusion models at inference time by steering their internal representations toward safe generation. Our key finding is that safety-relevant structure is linearly encoded in the hidden-state activations of video diffusion transformers, and a single direction, discovered via Supervised PCA on binary safety labels, suffices to separate safe from unsafe generation trajectories. At inference, adding this direction to hidden states at an intermediate transformer layer redirects generation from harmful content to semantically related safe alternatives, with no weight updates, no concept enumeration, and negligible computational overhead. Through mechanistic analysis, we reveal that while safety information accumulates monotonically with transformer depth, steering effectiveness peaks at intermediate layers (~50% depth), exposing a fundamental tradeoff between information availability and downstream propagation capacity. We evaluate REINS across 9 video diffusion models, multiple parameter scales (1.3B-5B), and both text-to-video and image-to-video generation, to our knowledge, the broadest safety evaluation suite in the video generation literature.

Generating novel renderings of a scene along user-defined camera trajectories from a single monocular video, dubbed video retaking, is a compelling but difficult problem in content creation and visual effects. Existing geometry-guided approaches reconstruct a 4D representation from the source video and render it along the target trajectory to condition video diffusion models. However, this guidance degrades as the target camera departs from the source trajectory, leaving newly revealed regions sparse or entirely missing. We propose SierpinskiCam, which addresses this limitation by augmenting geometry-based guidance with Sierpinski dome texture cues that contains rich trackable features even under large viewpoint changes. We further introduce a reference video conditioning mechanism that appends source-video tokens to the target-token sequence and separates the two streams with negative RoPE indices, enabling appearance grounding without architectural modification or per-video adaptation. Extensive experiments show that SierpinskiCam achieves significant gains in camera controllability, geometric consistency, and video quality across diverse and challenging retaking scenarios. Project page: https://hyelinnam.github.io/SierpinskiCam/.

Visual textures -- spatially homogeneous image regions containing repeated elements (e.g. a field of grass, the bark of a tree) -- are ubiquitous in visual scenes and provide important cues for recognizing and analyzing materials and objects. A number of existing texture models extract essential statistics from a single texture image, and can then generate high-quality samples that are visually similar to the original by matching these statistics. However, their statistics are either hand-designed or based on a network pretrained for another purpose (e.g., object recognition). Here, we develop the first principled method for unsupervised learning of a set of statistics that are used to constrain a maximum entropy probability model. We leverage methods developed for generative diffusion models to derive training and sampling procedures, and compare these to the traditional method of sampling via matching the statistics. Despite the compactness of our trained model (512 statistics), it generates texture images whose quality is as good as or better than the current state-of-the-art model (~177k statistics). A more direct comparison of the two models, obtained by synthesizing images that are indistinguishable for one model but maximally different for the other, reveals their relative strengths and weaknesses. Finally, we show that unlike previous statistical texture models, a straight trajectory in the representation space of our model generates homogeneous texture samples that interpolate smoothly between the features of the two end points.

Generative AI has advanced the ability to render photorealistic or artistic images, yet it remains limited in a key aspect of human creativity: interpreting ambiguous shapes. This phenomenon, rooted in pareidolia, allows humans to perceive meaningful forms in random patterns such as clouds, stones, or leaves. To computationally replicate this imaginative process, we introduce Visual Retrieval-Augmented Generation (Visual-RAG), a framework that generates animal art directly from natural silhouettes. Our method retrieves structurally similar animal shapes from a curated corpus of 28,586 high-quality silhouettes and uses them as reference exemplars to guide diffusion-based generation with ControlNet and IP-Adapter. Ablation studies confirm that shape Context with RANSAC provides the most accurate alignment, while removing shape standardization reduces the inlier ratio to just 13.4\%, underscoring the importance of structural fidelity in Visual-RAG. A user study with 12 participants evaluated the outputs in terms of aesthetics, silhouette fidelity, and overall impression. Results reveal that while Visual-RAG provides plausible interpretations, challenges remain in achieving high perceptual impact. This work lays the foundation for computational pareidolia, showing how machines can contribute to the early stages of imaginative discovery.

Finding the initial noise that generates a given data sample, known as inversion, is a key component for downstream applications such as training-free image editing. Existing fixed-point inversion methods improve inversion accuracy by formulating each inversion step as a fixed-point problem, but they lack a principled mechanism for selecting among multiple fixed-point solutions that can arise in practice. We observe that different selections induce different inversion trajectories, leading to substantial variation in reconstruction and editing quality. For rectified flows, we further find that this variation is closely associated with trajectory straightness, motivating straightness as a principled selection criterion. We propose SelFix, a fixed-point inversion method that selects fixed-point solutions inducing straighter inverse trajectories while retaining convergence to an exact inverse root under standard local assumptions. Experiments on FLUX.1-dev and PIE-Bench show that SelFix improves fixed-point inversion, achieving stronger real-image reconstruction and better source-preserving prompt-based editing than prior inversion baselines. The code is available at https://github.com/seminkim/selfix.

Video tokenization is fundamental to scalable video generation, as the number of tokens directly determines the computational cost and the length of videos that can be modeled. Existing tokenizers mainly improve scalability by compressing videos into fewer tokens, but they often continue to represent persistent content, such as static backgrounds and consistent object appearances, repeatedly across frames and chunks. In this paper, we propose \textbf{TivTok} (\textit{Time-Invariant Tokenizer}), a reuse-aware video tokenizer that makes persistent information reusable across time. TivTok represents a clip with Time-Invariant (TIV) tokens that encode information shared across frames and Time-Variant (TV) tokens that encode frame-specific residuals. To obtain this factorization, we introduce Scope-Induced Factorization (SIF), which assigns different attention scopes to the two token groups: TIV tokens attend to the full clip, whereas each TV token only accesses its corresponding frame together with the TIV tokens. In the decoder, Invariant Broadcasting (IB) reuses the same TIV tokens across frames and chunks for parallel reconstruction and long-video tokenization. Experiments show that TivTok achieves an rFVD of 12.65 on the standard $16{\times}256{\times}256$ benchmark and improves compression efficiency by 2.91$\times$ for 128-frame videos compared with the evaluated baselines, while using only 1.1\% of the tokens required by downsample-based tokenizers in our evaluation.

Reference-driven image generation has made rapid progress on identity preservation, but reliable viewpoint control across different subjects remains poorly understood. The difficulty is not merely generating a new image of the target subject: the model must infer the implicit viewpoint of one subject and transfer it to another subject using only image-level evidence, without camera poses, depth, or ray-based conditions. In this setting, existing generators conditioned on multiple image references often rely on spurious semantic correlations, which lead to viewpoint drift, part-level structural mismatches, and missing or unsupported target-specific content. We formulate this challenge as cross-subject viewpoint alignment and propose RAVA, a retrieval-augmented framework that supplies explicit geometric evidence before generation. RAVA first learns a cross-instance viewpoint embedding that retrieves target-subject images aligned with the anchor viewpoint, then applies a LogDet-based subset selection strategy to retain a compact reference set that is both view-consistent and structurally complementary. The selected references are finally consumed by a fine-tuned multi-reference image generator. Experiments show that generic semantic embeddings are nearly random for this task, while the proposed retriever substantially improves viewpoint retrieval quality. On cross-subject generation, RAVA consistently outperforms zero-shot baselines and stronger retrieval alternatives under the same generation backbone. These results indicate that cross-subject viewpoint alignment benefits from retrieval-augmented geometric grounding rather than relying on end-to-end generation alone.

As an increasing majority of global video content is consumed on social platforms for interactive social purposes, video generation models built for social worlds are important but largely overlooked by previous studies. In this work, we define the position of social world models and build a prototype model as the first step towards this goal. While previous world models successfully simulate physical environments or gaming world exploration, they remain fundamentally detached from human-centric social dynamics. To bridge this gap as the first step to social world models, we present MaineCoon, the first real-time audio-visual autoregressive model that has 22B parameters and is capable of real-time streaming generation and sub-second interaction, with a record-breaking frame rate of up to 47.5 FPS, on a single GPU. To the best of our knowledge, MaineCoon is also the first real-time audio-visual generation model specifically optimized for social-interactive applications. To enable efficient and stable training, we introduce several novel techniques into MaineCoon, including self-resampling, cross-modal representation alignment, domain-aware preference optimization, and reinforced online-policy distillation (ROPD). We also design the first agentic streaming inference framework that supports thousand-second-scale or even longer generation while mitigating drift with agentic cache management and prompt planing. These innovations significantly accelerate training while optimizing real-time inference performance. We believe this work not only sets a new state-of-the-art (SOTA) performance benchmark for high-quality, low-latency, and long-horizon audio-visual autoregressive models, but also points out the paradigm shift desired for next-generation AI-native social platforms.

We present a novel framework for realistic and controllable 3D face re-aging which produces highly detailed, identity-preserving results. Existing 3D editing methods, while effective for coarse semantic changes, are not well suited for re-aging, as even small inconsistencies across re-aged 2D views can lead to over-smoothing of subtle but perceptually important age-related details. To address this challenge, we first introduce a 2D diffusion-based re-aging model, DiffReaging, trained on synthetically generated image pairs. We further propose a center-out editing propagation strategy that leverages this re-aging model to reconstruct multi-view-consistent re-aged images. Specifically, starting from a re-aged frontal pivot view, we reconstruct the remaining views through warping and our proposed Masked-DiffReaging process. By injecting existing content at every step of the diffusion process, Masked-DiffReaging ensures that the reconstructed regions remain coherent with existing pixels. The resulting consistent set of re-aged views supervises the optimization of the re-aged 3D representation. Our method outperforms existing 3D editing techniques both visually and quantitatively, enabling smooth, fine-grained control over age transformations in 3D face models.

We present Edit3DGS, a unified framework for dynamic 3D head editing that integrates 2D instruction-guided diffusion with 3D Gaussian splatting. Unlike prior approaches that separately address frame-based edits or static 3D reconstruction, our method couples semantic controllability in the image domain with photorealistic, temporally consistent 3D representations. Given an input video, editable facial regions are masked and modified using a text-conditioned diffusion model to support fine-grained operations such as expression transformation, attribute modification, and appearance refinement. The edited frames are then aggregated through 3D Gaussian splatting to produce a coherent, high-fidelity avatar that preserves both identity and motion dynamics. To enforce consistency, Edit3DGS incorporates multi-view batch editing and lightweight inpainting strategies that recover lost expressions across timesteps. Experimental results demonstrate that our framework enables controllable, artifact-free head editing with smooth temporal transitions, offering practical applications in virtual avatars, immersive communication, film production, and interactive media.

Current world models face a fundamental tension: faithful long-horizon simulation demands deep computation, but deeper models are expensive to deploy and prone to compounding errors. We resolve this by introducing Looped World Models (LoopWM), which are the first looped architectures for world modelling. Our method iteratively refines latent environment states through a parameter-shared transformer block. This yield up to 100x parameter efficiency over conventional approaches with adaptive computation that automatically scales depth to match the complexity of each prediction step. Orthogonal to scaling model size and training data, LoopWM establishes iterative latent depth as a new scaling axis for world simulation, which might significantly push the community forward.

Generative models have shown great promise for novel view synthesis (NVS) by leveraging strong image generation priors. However, existing approaches typically follow a 2D inpainting paradigm, first completing missing image regions and then performing 3D reconstruction. This strategy often causes geometry distortion and appearance drift, as 2D inpainting models cannot reliably infer the underlying 3D structure required for cross-view consistent generation. In this paper, we propose \textbf{SceneCompleter}, a geometry-aware framework that reformulates generative NVS as dense 3D scene completion. Instead of hallucinating isolated 2D views, SceneCompleter jointly completes geometry and appearance through a geometry-appearance dual-stream diffusion model in a spatially aligned RGBD latent space. To provide holistic scene context, we further introduce a Scene Embedder that conditions generation on global semantic and stylistic information from reference images. The completed RGBD predictions are then aligned and integrated into an expandable 3D scene representation, enabling iterative and coherent scene completion. Extensive experiments on in-domain and out-of-distribution datasets demonstrate that SceneCompleter produces visually plausible and geometrically consistent novel views across diverse scenarios. Project Page: https://chen-wl20.github.io/SceneCompleter

Large-scale, high-quality dynamic 3D (4D) assets are essential for learning physically grounded representations, but remain costly to capture and annotate at scale. This limits the viability of supervised 4D learning and motivates zero-shot text-to-4D generation leveraging pretrained diffusion priors. To model complex dynamics, prior methods typically adopt implicit 3D representations (e.g., NeRFs or 3DGS) for their deformation capacity. However, their implicit nature provides limited control over surface topology, which hinders high-fidelity geometry and makes temporally coherent surface reconstruction challenging. To address these limitations, we explore zero-shot text-to-4D mesh generation. However, a structural mismatch arises when combining diffusion-based guidance with topology-constrained meshes: the guidance is noisy and spatially inconsistent, while meshes impose severe topological constraints, making direct vertex-level deformation unstable. In this paper, we introduce TextMesh4D, the first zero-shot framework for text-to-4D that directly generates dynamic meshes by addressing the above challenge at two complementary levels. Geometrically, we shift deformation modeling from vertices to faces via a Jacobian Deformation Field (JDF), enabling topology-aware surface reconstruction through an integrability-enforcing integration formulation. Semantically, we propose a Local-Global Semantic Regularizer (LGSR) that preserves identity over time by jointly constraining local deformation plausibility and global shape consistency. Extensive experiments demonstrate state-of-the-art temporal consistency, structural fidelity, and visual quality, while remaining efficient on a single 24GB GPU.

Recent advances in text-to-image (T2I) generation have led to impressive visual results. However, these models still face significant challenges when handling complex prompt, particularly those involving multiple subjects with distinct attributes. Inspired by the human drawing process, which first outlines the composition and then incrementally adds details, we propose Detail++, a training-free framework that introduces a novel Progressive Detail Injection (PDI) strategy to address this limitation. Specifically, we decompose a complex prompt into a sequence of simplified sub-prompts, guiding the generation process in stages. This staged generation leverages the inherent layout-controlling capacity of self-attention to first ensure global composition, followed by precise refinement. To achieve accurate binding between attributes and corresponding subjects, we exploit cross-attention mechanisms and further introduce a Centroid Alignment Loss at test time to reduce binding noise and enhance attribute consistency. Extensive experiments on T2I-CompBench and a newly constructed style composition benchmark demonstrate that Detail++ significantly outperforms existing methods, particularly in scenarios involving multiple objects and complex stylistic conditions.

Recent Progress in post-training flow matching for text-to-image (T2I) generation with Group Relative Policy Optimization (GRPO) has demonstrated strong potential. However, it is hindered by a critical limitation: inaccurate advantage attribution. In this work, we argue that aggregating consecutive steps into a coherent 'chunk' and shifting the policy optimization paradigm from GRPO's step level to the chunk level can effectively mitigate the negative impact of this issue. Building on this insight, we propose Group Chunking Policy Optimization (GCPO), the first chunk-level reinforcement learning approach for post-training flow matching. Extensive experiments demonstrate that GCPO achieves superior performance on both standard T2I benchmarks and preference alignment, with up to 43% relative gains over GRPO, highlighting the promise of chunk-level policy optimization. The code is available on https://github.com/xingzhejun/GCPO.

Text-to-image diffusion models achieve impressive generation quality but inherit and amplify training-data biases, skewing coverage of semantic attributes. Prior work addresses this in two ways. Closed-set approaches mitigate biases in predefined fairness categories (e.g., gender, race), assuming socially salient minority attributes are known a priori. Open-set approaches frame the task as bias identification, highlighting majority attributes that dominate outputs. Both overlook a complementary task: uncovering rare or minority features underrepresented in the data distribution (social, cultural, or stylistic) yet still encoded in model representations. We introduce RAIGen, the first framework, to our knowledge, for label-free rare-attribute discovery in diffusion models, requiring no predefined minority categories. RAIGen leverages Matryoshka Sparse Autoencoders and a novel minority metric combining neuron activation frequency with semantic distinctiveness to identify interpretable neurons whose top-activating images reveal underrepresented attributes. Experiments show RAIGen discovers attributes beyond fixed fairness categories in Stable Diffusion, scales to larger models such as SDXL, supports systematic auditing across architectures, and enables targeted amplification of rare attributes during generation. The project page is available at https://vssilpa.github.io/RAIGen_webpage/ .

Recent video diffusion models have achieved impressive capabilities as large-scale generative world models. However, these models often struggle with fine-grained physical consistency, exhibiting physically implausible dynamics over time. In this work, we present \textbf{Phys4D}, a pipeline for learning physics-consistent 4D world representations from video diffusion models. Phys4D adopts \textbf{a three-stage training paradigm} that progressively lifts appearance-driven video diffusion models into physics-consistent 4D world representations. We first bootstrap robust geometry and motion representations through large-scale pseudo-supervised pretraining, establishing a foundation for 4D scene modeling. We then perform physics-grounded supervised fine-tuning using simulation-generated data, enforcing temporally consistent 4D dynamics. Finally, we apply simulation-grounded reinforcement learning to correct residual physical violations that are difficult to capture through explicit supervision. To evaluate fine-grained physical consistency beyond appearance-based metrics, we introduce a set of \textbf{4D world consistency evaluation} that probe geometric coherence, motion stability, and long-horizon physical plausibility. Experimental results demonstrate that Phys4D substantially improves fine-grained spatiotemporal and physical consistency compared to appearance-driven baselines, while maintaining strong generative performance. Our project page is available at https://sensational-brioche-7657e7.netlify.app/

Attention sinks -- tokens that receive disproportionate attention mass -- are assumed to be functionally important in autoregressive language models, but their role in diffusion transformers remains unclear. We present a causal analysis in text-to-image diffusion, dynamically identifying dominant attention recipients per timestep and suppressing them via paired, training-free interventions on the score and value paths. Across 553 GenEval prompts on Stable Diffusion~3 (with SDXL corroboration), removing these sinks does not degrade text-image alignment (CLIP-T) or preference proxies (ImageReward, HPS-v2) at $k{=}1$; only under stronger interventions ($k\!\geq\!10$) does HPS-v2 exhibit a metric-dependent boundary, while CLIP-T remains robust throughout. The perceptual shifts induced by suppression are nonetheless \emph{sink-specific} -- $\sim\!6\times$ larger than equal-budget random masking -- revealing an empirical dissociation between trajectory-level perturbation and \emph{semantic alignment} in diffusion transformers. \footnote{Code available at https://github.com/wfz666/ICML26-attention-sink.}

Group Relative Policy Optimization has emerged as essential for aligning video diffusion models with human preferences, but faces a critical computational bottleneck: training a 14B parametered model typically demands hundreds of GPU days per experiment. Existing efficiency methods reduce costs through sliding window subsampling training timesteps, but fundamentally compromise optimization, exhibiting severe instability and failing to reach full trajectory performance. We present Flash-GRPO, a single-step training framework that outperforms full trajectory training in alignment quality under low computational budgets while substantially improving training efficiency. Flash-GRPO addresses two critical challenges: iso-temporal grouping eliminates timestep-confounded variance by enforcing prompt-wise temporal consistency, decoupling policy performance from timestep difficulty; temporal gradient rectification neutralizes the time-dependent scaling factor that causes vastly inconsistent gradient magnitudes across timesteps. Experiments on 1.3B to 14B parameter models validate Flash-GRPO's effectiveness, demonstrating substantial training acceleration with consistent stability and state-of-the-art alignment quality.

Diffusion Transformers (DiTs) have become a de facto backbone of modern visual generation, and nearly every major axis of their design -- tokenization, attention, conditioning, objectives, and latent autoencoders -- has been extensively revisited. The residual stream that governs how information accumulates across layers, however, has been directly inherited from the original Transformer. In this paper, we present a systematic empirical analysis of cross-layer information flow in DiTs, jointly along depth and denoising timestep, and identify three concrete symptoms of traditional residual addition, namely monotonic forward magnitude inflation, sharp backward gradient decay, and pronounced block-wise redundancy. Motivated by this diagnosis, we propose Diffusion-Adaptive Routing (\textsc{DAR}), a drop-in residual replacement that performs \emph{learnable, timestep-adaptive, and non-incremental} aggregation over the history of sublayer outputs. Moreover, the proposed \textsc{DAR} is compatible with many modern Transformer enhancement methods, such as REPA. On ImageNet $256\times256$, \textsc{DAR} improves SiT-XL/2 by $2.11$ FID ($7.56$ vs.\ $9.67$) and matches the baseline's converged quality with $8.75\times$ fewer training iterations. Stacked on top of REPA, it yields a $2\times$ training acceleration in the early stage, suggesting cross-layer information routing as an underexplored design axis in diffusion modeling, one that operates orthogonally to existing representation-alignment objectives. Beyond pretraining, \textsc{DAR} can also be applied during the fine-tuning stage of large-scale T2I models and preserves high-frequency details during Distribution Matching Distillation.

Pixel-space diffusion models are trained on full-bandwidth noisy images, yet the useful signal available to the denoiser is strongly frequency dependent. Under rectified-flow diffusion and natural-image power-law spectra, the per-band data-to-noise contour $k^{*}(t) = (1-t)^{-2/α}$ separates a signal-bearing low-frequency region from a noise-dominated high-frequency region at each time $t$. We show that this implicit coarse-to-fine structure is not merely descriptive: it induces a capacity-allocation problem. A standard pixel-space denoiser must discover the moving bandwidth boundary internally and can spend computation on frequency-time regions where the optimal prediction collapses to deterministic baselines rather than data-distribution modeling. To make this boundary explicit, we introduce Spectral Forcing, a parameter-free, time-conditional 2D-DCT low-pass operator applied to the noisy input before the patch embedder. Its cutoff expands monotonically with the diffusion time and becomes the identity at the data endpoint. Through controlled synthetic experiments, we identify the regime in which the operator is beneficial: coarse patch tokenization and data whose high-frequency content is predominantly noise rather than essential signal. On ImageNet-256 with JiT-700M/32, Spectral Forcing consistently improves both FID and Inception Score across different training epochs, demonstrating robust gains throughout training; at finer tokenization, the spectral forcing is still competitive. We further insert the unchanged operator into SenseNova-U1, a unified text-to-image model, where it improves DPG-Bench and GenEval, showing that the input-side spectral prior transfers beyond class-conditional generation. These results suggest a route to capacity-efficient pixel-space diffusion by showing the signal and hiding the noise.

Collaborative generation, which coordinates multiple diffusion trajectories to extend the capabilities of pretrained priors, has emerged as a powerful paradigm for extending the applicability of diffusion models. Among existing approaches, diffusion synchronization provides a scenario-agnostic solution by introducing general guidance mechanisms. However, current synchronization approaches rely heavily on heuristics and still require task-specific tailoring, which limits their generalizability and performance. In this work, we mathematically derive a synchronization framework based on optimal control, providing a principled explanation of diffusion synchronization. During sampling, we optimize control variables to guide multiple trajectories toward coherent solutions while remaining close to the underlying diffusion prior. Our method operates entirely at test-time without additional training, thereby enabling broad applicability across diverse generation scenarios when combined with strong pretrained priors. We demonstrate consistent improvements over baselines on three representative collaborative generation tasks, covering a wide range of modalities and applications. Beyond performance gains, our work establishes a novel foundation for collaborative generation, opening a principled path toward extending pretrained generative models to new collaborative generation settings.

Consistent video generation under editing operations requires persistence: when edits modify scene appearance or layout, subsequent generations should remain coherent across time and viewpoints. However, existing memory designs struggle to maintain long-term consistency after such modifications, as stored contexts may become outdated or invalid. To address this, we propose PermaVid, a novel framework built upon a multi-modal context memory that disentangles spatial context into semantic appearance and geometric structure, together with an edit-aware memory update and retrieval strategy that keeps memory evolution aligned with subsequent observations. Specifically, we develop two complementary memory banks: an RGB context memory that captures appearance-aware observations while implicitly encoding geometry, and a depth context memory that preserves geometry-only structure disentangled from semantics. Building on this design, we introduce a memory-guided video generation model that performs multi-modal feature fusion under reference conditions drawn from mixed-modality memory contexts. Experiments demonstrate that our method maintains strong long-term semantic and structural consistency after edits, significantly outperforming state-of-the-art methods.

This paper presents a contact-based 3-D surface measurement method based on a Digital Fringe Projection (DFP) system, belonging to the vision-based tactile sensing family pioneered by the commercially successful GelSight sensor. Such sensors have proven effective for robotic fingertip manipulation and contact sensing. However, because GelSight employs photometric stereo with RGB LEDs, it does not measure absolute depth directly but instead infers it by integrating estimated surface gradients, which can accumulate reconstruction errors; in addition, it becomes increasingly difficult to calibrate as the sensing area grows, and its depth accuracy is challenged on highly reflective or transparent objects. To overcome these drawbacks, we propose a fringe-projection-based contact measurement technique that performs triangulation-based 3-D reconstruction on a coated silicone contact surface, providing dense per-pixel surface geometry and full-field 3-D shape measurement over the contact region. By integrating high-accuracy digital fringe projection into the sensor, our approach simplifies calibration over larger areas and enhances depth precision for complex surfaces. Experimental results, including a direct comparison with a GelSight Mini sensor, a sphere-fitting accuracy evaluation, and an uncertainty analysis, confirm that the proposed method significantly improves the accuracy and stability of structured-light-based 3-D measurements, allowing reliable reconstruction of objects with diverse optical properties.

Segmenting 3D assets into meaningful regions remains challenging, especially when segmentation criteria are application-dependent and require user control. We present a human-in-the-loop pipeline for generating a segmented 2D parameterized atlas from a 3D model for interactive media, game, and XR content workflows. Our method first selects a compact set of rendered views using a greedy set cover strategy over sampled surface points, and then supports interactive segmentation of these views with SAM~2 and Label Studio. The resulting masks are back-projected onto the model's UV parameterization to produce a unified segmented atlas that supports downstream production tasks such as segment-wise material assignment, style transfer, and semantic labeling. We assess the pipeline through a demonstration-based technical evaluation on eight cultural heritage objects. The results show that the approach can generate usable segmented atlases across diverse geometries while revealing recurring sources of manual correction, particularly fine structures, cavities, and weak appearance boundaries.

Online 3D reconstruction from monocular image sequences is a challenging and ongoing research topic. 3D Gaussian Splatting (3DGS), leveraging its high-quality real-time rendering capability, empowers online 3D reconstruction to represent dense scenes with enhanced expressiveness, and thus holds great promise for a wide range of applications such as robotics and AR/VR. However, existing online 3DGS methods still suffer from some key challenges: fragile camera pose estimation due to the lack of global optimization, and low optimization efficiency in large-scale or long-sequence scenarios. To address these issues, we propose a robust and efficient online voxelized 3DGS reconstruction framework integrated with global $\text{Sim}(3)$ optimization, which enables reliable camera tracking and efficient global loop closure for both camera poses and voxelized 3DGS. To accelerate the convergence of the voxelized 3DGS, we further introduce a color residual learning strategy, which not only boosts optimization speed but also enhances rendering quality. Extensive experiments on diverse indoor and outdoor datasets demonstrate that our method achieves state-of-the-art performance in both camera pose estimation accuracy and rendering quality, while retaining real-time efficiency. Additionally, we develop and deploy a real-world UAV-based active reconstruction system grounded on our proposed method, validating its robustness and generalizability for practical online 3D reconstruction tasks. Our code and data are available at https://github.com/TrickyGo/MoonSplat.

The Open Forest Observatory (OFO) is a collaboration across universities and other partners to make low-cost forest mapping accessible to ecologists, land managers, and the general public. The OFO is building both a database of geospatial forest data as well as open-source methods and tools for forest mapping by uncrewed aerial vehicle. Such data are useful for a variety of climate applications including prioritizing reforestation efforts, informing wildfire hazard reduction, and monitoring carbon sequestration. In the current iteration of the OFO's forest map database, 3D tree maps are created using classical structure-from-motion techniques. This approach is prone to artifacts, lacks detail, and has particular difficulty on the forest floor where the input data (overhead imagery) has limited visibility. These reconstruction errors can potentially propagate to the downstream scientific tasks (e.g. a wildfire simulation.) Advances in 3D reconstruction, including methods like Neural Radiance Fields (NeRF), produce higher quality results that are more robust to sparse views and support data-driven priors. We explore ways to incorporate NeRFs into the OFO dataset, outline future work to support even more state-of-the-art 3D vision models, and describe the importance of high-quality 3D reconstructions for forestry applications.

Accurate mechanical properties (or materials) Young's modulus ($E$), Poisson's ratio ($ν$) and density ($ρ$) are essential for reliable physics simulation of digital worlds, but most 3D assets lack this information. We propose AdaVoMP, a method for predicting accurate dense spatially-varying ($E$, $ν$, $ρ$) for input 3D objects across representations, improving the resolution, accuracy, and memory efficiency over the state-of-the-art. The foundation of our technique is a sparse and adaptive voxel structure SAV that efficiently represents both the input 3D shape and the material field output. We replace the fixed-voxel model of the most accurate prior method, VoMP, with a novel sparse transformer encoder-decoder model that learns to generate a unique SAV autoregressively for every input shape to represent its materials, achieving a resolution $16^3\times$ higher than prior art. Experiments show that AdaVoMP estimates more accurate volumetric properties, even with lesser test-time compute than all prior art. This allows us to convert high-resolution complex 3D objects into simulation-ready assets, resulting in realistic deformable simulations.

A surface representation suitable for geometry processing should be compact and explicit, provide global smoothness guarantees, support a wide range of surface topologies, and offer reliable access to differential quantities such as normals and surface energies, while remaining compatible with modern differentiable optimization. Existing neural representations typically sacrifice one or more of these properties: implicit fields typically require iso-surfacing for downstream use, while explicit neural maps are constrained by canonical-domain parametrizations or exhibit seam artifacts between local charts. We introduce Blended Chart Surfaces, a compact, network-free, explicit representation that is smooth by construction and anchored to user-provided topology. Given a coarse proxy mesh encoding the intended surface topology and approximate geometry, Blended Chart Surfaces jointly optimize for a polynomial map at each proxy vertex using an off-the-shelf optimizer to fit to an implicit target shape, avoiding the need for an input parametrization. Neighboring maps are fused using a smooth 'one-ring coordinate' blending scheme, decoupling topology and coarse geometry (carried by the proxy) from geometric details (carried by the local patches). The surface is globally smooth, fully differentiable, and enables stable evaluation of derivatives, making differential quantities and surface energies directly accessible. Additionally, our construction is equivariant to rigid motions and scaling of the proxy mesh. We evaluate Blended Chart Surfaces on various topologies and geometric complexity, and compare against explicit alternatives including interpolating-function baselines and mesh-displacement MLPs. Across these, Blended Chart Surfaces achieve a favorable trade-off among compactness, simplicity, access to differential quantities, and expressivity while remaining smooth across patch boundaries.

Reconstructing fast-dynamic scenes from multi-view videos is crucial for high-speed motion analysis and realistic 4D reconstruction. However, the majority of 4D capture systems are limited to frame rates below 30 FPS (frames per second), and a direct 4D reconstruction of high-speed motion from low FPS input may lead to undesirable results. In this work, we propose a high-speed 4D capturing system only using low FPS cameras, through novel capturing and processing modules. On the capturing side, we propose an asynchronous capture scheme that increases the effective frame rate by staggering the start times of cameras. By grouping cameras and leveraging a base frame rate of 25 FPS, our method achieves an equivalent frame rate of 100-200 FPS without requiring specialized high-speed cameras. On processing side, we also propose a novel generative model to fix artifacts caused by 4D sparse-view reconstruction, as asynchrony reduces the number of viewpoints at each timestamp. Specifically, we propose to train a video-diffusion-based artifact-fix model for sparse 4D reconstruction, which refines missing details, maintains temporal consistency, and improves overall reconstruction quality. Experimental results demonstrate that our method significantly enhances high-speed 4D reconstruction compared to synchronous capture.

This paper proposes an effective Gaussian management framework for high-fidelity scene reconstruction of both appearance and geometry. Unlike recent Gaussian Splatting (GS) pipelines that treat all primitives uniformly during optimization, our framework explicitly manages the attribute activation, representation and pruning of Gaussian. Specifically, our framework first introduces GauSep, a novel densification strategy that selectively activates Gaussian color or normal attributes to alleviate destructive gradient conflicts arising from dual supervision. We further propose GauRep, an adaptive Gaussian representation that dynamically adjusts spherical harmonics (SHs) orders and performs task-decoupled pruning to reduce redundancy at both the individual and global levels. To provide reliable geometric supervision for above mangement process, we additionally introduce CoRe, an regularized surface reconstruction module that distills robust normal fields from an SDF branch to the Gaussian representation through a confidence mechanism. Notably, the proposed Gaussian management is compatible with various reconstruction architectures and can be seamlessly integrated to improve performance while reducing size of the model. Extensive experiments demonstrate that our approach achieves superior or comparable performance in appearance and geometry reconstruction compared with state-of-the-art methods, while using significantly fewer parameters.

Registration of multiview point clouds conventionally relies on extensive pairwise matching to build a pose graph for global synchronization, which is computationally expensive and inherently ill-posed without holistic geometric constraints. This paper proposes FUSER, the first feed-forward multiview registration transformer that jointly processes all scans in a unified, compact latent space to directly predict global poses without any pairwise estimation. To maintain tractability, FUSER encodes each scan into low-resolution superpoint features via a sparse 3D CNN that preserves absolute translation cues, and performs efficient intra- and inter-scan reasoning through a Geometric Alternating Attention module. Particularly, we transfer 2D attention priors from off-the-shelf foundation models to enhance 3D feature interaction and geometric consistency. Building upon FUSER, we further introduce FUSER-DF, an SE(3)$^N$ diffusion refinement framework to correct FUSER's estimates via denoising in the joint SE(3)$^N$ space. FUSER acts as a surrogate multiview registration model to construct the denoiser, and a prior-conditioned SE(3)$^N$ variational lower bound is derived for denoising supervision. Extensive experiments on 3DMatch, ScanNet and ArkitScenes demonstrate that our approach achieves the superior registration accuracy and outstanding computational efficiency.

We introduce Discrete Voxel Diffusion (DVD), a discrete diffusion framework to generate, assess, and edit sparse voxels for SLat (Structured LATent) based 3D generative pipelines. Although discrete diffusion has not generally displaced continuous diffusion in image-like generation, we show that it can be an effective first-stage prior for sparse voxel scaffolds. By treating voxel occupancy as a native discrete variable, DVD avoids continuous-to-discrete thresholding and provides a simple framework for voxel generation, uncertainty estimation, and editing. Beyond quality gains, DVD provides more interpretable generation dynamics through explicit categorical modeling. Furthermore, we leverage the predictive entropy as a robust uncertainty metric to identify ambiguous voxel regions and complicated samples, facilitating tasks such as data filtering and quality assessment. Finally, we propose a lightweight fine-tuning strategy using block-structured perturbation patterns. This approach empowers the model to inpaint and edit voxels within a single sampling round, requiring negligible auxiliary computation and no additional model evaluations. Code is available at https://github.com/TeCai/DVD.

Generating complete 3D scenes from a single image requires inferring globally consistent geometry, object relationships, and environmental context from inherently ambiguous visual evidence. Despite recent progress in joint layout-and-mesh generation, existing methods often rely on holistic or weakly decomposed pipelines that entangle many factors at once and demand extensive scene-level supervision, limiting their generalization to complex real-world environments. We propose a multi-agent orchestration framework that decomposes single-image 3D scene generation into three structured stages: scene initialization, environment construction, and multi-agent refinement. The initialization stage extracts image-derived object masks, builds object-level 3D representations, and predicts an initial spatial layout to form a coarse 3D scene. The environment-construction stage then leverages this initialization together with point-map geometry to build an environmental scaffold of supporting surfaces, room boundaries, materials, and illumination. Finally, in the refinement stage, a planner agent identifies structural and visual inconsistencies, applies simple corrections directly, and dispatches specialist agents for complex localized revisions that are reintegrated into the global scene. To provide reliable structural initialization while reducing reliance on scene-level annotations, we further introduce a geometry-aware layout predictor supervised by sparse geometric priors derived from point maps. Unlike fully supervised layout generators, the predictor can be trained from segmentation-level data and generalizes robustly to diverse real-world scenes. Extensive experiments on benchmark datasets show that our method consistently outperforms prior approaches in geometric accuracy, spatial consistency, and perceptual realism.

Accurate vision-based navigation in monocular endoscopy is difficult due to limited depth cues, weak tissue texture, non-rigid deformation, and substantial appearance variation across domains, all of which complicate pose estimation, depth prediction, and image-to-anatomy alignment. Although recent vision foundation models have shown promise, their learned representations often remain insufficiently geometry-consistent, hindering stable feature correspondence and limiting their reliability for downstream navigation tasks. We propose a unified framework for learning geometry-consistent and domain-robust image representations for monocular endoscopy. The framework combines a synthetic data pipeline that provides accurate geometric supervision with Hierarchy-Aware Geometry-Semantic Adaptation, a structured alternative to standard LoRA that inserts low-rank adapters selectively across the transformer hierarchy and couples them with layer-wise training objectives to encourage geometric correspondence in intermediate features and semantic consistency in deeper features. Experiments on public and proprietary datasets show improved geometric and semantic representation quality, leading to better performance on downstream navigation tasks including pose estimation and monocular depth estimation. The learned representations show favorable synthetic-to-real transfer on clinical bronchoscopy and provide a useful initialization for adaptation to sinus endoscopy and colonoscopy under limited supervision. The framework also shows favorable scaling with model size and training data. These results support hierarchy-aware, geometry-guided adaptation as a practical approach for endoscopic representation learning.

We propose a novel framework for uncertainty quantification using compressed sensing magnetic resonance image reconstruction. The problem is formulated within a Bayesian framework as a linear inverse problem, with prior distributions assigned to the unknown model parameters. Specifically, the image to be reconstructed is assumed to be sparse in a given basis. We develop a general framework applicable to any basis and as examples, we test the sparsity of the image in its (1) spatial gradients using a total variation prior model, and in its (2) wavelet transform. A Markov chain Monte Carlo (MCMC) method, based on a split-and-augmented Gibbs sampler, is then employed to sample from the posterior distribution of the unknown parameters. The non-differentiable conditional distributions are efficiently sampled using a proximal MCMC method. The proposed algorithms are validated on both single-coil and multi-coil datasets using various k-space sub-sampling patterns and ratios. The results demonstrate the superior performance of each proposed approach in reconstructing images compared to its counterpart optimisation-based method. Moreover, our framework effectively quantifies uncertainty, showing a notable correlation between estimated uncertainty maps and error maps computed using ground truth and reconstructed images, compared with existing deep learning-based methods.

Accurate intraoperative liver registration is challenging due to substantial soft-tissue deformation yet sparse intraoperative measurements. Biomechanical models regularize this ill-posedness with prior knowledge but exhibit persistent prediction bias due to simplifying assumptions, while data-driven learning solutions struggle with data efficiency, generalization, and physical plausibility. We propose a hybrid registration framework that adapts a biomechanical prior using sparse intraoperative correspondences. Rather than learning a full deformation field, we learn a residual deformation function that corrects linear biomechanical predictions, modeled as a graph neural diffusion function with geometry-aware attention over the 3D liver mesh. To enable long-range information transfer of sparse observations, we take a novel perspective of sparse intraoperative measurements as \textit{context} samples where input-output pairs of the residual deformation function are fully observed, casting the problem into learning-to-learn this residual function from intraoperative context samples with feedforward meta-learners. Experiments on a deformable liver phantom dataset demonstrate improved registration accuracy and generalization compared to rigid, biomechanical, and data-driven baselines, particularly for out-of-distribution geometries and deformations.

Automated classification of standard echocardiographic views is crucial for efficient clinical workflow but faces three main challenges. First, publicly available datasets are scarce and limited in scale and view coverage. Second, the performance of some modern video-level architectures for echocardiographic view classification remains underexplored. Third, some view categories exhibit highly similar spatial appearances, making single-frame features insufficient for discrimination, while heterogeneous frame quality complicates robust temporal information fusion. To address these challenges, we release the Echocardiographic Videos of Nine Views (EV9V) dataset, comprising 5,138 videos, 910,579 frames, and 9 standard views, which is, to the best of our knowledge, the largest publicly available echocardiography video dataset. Using EV9V, we systematically benchmark representative video classification architectures, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformers. Furthermore, we propose a Spatio-Temporal Fusion Model (STFM), an efficient dual-stream CNN-LSTM (Long Short-Term Memory) framework that jointly captures spatial anatomical structures and temporal cardiac dynamics. The proposed framework leverages uncertainty-aware learning to preferentially sample representative video segments during training and evidence-based fusion during inference, improving robustness to variations in frame quality across echocardiographic videos. Extensive experiments demonstrate that our method achieves competitive performance across diverse video classification models, validating the effectiveness of uncertainty-aware spatio-temporal learning for echocardiographic view classification. The code is available at https://github.com/bgx666/stfm.

Magnetic resonance imaging-signal fat fraction (MRI-SFF) quantifies tissue fat and serves as an established biomarker for metabolic and musculoskeletal disorders. The acquisition requires, however, specialized MRI sequences, which are not available routinely. We investigate whether SFF can be estimated from widely available T2-weighted (T2w) MRI via image-to-image translation (I2I). We further compare a lightweight 4-level U-Net to a state-of-the-art Denoising Diffusion Probabilistic Model (DDPM) using a dataset of 230 048 paired 2D images (183 517 train, 23 621 val, 22 910 test) from the German National Cohort (NAKO). Both models clearly outperform the identity baseline (Pearson correlation r = 0.769, mean absolute error MAE = 0.070 +/- 0.054), which confirms that the models learn a non-trivial cross-modal mapping. Interestingly, the lightweight U-Net outperforms the DDPM in both correlation (r = 0.975 vs. 0.962) and error (MAE = 0.014 +/- 0.015 vs. 0.019 +/- 0.019), while reducing inference time by a factor of 208 (25.2 ms vs. 5 227.2 ms per image using 50 Denoising Diffusion Implicit Model (DDIM) steps). The strong clinical performance at substantially reduced computational cost enables real-time clinical use.

Characterising the tumour microenvironment (TME) from routine H&E-stained histology images requires simultaneous cell segmentation, feature extraction, and interpretable clinical reporting. We present SEGTME-UNI2, a unified framework addressing these requirements. Its core is UNI2-UPERHOVER, a dual-head segmentation model pairing the UNI2-H pathology foundation model (ViT-Giant, pretrained on >100M tiles from 100K slides) with two parallel UperNet decoders: one for six-class semantic segmentation and one for horizontal-vertical gradient regression enabling watershed-based nuclear instance separation. To address the lack of pixel-level annotations in large real-world repositories, UNI2-UPERHOVER undergoes a three-stage progressive pseudo-label curriculum. Each stage trains a fresh model without weight transfer, driving improvement entirely via increased pseudo-label quality: Stage 1: Uses human-annotated PanNuke (7,901 images, 189,744 nuclei, 0.25 um/pixel). Stage 2: Uses entropy-filtered pseudo-labels from the Stage 1 model on 271,711 TCGA-UT scale-0 patches (0.5 um/pixel). Stage 3: Uses pseudo-labels from the Stage 2 model on all 1,608,060 TCGA-UT patches across six resolution scales (0.5-1.0 um/pixel). Segmentation outputs feed a structured TME feature extraction pipeline computing 20+ per-patch compositional, morphological, spatial entropy, and intercellular distance metrics. These are encoded as JSON and passed to a fine-tuned NVIDIA BioNeMo GPT model to generate clinically interpretable TME narratives. Preliminary validation on held-out PanNuke and TCGA-UT partitions demonstrates framework feasibility and internal consistency. The pseudo-labelled TCGA-UT dataset and UNI2-UPERHOVER checkpoint are publicly released to support large-scale TME profiling and spatial biology research.

Medical vision-language models report strong chest radiograph accuracy, and this is increasingly read as evidence that they use the image. That inference is unsafe: a model exploiting finding-name priors scores like one that reads the scan, and no standard benchmark separates them. We introduce a causal audit that intervenes on the image, occluding the relevant region, occluding an irrelevant one, and swapping in another patient's same-label scan, and combines three behavioral metrics to test whether a correct answer depends on the image. Across nine systems, a text-only model with no image access reaches within 5.7 accuracy points of the best multimodal one, and a 119-billion-parameter multimodal model is statistically indistinguishable from a 7-billion text-only baseline. The audit splits the cohort into three models that ignore the image, one that is unstable, and five that use it selectively, for a subset of findings; the categories hold across a second dataset, resolution, and prompt phrasing. Against board-certified radiologists, a text-only model is statistically indistinguishable from a radiologist's accuracy while grounding at zero, whereas the image-using models ground at radiologist-comparable rates. Reported confidence flags ungrounded answers only when a model uses the image. Grounding audits, not accuracy, should gate clinical deployment.

Whole-brain 4D fMRI generation is valuable for modeling functional brain dynamics, yet existing fMRI foundation models mainly target representation learning and downstream prediction rather than conditional predictive generation. We introduce BrainWorld, a structural-prior-conditioned generative model for whole-brain 4D fMRI dynamics. BrainWorld uses sMRI as subject-level anatomical context to guide future fMRI generation, integrating structural information into the denoising process rather than treating it as a parallel modality. Evaluated on 22 datasets spanning diverse cohorts and brain states, BrainWorld generates stable 4D fMRI trajectories up to 400 frames, improves downstream performance through generated-example augmentation, and learns transferable multimodal representations that outperform baselines. Together, these results establish BrainWorld as a condition-aware generative framework for long-horizon brain dynamics modeling and multimodal representation learning.

Patient-specific 3D reconstruction of pelvic organ geometry from MRI is important for pelvic floor modeling and downstream patient-specific analysis. However, while previous studies have focused primarily on either image segmentation or downstream use of 3D models, the reconstruction of high-fidelity, high-quality geometries remains labor-intensive and poorly standardized. The study introduced a hybrid deformable shape modeling framework that integrates deep learning prediction with iterative optimization for the reconstruction of the bladder, uterus, and rectum. The framework consists of three core components: a geometry-aware multi-level deep learning architecture that preserves topological consistency of pelvic organs; a two-stage amortized optimization training strategy that balances global shape capture and local surface refinement; and a holistic synergy mechanism--where iterative optimization provides supervision for deep learning during the training phase, and during inference, deep learning rapidly predicts the global organ morphology, followed by iterative optimization to refine local surfaces and mesh quality. This framework demonstrated marked superiority in geometric fidelity than current mainstream deep learning-based organ reconstruction models. For individual anatomical structures, the reconstructed 3D geometries for the bladder, rectum, and uterus achieved significantly lower Chamfer Distance values and higher Dice Similarity Coefficient scores. In addition, while maintaining high computational efficiency, the proposed architecture yielded superior overall volumetric mesh quality. At the patient level, the framework achieved higher mean values for the 10 worst elements for both minSICN and minSIGE compared to traditional geometric post-processing algorithms.

Despite increasing adoption of multimodal approaches in Alzheimer's Disease (AD) research -- aimed at integrating molecular, structural, clinical, and genetic biomarkers to enhance disease characterization -- the relationships among these modalities remain poorly understood. A systematic analysis of their dynamic interaction is essential for improving disease modeling, identifying redundant assessments, and reducing patient burden and acquisition costs. In this paper, we present a quantitative analysis of multimodal AD biomarkers by integrating tau-PET, structural MRI, cognitive scores (MMSE and CDR), and APOE4 data from 789 subjects drawn from the ADNI dataset. In our analyses, we (A) quantify cross-modal mutual information and explained variance to assess redundancy and predictive dependencies; (B) examine associations between tau topologies and structural atrophy across brain regions to select informative ROIs; (C) perform a statistical decomposition of the tau-cognition association into atrophy-related and atrophy-independent components; (D) and identify a dominant neurodegenerative trajectory that aligns with cognitive decline. This study provides a systematic characterization of cross-modal relationships, improving the interpretability and selection of biomarkers in AD. Code is publicly available at: https://github.com/antonioscardace/Multimodal-AD.

Semi-supervised medical image segmentation has emerged as a dominant research problem in medical image analysis, mitigating annotation scarcity by leveraging consistency regularization on unlabeled data. However, existing approaches operate predominantly via visual pattern matching, relying heavily on pixel-level similarities. This visual-centric dependency often falters in clinical scenarios characterized by the visual-semantic mismatch, where visually similar lesions warrant distinct diagnostic conclusions, thus failing to capture the underlying diagnostic logic used by experts. To address this, we move beyond visual cues and propose CERS (CoT-Enhanced Reasoning Segmentation), a framework that integrates Chain-of-Thought (CoT) reasoning to distinguish pathologically distinct cases. Specifically, we construct a knowledge pool enriched with linguistic reasoning descriptions generated by large language models (LLMs). A semantic-aware reference selection strategy is introduced to identify historical evidence, filtering candidates first by morphology, and then refining them via CoT consistency to eliminate hard negatives. Furthermore, a multi-scale coordinate attention module (MCAM) is designed to effectively fuse this reasoning-derived context into the decoding process. Extensive experiments demonstrate the superiority of CERS against state-of-the-art approaches, particularly in resolving boundary ambiguities and semantic inconsistencies. The code is available at https://github.com/cymasuna/CERS.

Self-supervised DINO models provide strong transferable visual representations, yet applying them directly to image segmentation remains challenging. Existing approaches commonly rely on heavy decoders with complex upsampling, introducing substantial parameter and computational overhead. We observe that introducing scale into DINO features is far more critical than increasing decoder capacity. In this work, we present SegDINO, an efficient segmentation framework that integrates a DINOv3 backbone with lightweight scale modeling. SegDINO introduces Token Pyramid Adaptation (TPA) to reorganize intermediate DINO features into a pseudo multi-scale hierarchy, and Scale-Aware Decoding (SAD) for efficient intra-scale refinement and top-down multi-scale propagation. We further curate PanCT, a new CT dataset containing 284 patients with expert-annotated pancreatic tumors, to assess SegDINO's ability to handle difficult small-lesion cases. Extensive experiments on PanCT and three public benchmarks demonstrate that SegDINO achieves state-of-the-art results with high efficiency. The code is available at https://github.com/script-Yang/segdino_v2.

Multi-contrast magnetic resonance imaging (MRI) provides complementary information for clinical diagnosis. However, acquiring all MRI sequences is often time-consuming and costly. Recent generative models perform cross-contrast synthesis to address this issue by inferring absent contrasts from the available ones. Nevertheless, synthesizing 3D MRI presents significant challenges. Due to the massive volume sizes, operating directly in the pixel space is computationally prohibitive; therefore, a common approach is to first compress the 3D volumes into a latent space and subsequently train generative models in that space. We observe that existing compression architectures face several critical issues: they under-preserve long-range anatomical coherence, discard clinically meaningful semantics, and rely on optimization objectives that lead to over-smoothed reconstructions. Ultimately, these shortcomings compromise the performance of subsequent generative models. In this work, we propose a semantics-first latent modeling framework for 3D MRI reconstruction and cross-contrast synthesis. Specifically, we introduce a Latent Harmonization Encoder (LHE) to capture global anatomical dependencies, ensuring coherent volumetric representations. To mitigate semantic degradation during latent compression, we further design a Semantic Recovery Block (SRB) that injects high-level priors from a self-supervised semantic teacher, enhancing contrast-aware separability in the latent space. Additionally, we propose an Anatomy-aware Frequency Loss (AFL) to adaptively preserve diagnostically relevant high-frequency structures. Extensive experiments on two public multi-contrast MRI datasets demonstrate consistent improvements in reconstruction fidelity and cross-contrast synthesis quality. Our code is available at https://github.com/script-Yang/RSF.

Medical image classification faces a fundamental dilemma: while deep learning models achieve remarkable performance at scale, real-world clinical scenarios often suffer from severe data scarcity due to annotation costs, privacy constraints, and disease rarity. This challenge is particularly pronounced in pathological scar classification, where differentiating keloids from hypertrophic scars requires subtle expert knowledge and labeled images are extremely limited. We propose a novel paradigm that repositions large language models (LLMs) as knowledge-driven feature engineers rather than end-to-end classifiers. We call this framework ScaFE (Scar Feature Engineering). Our key insight is that LLMs encode rich medical knowledge that can be externalized as executable feature extraction code, enabling the transformation of high-dimensional images into low-dimensional, clinically interpretable representations. Specifically, we prompt an LLM with established scar assessment criteria to generate deterministic Python code that extracts features aligned with clinical scoring systems such as the Vancouver Scar Scale. Our approach offers three key advantages: (1) data efficiency, achieving robust performance with limited training samples by decoupling knowledge acquisition from statistical learning; (2) privacy preservation, as raw images are processed locally without exposure to external LLMs; and (3) interpretability, through explicit features grounded in clinical reasoning. Extensive experiments on scar classification demonstrate that our method consistently outperforms end-to-end deep learning baselines or using LLMs as black-box classifiers under limited data conditions, establishing a promising direction for integrating LLMs into data-efficient and clinically transparent medical AI systems.

Predicting immune biomarkers associated with the tumor immune microenvironment (TIME) is critical for advancing precision oncology, yet existing approaches are largely limited to single image modalities and suffer from insufficient resolution and incomplete utilization of complementary clinical and biological information. Here we introduce MixTIME, a multimodal foundation model that leverages a mixture-of-experts (MoE) architecture to integrate pathology foundation models trained across distinct modalities: image only (UNIv2), image text (CONCHv1.5), and image transcriptomic (STPath) representations for pixel-level and slide-level prediction of multiplex immunofluorescence (mIF) protein expression from hematoxylin and eosin (HE) whole-slide images. MixTIME employs a learnable router to dynamically weight expert contributions and is trained with a distribution- and tendency-aware loss function. Benchmarked on two datasets of different scales, MixTIME achieves state-of-the-art performance across 17 protein markers as measured by correlation metrics. The predicted mIF profiles substantially enhance downstream tasks, including spatial domain identification, survival prediction, and AI-assisted pathology report generation validated by expert pathologists from multiple institutes across the world. Furthermore, MixTIME enables longitudinal tracking of protein expression dynamics across clinical time points and reveals protein gene interaction patterns linked to drug resistance and immune suppression in tumor microenvironments. Collectively, MixTIME provides a scalable framework for multimodal biomarker discovery and clinical translation in computational pathology.

Recent advances in multimodal learning, including large language models (LLMs) and vision-language models (VLMs), have demonstrated strong adaptability to natural images. However, extending their use to the medical domain, particularly for volumetric (3D) images, is challenging due to high computational complexity, volumetric dependencies and the semantic gap between visual features and clinical terminology. Naively fine-tuning LLMs on limited medical data often leads to overfitting and clinical hallucination, where linguistic fluency is prioritized over clinical factuality. In this study, we investigate parameter-efficient adaptation strategies for volumetric CT report generation and introduce RAD3D-Prefix, a lightweight diagnostic-prior conditioning framework that minimizes the need for extensive parameter training. This module integrates image embeddings with multi-label diagnostic classification logits, preserving critical clinical details while bridging the semantic gap. By keeping the LLM frozen, our method requires minimal trainable parameters and mitigates the risk of overfitting on small, domain-specific datasets. Through a systematic study spanning LLMs from 96.1M to 1.6B parameters, we find that fine-tuning is most beneficial for smaller LLMs, whereas freezing larger (~1B+ LLMs and training only lightweight projection layers provides a superior trade-off between performance, generalization, and computational efficiency. Across multiple automatic metrics and a clinical reader study, RAD3D-Prefix outperforms comparable parameter-efficient baselines and demonstrates strong out-of-domain generalization while using substantially fewer trainable parameters than fully fine-tuned alternatives.

The full potential of artificial intelligence in tibial plateau fracture characterisation remains unrealised, constrained by a fundamental dependency on labelled datasets whose consistency cannot be guaranteed: conventional classification schemes such as Schatzker and AO/OTA suffer from inter-observer variability, causing supervised models to learn human disagreement rather than stable fracture morphology. We design, implement, and validate a label-agnostic framework that eliminates this constraint by learning fracture representations directly from imaging data without observer-assigned labels. A RadImageNet-pretrained ResNet-50 encoder is fine-tuned on 154 cleaned knee radiographs using the SimCLR contrastive objective, preceded by a data cleaning protocol and followed by UMAP dimensionality reduction and k-means clustering to discover four imaging-derived phenotypes. Phenotype validity is assessed through a blinded expert review protocol administered to two independent clinicians. The four phenotypes demonstrate robust stability (bootstrap ARI = 0.319 +/- 0.041), strong internal cohesion (silhouette = 0.511), and coherence ratings of 3-5/5 from both reviewers under blinded conditions; one phenotype was unanimously identified as exhibiting comminution -- a high-complexity feature isolated without any supervisory signal. Inter-partition comparison against Schatzker labels yields ARI = 0.013, confirming orthogonality to conventional classification boundaries. Notably, expert reviewers anchored to established classification vocabularies perceived imaging-derived groups as heterogeneous precisely where Schatzker alignment was lowest, suggesting that Schatzker-trained perception and label-agnostic embedding geometry measure orthogonal dimensions. These findings establish label-agnostic SSL phenotyping as a reproducible and clinically interpretable complement to conventional classification.

Melanoma is the most dangerous form of skin cancer with five-year survival rates exceeding 99% when detected early but falling sharply once the disease spreads. This paper proposes and evaluates a two-stage fine-tuning approach for ResNet50 applied to binary melanoma classification on dermoscopic images. The core challenges addressed are class imbalance and suboptimal transfer learning from single-stage fine-tuning. After stratified train/validation/test splitting, random oversampling was applied exclusively to the training set to achieve a 1:1 class balance. Stage 1 trained only the classification head with the ResNet50 base frozen, while Stage 2 fine-tuned all layers jointly at a low learning rate of 1e-5 to prevent catastrophic forgetting of learned visual features. On an independent test set of 3,826 images, the model achieved an AUC-ROC of 0.9559, accuracy of 88.34%, sensitivity of 87.56%, specificity of 89.13%, and F1-score of 88.29%. An ablation study confirms the two-stage protocol significantly outperforms single-stage fine-tuning, with sensitivity gains of over 4%. Grad-CAM visualizations demonstrate correct lesion localization. A fully deployable Streamlit detection application is provided alongside all training code.

AI-assisted clinical documentation tools increasingly summarize, standardize, and reformat radiology reports using large language models (LLMs). We present a controlled measurement of the resulting information degradation. Using 450 chest X-ray reports from the Indiana University dataset, we generate synthetic versions via three realistic LLM rewriting tasks: EHR summarization, standardized rewriting, and teaching case preparation. We measure entity erosion (via medical NER), hedging collapse (loss of clinical uncertainty language), and cross-modal alignment degradation (via BiomedCLIP image-text similarity). Our central finding is a dissociation between information loss and cross-modal fidelity. EHR summarization is the most destructive at the content level, eroding 51.4% of clinical entities and 43.7% of hedging language, yet it preserves image-text alignment almost entirely (a 2.5% drop). The two tasks meant to produce cleaner training data, standardized rewriting and teaching case preparation, do the reverse: they preserve more entities (26.8% and 29.3% eroded) but cause 14.9-16.5% alignment drops, six to seven times those of EHR summarization. We term this the slop paradox: rewriting that makes clinical text look cleaner for multimodal training is precisely what pulls it away from the image. Contrary to our pre-specified hypothesis, rare pathologies were not preferentially degraded: across nine rare-versus-common comparisons, no difference survived multiple-comparison correction, and nominal differences ran in the opposite direction (common > rare), so contamination is invisible to condition-specific monitoring. The dominant determinant of degradation is the type of AI rewriting task, not the clinical content. These findings bear on multimodal medical AI dataset construction and the governance of AI-assisted clinical documentation.

Agentic artificial intelligence systems promise to accelerate scientific workflows, but neuroimaging poses unique challenges: heterogeneous modalities (sMRI, fMRI, dMRI, EEG), long multi-stage pipelines, and persistent reproducibility risks. To address this gap, we present NeuroClaw, a domain-specialized multi-agent research assistant for executable and reproducible neuroimaging research. NeuroClaw operates directly on raw neuroimaging data across formats and modalities, grounding decisions in dataset semantics and BIDS metadata so users need not prepare curated inputs or bespoke model code. The platform combines harness engineering with end-to-end environment management, including pinned Python environments, Docker support, automated installers for common neuroimaging tools, and GPU configuration. In practice, this layer emphasizes checkpointing, post-execution verification, structured audit traces, and controlled runtime setup, making toolchains more transparent while improving reproducibility and auditability. A three-tier skill/agent hierarchy separates user-facing interaction, high-level orchestration, and low-level tool skills to decompose complex workflows into safe, reusable units. Alongside the NeuroClaw framework, we introduce NeuroBench, a system-level benchmark for executability, artifact validity, and reproducibility readiness. Across multiple multimodal LLMs, NeuroClaw-enabled runs yield consistent and substantial score improvements compared with direct agent invocation. Project homepage: https://cuhk-aim-group.github.io/NeuroClaw/index.html

Long-term visual acuity (VA) forecasting after anti-VEGF therapy is important for counseling and follow-up planning in diabetic macular edema (DME), yet remains challenging when only early post-treatment findings are available. While prior OCT-based methods mainly focus on short-term response or single-endpoint prediction, multi-horizon VA forecasting from early longitudinal data remains insufficiently under-explored. In this study, we assembled a real-world cohort of 188 anti-VEGF--treated DME patients with paired baseline and month-1 OCT scans, along with tabular OCT-derived biomarkers and non-imaging clinical variables. Using only these early data, we formulate a multi-horizon VA forecasting problem aimed at predicting visual outcomes at 3, 6, 12, 18, and 24 months, reflecting clinically meaningful follow-up intervals. We propose ReVA, a response-aware multimodal framework that combines baseline and month-1 OCT features with tabular variables to capture disease status and early treatment response. ReVA integrates spatial OCT attention, dependency-aware tabular encoding, and cross-modal fusion to predict patient-specific long-term VA trajectories. The proposed framework achieves MAE=0.1246, RMSE=0.1621, and R^2=0.6064 for 24-month VA prediction, with consistent performance across all forecast horizons. Our findings show that incorporating early treatment-response signals enables clinically meaningful long-term visual acuity forecasting, supporting data-driven decision support for routine anti-VEGF management. Code and pretrained models will be released on https://github.com/nguyenpbui/ReVA.

Interpretability is essential for trustworthy medical image diagnosis. However, existing concept-driven interpretable methods have key limitations: Concept Bottleneck Models (CBMs) require scoring all predefined concepts at inference time and for manual intervention, imposing a substantial burden on clinicians, while rationale-based generative approaches often select concepts by class discriminability, which can drift from diagnostic ontologies. To address these issues, we propose Neuro-Symbolic Rule Distillation (NeRD), a framework that produces efficient, ontology-grounded reasoning chains that are sufficient yet non-redundant, without manually crafting diagnostic rules. Experiments on two skin datasets demonstrate strong diagnostic performance and interpretability, and blinded expert evaluation confirms the clinical plausibility of NeRD rationales. Our method further enables a first expert-in-the-loop study for Multimodal Chain-of-Thought-based diagnosis, achieving efficient and effective concept-level intervention.

Post-traumatic epilepsy (PTE) is a severe complication of traumatic brain injury (TBI), yet early identification remains challenging due to the complex structural and functional alterations it induces in the brain. To address this, we propose a dynamic multimodal Mixture-of-Experts (MoE) framework that integrates functional and structural MRI through time-aware functional-structural encoding and class-conditioned expert routing. Within this framework, modality-specific and cross-modal experts learn complementary representations, while a Modality-Class MoE (MCoE) module dynamically dispatches expert weights according to each classification objective. Experimental results across three binary classification tasks demonstrate that the framework consistently outperforms static fusion baselines, and high-interpretability analyses further reveal meaningful region-of-interest (ROI) interactions. This dynamic multimodal expert framework effectively captures class-dependent brain interaction patterns and provides an interpretable approach for PTE diagnosis and risk stratification.

Understanding how cellular morphology, gene expression, and spatial context jointly shape tissue function is a central challenge in biology. Image-based spatial transcriptomics technologies now provide high-resolution measurements of cell images and gene expression profiles, but existing methods typically analyze these modalities in isolation or at limited resolution. We address the problem by introducing SPATIA, a multi-level generative and predictive model that learns unified, spatially aware representations by fusing morphology, gene expression, and spatial context from the cell to the tissue level. SPATIA also incorporates a spatially conditioned generative framework with confidence-aware OT reweighting and morphology-profile alignment for modeling target-state morphology distributions. Specifically, we propose a confidence-aware flow matching objective that reweights weak optimal-transport pairs based on uncertainty. We further apply morphology-profile alignment to encourage biologically meaningful image generation, enabling the modeling of microenvironment-dependent phenotypic transitions. We assembled a multi-scale dataset consisting of 25.9 million cell-gene pairs across 17 tissues. We benchmark SPATIA against 18 models across 12 tasks, spanning categories such as phenotype generation, annotation, clustering, gene imputation, and cross-modal prediction. SPATIA achieves improved performance over state-of-the-art models, improving generative fidelity by 8% and predictive accuracy by up to 3%.

Alzheimer's Disease (AD) is a progressive neurodegenerative disorder that affects millions of older adults, with prevalence expected to rise significantly in the coming years. Early diagnosis, particularly during the mild cognitive impairment (MCI) stage, is critical for timely intervention. Structural Magnetic Resonance Imaging (sMRI) has emerged as a key modality for detecting AD-related brain changes, but traditional graph-based approaches often struggle with modality and inter-site heterogeneity, limiting diagnostic performance. In this paper, we propose Graph Matching Network for Alzheimer's Disease Diagnosis (GMN4AD), designed to model interactions between heterogeneous brain graphs derived from neuroimaging data. Unlike conventional methods that treat each brain graph independently, GMN4AD leverages graph matching to capture cross-graph relationships, enhancing diagnostic precision. Furthermore, we introduce a test-time domain adaptation strategy that combines contrastive learning to mitigate domain shifts during inference. Extensive experiments on three public AD datasets demonstrate that GMN4AD achieves superior performance compared to state-of-the-art methods, offering a robust and generalizable solution for AD diagnosis.

Brain Magnetic Resonance Imaging (MRI) plays a central role in studying neurological development, aging, and diseases. One key application is Brain Age Prediction (BAP), which estimates an individual's biological brain age from MRI data. Effective BAP models require large, diverse, and age-balanced datasets, whereas existing 3D MRI datasets are demographically skewed, limiting fairness and generalizability. Acquiring new data is costly and ethically constrained, motivating generative data augmentation. Current generative methods are often based on latent diffusion models, which operate in learned low dimensional latent spaces to address the memory demands of volumetric MRI data. However, these methods are typically slow at inference, may introduce artifacts due to latent compression, and are rarely conditioned on age, thereby affecting the BAP performance. In this work, we propose FlowLet, a conditional generative framework that synthesizes age-conditioned 3D MRIs by leveraging flow matching within an invertible 3D wavelet domain, helping to avoid reconstruction artifacts and reducing computational demands. Experiments show that FlowLet generates high-fidelity volumes with few sampling steps. Training BAP models with data generated by FlowLet improves performance for underrepresented age groups, and region-based analysis confirms preservation of anatomical structures.

Many digitized corpora suffer from low resources because annotations may be scarce, page scans are noisy and of poor resolution, or layouts are structurally complex in ways that negatively affect the quality of automatic transcription. Developing robust classification models for low-resource languages is inhibited by the lack of large-scale annotated data and by the frequent semantic complexity of page layouts. To this end, we have curated a complex-layout dataset, manually classified into eight distinct layout types based on their separator regions. To overcome data scarcity, we propose a novel training strategy in the form of a CNN-based classifier that employs strong, domain-aware augmentations to improve generalization. We utilize narrow anisotropic Gaussian masking to suppress incidental textual details while preserving essential separations, compelling the model to learn global geometric arrangements. Additionally, we implement reflection-induced label transformations to enrich the training distribution while maintaining label consistency across asymmetric categories. The results demonstrate that layout-specific augmentations can substantially improve page-level layout classification under severe annotation scarcity.

Multi-task table recognition jointly addresses table structure prediction, cell localization, and cell content recognition within a unified framework. Existing approaches often rely on autoregressive decoders to generate table structures and reuse their hidden states for cell localization and content recognition. This autoregressive generation process can make cell representations order-dependent, degrading global consistency across cells. This paper proposes a structural refinement module that produces order-independent cell features through non-causal attention. This design enables parallel inference of cell contents while conditioning each cell on global context encoded in the refined features. Experiments on two large datasets demonstrate consistent gains in cell localization and end-to-end recognition, while reducing overall inference time by around threefold.

Recent advances in visual language models (VLMs) have transformed end-to-end document understanding. However, their ability to interpret the complex layout semantics of historical scholarly texts remains limited. This paper investigates structure-aware text recognition for Ancient Greek critical editions, which have dense reference hierarchies and extensive marginal annotations. We introduce two novel resources: (i) a large-scale synthetic corpus of 185,000 page images generated from TEI/XML sources with controlled typographic and layout variation, and (ii) a curated benchmark of real scanned editions spanning more than a century of editorial and typographic practices. Using these datasets, we evaluate three state-of-the-art VLMs under both zero-shot and fine-tuning regimes. Our experiments reveal substantial limitations in current VLM architectures when confronted with highly structured historical documents. In zero-shot settings, most models significantly underperform compared to established off-the-shelf software. Nevertheless, the Qwen3VL-8B model achieves state-of-the-art performance, reaching a median Character Error Rate of 1.0\% on real scans. These results highlight both the current shortcomings and the future potential of VLMs for structure-aware recognition of complex scholarly documents.

Rapid assessment of building damage from satellite imagery is essential for effective disaster response and recovery. While most deep learning methods rely on spatial-domain features, frequency-domain representations can capture complementary structural cues such as debris patterns and collapse-induced textures. This study presents a controlled comparison of spatial-domain, frequency-domain, and dual-domain deep learning approaches for multi-class building damage classification using post-disaster imagery from the xView2 (xBD) dataset. To ensure fairness, all models are built on an EfficientNet-B0 backbone and trained under identical settings, differing only in their input representations and fusion strategies. Performance is evaluated using accuracy, macro F1-score, per-class metrics, and confusion matrices. Results show that dual-domain models provide measurable improvements over single-domain approaches. The dual spatial configuration achieves the highest test accuracy (0.4688) and lowest loss, while the spatial-only model attains the best macro F1-score (0.4254), indicating more balanced class performance. In contrast, frequency-only models perform worst and exhibit overfitting, suggesting limited generalization. Despite these gains, all models struggle to detect subtle damage levels, particularly the Minor class, due to class imbalance and fine-grained visual ambiguity. While dual-domain approaches improve detection of severe damage, challenges remain. These findings highlight the benefits and limitations of hybrid representations and motivate future work on data balancing, advanced fusion, and regularization.

Image restoration seeks to recover high-quality images from degraded inputs but becomes highly ill-posed under complex, mixed degradations. While unified all-in-one models are common, their performance declines as degradation complexity increases. Recent works adopt Chain-of-Thought (CoT) reasoning for multi-round restoration using specialized modules. However, this approach faces two key limitations: (i) increased computational cost due to multi-step processing, and (ii) weak modeling of interactions between degradations during stepwise inference. We introduce CoTIR, a universal image restoration framework that internalizes CoT reasoning within a single model. Concretely, we view image restoration as a specialized subtask of image editing, which implies that a large-scale pre-trained editing model provides a more favorable optimization starting point. Building on this, we fine-tune the model for restoration and further encode structured CoT-style reasoning into the learning objective via a differentiable formulation inspired by Lagrangian optimization, enabling holistic restoration without chaining specialized restorers. To facilitate training and evaluation, we further present CoTIR-Bench, a large-scale benchmark comprising 5.2 million samples with CoT-style reasoning traces. Extensive experiments on CoTIR-Bench and broad real composite degradation scenes show that CoTIR achieves stronger perceptual quality and more competitive fidelity than both all-in-one models and multi-round restoration methods. The source code is available at https://github.com/gy65896/CoTIR.

Pansharpening aims to generate high-resolution multispectral (HRMS) images by fusing low-resolution multispectral (LRMS) and panchromatic (PAN) observations. Most existing deep learning methods treat pansharpening as fixed-grid prediction, which limits scale adaptation. To address this, we propose GSPan, a framework that introduces 2D Gaussian Splatting (GS) into pansharpening. Instead of directly predicting pixels, GSPan represents band-wise residual details as continuous and learnable 2D Gaussian primitives. We design a Dual-Stream Hierarchical Interaction (DSHI) architecture with a Spatial-Spectral Interactive Attention (SSIA) module to estimate these primitives from complementary PAN and MS observations. The predicted primitives are rendered as a residual detail field and injected into the upsampled MS image. This continuous representation allows GSPan to render fused images on arbitrary target sampling grids without scale-specific retraining. It further enables a Scale-Decoupled Asymmetric Inference (SDAI) strategy, which estimates primitives at a reduced resolution and renders the fused image at the target resolution for efficient large-scene pansharpening. Experiments on QuickBird, GaoFen-2, WorldView-3, and WorldView-3-4K datasets show that GSPan delivers state-of-the-art fusion performance. Moreover, SDAI markedly accelerates inference, achieving a favorable trade-off between computational efficiency and fusion quality. Our results demonstrate the potential of continuous Gaussian residual representations as a flexible and scale-decoupled alternative to fixed-grid prediction.

Existing unsupervised low-light image enhancement methods often encounter local exposure imbalance and color distortion under complex non-uniform illumination. In addition, most Vision Transformers lack an explicit mechanism for modeling the physical priors of illumination degradation. To address these limitations, we propose GLFS, a Gaussian light field splatting-based Vision Transformer that integrates continuous physical illumination modeling from Gaussian splatting into the Transformer architecture. In GLFS, scene illumination is represented by a superposition of anisotropic Gaussian basis functions. Physics-guided biases are introduced into self-attention to adaptively infer a spatial gain field, enabling accurate and uniform restoration under complex illumination. To reduce color bias and structural degradation during enhancement, a color-vector angular loss and a luminance-edge loss are further developed. These losses enforce hue consistency and improve the structural fidelity of local details. Extensive ablation studies and quantitative evaluations show that GLFS provides clear advantages in illumination correction and detail preservation. It achieves state-of-the-art performance and offers a new representation paradigm for low-light image enhancement.

Existing low-light image enhancement methods often face a bottleneck between the representation capacity of illumination-field modeling and computational complexity. To address this issue, this paper proposes an Adaptive Illumination Gaussian Splatting Network (AIGS-Net), an ultra-lightweight architecture for fast low-light enhancement. Unlike conventional static priors, AIGS-Net constructs an input-adaptive 2D Gaussian Splatting illumination field. The opacity of Gaussian basis functions is dynamically modulated by relative luminance statistics of the input image, and spatially varying illumination compensation is rendered through ordered alpha compositing. To guide adaptive illumination compensation efficiently, a zero-parameter nonlinear multiscale contextual encoding module is introduced to extract low-frequency structures and local contrast cues without additional convolutional weights. To suppress noise amplification and sensor-induced color bias, AIGS-Net integrates noise-mask estimation, locked single-channel Gamma mapping, cross-channel consistency regularization, and target color-alignment constraints. Experiments on LOL and LSRW benchmarks show that AIGS-Net improves detail recovery and color fidelity while requiring only approximately 40 learnable parameters, achieving an effective trade-off between enhancement quality and extreme inference efficiency.

Image restoration networks are usually comprised of an encoder and a decoder, responsible for aggregating image content from noisy, distorted data and to restore clean, undistorted images, respectively. Data aggregation as well as high-resolution image generation both usually come at the risk of involving aliases, i.e.~standard architectures put their ability to reconstruct the model input in jeopardy to reach high PSNR values on validation data. The price to be paid is low model robustness. In this work, we show that simply providing alias-free paths in state-of-the-art reconstruction transformers supports improved model robustness at low costs on the restoration performance. We do so by proposing BOA-Restormer, a transformer-based image restoration model that executes downsampling and upsampling operations partly in the frequency domain to ensure alias-free paths along the entire model while potentially preserving all relevant high-frequency information.

Arbitrary-Scale SR (ASISR) remains fundamentally limited by cross-scale distribution shift: once the inference scale leaves the training range, noise, blur, and artifacts accumulate sharply. We revisit this challenge from a cross-scale distribution transition perspective and propose CASR, a simple yet highly efficient cyclic SR framework that reformulates ultra-magnification as a sequence of in-distribution scale transitions. This design ensures stable inference at arbitrary scales while requiring only a single model. CASR tackles two major bottlenecks: distribution drift across iterations and patch-wise diffusion inconsistencies. The proposed SSAM module aligns structural distributions via superpixel aggregation, preventing error accumulation, while SARM module restores high-frequency textures by enforcing correlation-guided consistency and preserving self-similarity structure through correlation alignment. Despite using only a single model, our approach significantly reduces distribution drift, preserves long-range texture consistency, and achieves superior generalization even at extreme magnification.

Remote sensing techniques have been increasingly utilised in aquatic applications in recent years. A common challenge in using optical satellite data is the presence of missing observations due to cloud cover. These data gaps can lead to missed detection of critical events, such as algal blooms, in lakes of high interest to water authorities. As a result, enhancing the completeness of optical satellite datasets is crucial for improving the monitoring and prediction of algal blooms. In this study, we compared a traditional data imputation method (i.e., linear interpolation) with deep learning models for reconstructing missing spectral bands across four lakes with historical records of algal blooms. The deep learning models adopted include CNN-based architectures (i.e., CNN, Inception Resnet, and Autoencoder) and CNN-LSTM-based architectures (i.e., CNN-LSTM, Resnet-LSTM, and Autoencoder-LSTM). Our results demonstrated that deep learning models substantially outperformed the baseline linear interpolation method in imputing spectral band values within artificially masked regions. Among these models, CNN delivered the best performance across most lakes. Furthermore, we evaluated the performance of algal bloom indices (i.e., Green/Red and NDCI) derived from the imputed imagery by comparing them with the observed data. Our results demonstrate that deep learning models are effective for imputing missing data in PlanetScope SuperDove imagery, enabling more reliable applications in water monitoring.

Out-of-distribution (OOD) detection in dynamic open-world environments requires a model to continually adapt to evolving data distributions while generalizing to covariate-shifted inputs and rejecting semantic-shifted OOD examples. Most existing OOD detection methods optimize only the current-step objective and do not explicitly account for how post-deployment environment changes affect future OOD behavior. In this paper, we establish a theoretical grounding for dynamic OOD detection using a reinforcement learning (RL)-guided optimizer that explicitly favors updates that reduce the semantic OOD false positive rate over time. We develop a novel augmented optimizer that uses an RL-guided correction term on top of standard gradient descent (GD) and show its improvement over both future-domain generalization and semantic-OOD rejection. We analyze temporal error decomposition in terms of model-change and environment-change generalization errors and develop a new theoretical framework for comparing the generalization errors under both GD and RL-guided optimizers.

Multi-threat robustness remains a fundamental challenge in deep learning. Although joint adversarial training (JAT) is widely adopted, it suffers from negative transfer under heterogeneous threats, particularly between $\ell_p$-bounded and semantic attacks. Through first-order gradient analysis, we formalize this as gradient incompatibility and theoretically establish the necessity of decoupled optimization. We further reveal that these conflicting threats exhibit separable spectral characteristics in the frequency domain. Motivated by this observation, we propose Threat-aware Frequency Decoupling (TaFD), a two-stage defense framework that reformulates JAT as a frequency-domain divide-and-conquer paradigm. TaFD first discovers latent threat domains via unsupervised clustering of attack spectral prototypes and trains a lightweight classifier for inference-time threat domain identification. Conditioned on the prediction, TaFD employs a Frequency-Conditional Convolution that learns threat-domain-specific spectral masks and routes each sample to the corresponding expert, enforcing structural parameter separation and alleviating optimization conflicts. We validate TaFD on three representative image-classification benchmarks (CIFAR-10, CIFAR-100, and Tiny-ImageNet) and on two representative architectures (the convolutional ResNet and the hybrid-transformer MobileViT). Extensive results demonstrate that TaFD achieves more balanced robustness against heterogeneous attacks than existing JAT and frequency-domain baselines, improving average robust accuracy by approximately 11\% over the strongest baseline while maintaining leading clean accuracy.

Text-guided Open-vocabulary Object Counting (TOOC) enables counting arbitrary object categories specified by text prompts, offering substantially greater flexibility than conventional closed-set counting. However, existing TOOC methods are developed and evaluated primarily on ideal images, while real-world scenes often suffer from adverse conditions such as rain, fog, darkness, and sensor noise, which severely degrade visual quality and impair vision-language alignment. To bridge this gap, we introduce Robust-TOOC, the first benchmark for evaluating TOOC under diverse corruption conditions, which covers six representative degradation types: rain, fog, darkness, Gaussian noise, salt-and-pepper noise, and mixed corruption. To improve robustness while preserving the original counting architecture, we propose Dual-TTT, a dual-architecture test-time training framework for TOOC. Specifically, during test-time training, Dual-TTT updates only the Text-guided Lightweight Denoising module (TL-Denoiser), while keeping the original counting network frozen. Inspired by diffusion models, the TL-Denoiser is optimized to remove corruption-aware noise from image representations under degraded conditions. Since only the TL-Denoiser is trained at test time, Dual-TTT is annotation-free and can be seamlessly integrated into existing TOOC models without modifying their original architecture. Extensive experiments on multiple recent TOOC baselines demonstrate the effectiveness of our method.

The widespread deployment of face recognition (FR) systems exposes personal images shared on social media and public platforms to identity linkage and privacy risks. Existing adversarial privacy protection methods can degrade unauthorized FR performance but are not compatible with generative face editing. Artificial intelligence-driven face editing tools are gaining popularity, which has significantly increased user demand for personalized portrait generation and social sharing. However, current editing methods often preserve identity features, making the edited images still susceptible to tracking by malicious FR systems. Thus, this paper proposes Flux-Guard, a privacy-preserving face editing framework based on adversarial attacks, which integrates face editing and privacy protection within a unified generative process. Specifically, we design a flow trajectory control method to align semantic manipulations with the generative process and introduce latent-space adversarial optimization with an adaptive perceptual-loss-driven weighting strategy, dynamically adjusting adversarial strength to maximize attack effectiveness while preserving visual quality. Extensive experiments demonstrate that Flux-Guard supports face editing while significantly improving attack success rates against cross-domain face recognition models on the CelebA-HQ and LADN datasets. Furthermore, evaluation results for commercial APIs have confirmed its effectiveness in real-world applications. The code is released at https://github.com/JLMWang/Flux-Guard.

Pixel-wise adversarial patches are computationally heavy and often visually detectable, limiting utility in security-critical systems. We present adversarial Voronoi camouflage that optimizes only seed-point locations under fixed, printable palettes using a soft assignment, producing structured, splinter camouflage-like patterns without additional regularization. Evaluated on person detection with COCO-style AP@[.5:.95], naive placement (Inria -> COCO) performs comparably bad, while garment-level application via segmentation mask (3DPeople) results in a significant AP drop. The attack transfers to out-of-domain backgrounds and across detector families (YOLOv9/10/11/12), indicating robustness in black-box settings. Repainting with different palettes largely nullifies the effect, and single-color tweaks show limited tolerance (<=0.17), highlighting a structure-palette coupling. The parameter-efficient, palette-constrained design improves visual plausibility while degrading real-time detector performance. Physical validation and color calibration are left for future work. Code: https://github.com/JensBayer/Voronoi This paper was originally presented at the International Conference on Military Communication and Information Systems (ICMCIS), organized by the Information Systems Technology (IST) Scientific and Technical Committee, IST-224-RSY - the ICMCIS, held in Bath, United Kingdom, 12-13 May 2026.

When vision contradicts text, multimodal large language models (MLLMs) consistently favor text, even when images provide clear evidence otherwise. This bias poses risks for applications requiring visual grounding, yet its cause remains unclear. In this paper, we uncover a surprising finding: models often get it right initially, forming correct vision-based predictions in their intermediate layers, before changing their minds and favoring text in the final output. We call this "late-layer textual override". The visual information is encoded, it simply does not survive to the output. More intriguingly, we find that how predictions change reveals whether they're correct: 85% of failures shift toward text, while 89% of successes shift toward vision. This directional signature enables a simple but powerful intervention: when we detect a confident visual prediction being suppressed, we restore it. We propose CALRD (Conflict-Aware Layer Reference Decoding), a training-free method that recovers overridden predictions at inference time. Experiments across five MLLMs of varying architectures demonstrate up to 9.4% absolute improvements on conflict benchmarks while largely preserving standard performance, without training or external knowledge. It recovers what the model already knew but failed to preserve.

Positional encoding is a fundamental component of Transformer architectures, as it injects information about the spatial or sequential arrangement of inputs. Among recent alternatives to standard absolute and sinusoidal encodings, similarity-based positional encoding (simPE) has emerged as a flexible framework for representing positional structure through pairwise relations. simPE was originally designed for medical imaging applications, where geometric robustness is especially relevant: small rotations naturally arise during image acquisition, induced by imaging instruments, patient positioning, or slight acquisition misalignments. Despite its empirical promise, the theoretical behavior of simPE under geometric perturbations has not been fully characterized. In this paper, we study the robustness of simPE with respect to rotations, combining formal theoretical analysis with experimental validation. We first show that simPE is generally not rotation-invariant. We then prove that, under mild Lipschitz assumptions on the elementary components, simPE is stable under rotational perturbations and derive explicit perturbation bounds in Frobenius norm. We validate these findings experimentally on four controlled datasets--a synthetic Arrow dataset, a synthetic Shapes dataset (four geometric shape categories), a synthetic Digits dataset, and a benchmark image classification dataset (FashionMNIST)--in which training and validation images are kept in a fixed canonical orientation while test images are subjected to increasing rotation angles. Across all datasets, simPE consistently outperforms standard learned positional encoding in terms of accuracy, F1 score, precision, and recall under rotation, particularly in the small-to-moderate angle regime, corroborating the theoretical stability guarantees.

Visual attribution is a fundamental tool for interpreting modern vision and vision-language models, particularly when their decisions must be inspected, diagnosed, or audited. Its goal is to explain how a model's decision depends on local regions of the visual input, typically by assigning an importance ordering over candidate image regions. Given an image partitioned into $n$ regions, faithful attribution can be cast as an ordered subset-search problem, in which progressively inserting the selected regions should recover the target model response as early as possible. Exhaustive search over region subsets incurs exponential cost, while the widely used greedy search still requires a quadratic number of model evaluations, because every selection step rescores all remaining candidates. We propose PhaseWin, an efficient subset-search algorithm for faithful visual attribution. PhaseWin reorganizes greedy region selection into a phased window-search procedure: rather than re-evaluating the full candidate set at every step, it alternates between global candidate screening, adaptive pruning, and localized window refinement, while preserving the essential region-ranking behavior of greedy search. We analyze PhaseWin under monotone evidence-accumulation conditions and show that, under feature-level structural assumptions, it attains controllable linear evaluation complexity together with near-greedy faithfulness guarantees. Extensive experiments on image classification, object detection, visual grounding, and image captioning show that, among all compared attribution methods, PhaseWin reaches high faithfulness with the fewest forward passes, empirically realizing the predicted reduction from $O(n^2)$ to $O(n)$. The code is available at https://github.com/Qihuai27/phasewin-va.

We introduce MM++ (Multilayer Mahalanobis++), a fully unsupervised, strictly post-hoc, and scale-invariant framework for Out-of-Distribution (OOD) detection. To address the trade-off between scale invariance and hierarchical expressivity, MM++ constructs a principled joint feature space. It first identifies discriminative intermediate layers by measuring entropy density drops, which mark the boundaries of sharp semantic compression. By fusing these selected layers with the terminal representation, the framework captures latent cross-layer correlations while mitigating early-layer noise. Crucially, a Ledoit-Wolf regularized tied covariance matrix stabilizes this unified space, enabling reliable distance estimation. Requiring no auxiliary OOD data, classifier fine-tuning, or architectural modifications, MM++ delivers robust performance across distinct architectures for both near- and far-OOD detection.

Agent skills are emerging as an important attack surface in LLM-based systems. Through an empirical study of existing skill scanners, we find that current defenses primarily rely on textual descriptions, manifests, and source code as the main signals for security analysis, which can leave visually conveyed malicious intent insufficiently examined. This creates a practical blind spot: harmful operational instructions hidden in images may bypass scanning while still being recoverable by multimodal agents during deployment. To systematically investigate this threat, we propose SkillCamo, a document-mediated multimodal instruction attack that conceals malicious instructions within images bundled with a skill while rewriting the surrounding documentation to naturally reference those images as part of the normal workflow. Thus, the attack does not rely on the image alone, but on the joint interpretation of textual guidance and visual payload at execution time. To defend against such attacks, we further propose ExecScan, an execution-grounded multimodal scanning module that performs intent extraction, behavior reconstruction, abuse assessment, and deliberative execution simulation over skill artifacts. ExecScan jointly analyzes documentation, code, referenced resources, and visual content to recover hidden instructions, reconstruct executable behavior chains, and identify downstream risks such as exfiltration, destruction, persistence, deception, and privilege escalation. Extensive experiments show that image-hidden malicious instructions challenge existing skill scanners, while ExecScan can improve the skill scanning performance.

In service computing, video classification has become fundamental to many intelligent applications. While Deep Neural Networks (DNNs) have demonstrated excellent performance in recognizing video content, recent studies have shown that DNNs are highly vulnerable to adversarial examples. Thus, understanding adversarial attacks can better respond to emergency situations. In order to improve attack performance, many style-transfer-based attacks and patch-based attacks have been proposed. However, the global perturbation of the former will bring unnatural global colors, while the latter is difficult to achieve success in targeted attacks due to the limited perturbation space. Moreover, compared to a plethora of methods targeting image classifiers, video adversarial attacks remain relatively underexplored. Therefore, to generate adversarial examples with a low budget and to provide them with a higher verisimilitude, we propose a novel black-box video attack framework, called Stylized Logo Attack (SLA). SLA is conducted through three stages. The first stage involves building a style reference set for logos, which can not only make the generated examples more natural, but also carry more target class features in targeted attacks. Then, Reinforcement Learning is employed to determine the style reference and position parameters of the logo within the video, which ensures that the stylized logo is placed in the video with optimal attributes. Finally, perturbations are optimized in a step-by-step manner so as to improve the fooling rate. Experimental results indicate that SLA can achieve better performance than state-of-the-art methods and still maintain good deception effects when facing various defense methods. We believe SLA can raise awareness among the security community about the reliability and security of video classification systems and serve as a memorandum of possible attack methods.

The rapid advancement of generative AI has substantially improved image and video synthesis, amplifying the risk of multimodal visual misinformation. Recent MLLMs have shown promise for transparent AI-generated content detection through reasoning and explanation, yet existing approaches largely treat image and video forensics as isolated tasks, leaving cross-modal synergies underexplored. To address this, we present \textbf{BusterX++}, a unified MLLM for joint image and video detection with interpretable reasoning. We also introduce \textbf{GenBuster-Bench++}, a meticulously curated, difficulty-aligned benchmark containing balanced image and video samples spanning recent generation models and diverse real-world scenarios. Using this controlled setting, we revisit the widely adopted $SFT \rightarrow RL$ post-training paradigm. Notably, our findings demonstrate that a single-stage, pure RL strategy driven strictly by sparse outcome rewards consistently matches or surpasses a strong SFT+RL baseline across both unified and single-modality settings. Our key insight reveals that SFT imposes lower policy entropy, which restricts the policy search space and dampens exploratory freedom. In contrast, single-stage pure RL maintains higher policy entropy throughout training, effectively unlocking the spontaneous emergence of cross-modal capability transfer between image and video forensics. Extensive experiments demonstrate that BusterX++ achieves state-of-the-art performance, highlighting the powerful potential of RL for unified cross-modal visual reasoning.

The primary tools used to monitor and defend object detectors under adversarial attack assume that when accuracy degrades, detection count drops in tandem. This coupling was assumed, not measured. We report a counterexample observed on a single model: under standard PGD, EMS-YOLO, a spiking neural network (SNN) object detector, retains more than 70% of its detections while mAP collapses from 0.528 to 0.042. We term this count-preserving accuracy collapse Quality Corruption (QC), to distinguish it from the suppression that dominates untargeted evaluation. Across four SNN architectures and two threat models (l-infinity and l-2), QC appears only in one of the four detectors tested (EMS-YOLO). On this model, all five standard defense components fail to detect or mitigate QC, suggesting the defense ecosystem may rely on a shared assumption calibrated on a single substrate. These results provide, to our knowledge, the first evidence that adversarial failure modes can be substrate-dependent.

Why do adversarial examples exist, and why do they transfer between models? Existing explanations appeal to high-dimensional geometry, non-robust patterns in the input, and decision boundary structure, but none provides a representation-level mechanism that explains why specific perturbations succeed and why attacks transfer between models. In this paper, we show that adversarial vulnerability can stem from efficient information encoding in neural networks. Specifically, vulnerability can arise from superposition - the phenomenon where networks represent more concepts than they have dimensions, forcing non-orthogonal representation and thus interference. This interference causes perturbations targeting one representation to affect others, creating vulnerabilities determined by interference patterns. In synthetic settings with precisely controlled superposition, we establish that superposition suffices to create adversarial vulnerability. The resulting attacks are predictable: PGD-discovered perturbations align with theoretically optimal perturbations derived from the interference geometry. Models trained on similar data develop similar interference patterns, explaining attack transferability. We then show that successful attacks on image classifiers exhibit the structure predicted by our proposed mechanism. These findings reveal that adversarial vulnerability can be a byproduct of networks' representational compression, complementing existing explanations based on data properties or architectural factors.

Remote-sensing vision-language models (RS-VLMs) have advanced Earth-observation analysis toward visual interpretation and instruction-following, yet fall short of operational geo-intelligence, which demands tool-grounded spatial reasoning and structured, evidence-backed decisions. We introduce GeoDisaster, an operational geospatial disaster reasoning benchmark with 2,921 verified instances across 43 question types and five task families: deforestation monitoring, multi-hazard analysis, building-damage assessment, flood-safe routing, and Sentinel-1 SAR flood monitoring. Instances integrate heterogeneous EO/GIS evidence-optical and SAR imagery, raster masks, vector geometries, road networks, and exposure layers-spanning hazard detection, damage assessment, exposure estimation, and diagnostic report generation. Ground-truth answers are grounded in executable geospatial workflows and deterministic consistency checks, removing the need for language-model annotation. We further propose an orchestrated multi-agent framework with 18 disaster-oriented tools, where role-specialized agents coordinate through explicit execution contracts, aligned via Role-Contract Expectation Alignment (RCEA): failure-aware supervised fine-tuning combined with contract-grounded reinforcement learning over dense step-level signals. Experiments show that GeoDisaster challenges existing RS-VLMs and agentic systems, while RCEA improves tool use, evidence grounding, state consistency, and decision generation.

Large Vision Language Models (VLMs) excel at visual question answering and semantic grounding, but their capacity for autonomous logical reasoning remains underexplored. Existing anomaly benchmarks emphasize visual errors or direct prompting rather than the physical and social common sense needed for open-world deployment. To address this, we introduce LAD-bench, a benchmark of more than 1,000 curated synthetic images with logical anomalies across four domains: Residential, Urban, Collaborative, and Nature. We further propose a Tiered Prompting Protocol based on progressive disclosure, which measures how much explicit assistance a model needs to localize and reason about a logical fault. Evaluating leading foundation models reveals substantial weaknesses: even the best achieves only 70.11% overall accuracy, showing that implicit logical fault detection remains unsolved. Crucially, models often fail to identify anomalies even after receiving explicit hints in deeper tiers. By surfacing these limitations in sequential multimodal reasoning, LAD-Bench offers a rigorous framework for advancing the safety, reliability, and cognitive alignment of autonomous visual systems. Dataset and Code: https://huggingface.co/datasets/SahasraK/LADBench

Standardized evaluation protocols are indispensable for robust benchmarking in remote sensing, particularly as foundation features are increasingly transferred across diverse sensors and complex imaging geometries. In satellite multi-view reconstruction, conventional evaluations relying on unconstrained 2D global matching are often misleading. The Rational Function Model (RFM) and its Rational Polynomial Coefficients (RPC) dictate a curved, height-dependent epipolar geometry that render flat 2D search spaces physically inconsistent. We propose a geometry-faithful and reproducible protocol tailored for the RPC framework. Our approach integrates an RPC-projected 3D consistency metric with a geometry-constrained dense matching proxy, specifically evaluating whether similarity responses remain localized and unique under physically plausible search manifolds. A pivotal finding of our joint reporting strategy is the decoupling of semantic agreement and geometric localization: high cross-view similarity at a projected 3D point does not guarantee reliable matchability in practical inference. Our benchmark demonstrates that incorporating geometric constraints is fundamental to the problem definition in satellite imagery. Furthermore, we show that state-of-the-art 2D backbones remain remarkably competitive against specialized 3D-aware models when subjected to this RPC-consistent evaluation.

Datasets in practical document processing scenarios typically grow over time, and their class annotations undergo continuous refinement. This creates significant re-annotation efforts, which are time-consuming and costly. A promising remedy is to re-annotate only a small subset of available documents manually and apply semi-supervised learning techniques that leverage both labelled and unlabelled data. Although there are numerous approaches to tackle this problem for classification, there exists no adaptation for the problem of re-classifying object detection instances, e.g. for document layout analysis. To this end, we propose Bounding Box Label Propagation (BBLP), a pseudo-labelling framework for object detection. An object encoder integrates visual, textual, and positional embeddings from object detection samples to come up with a joint embedding that can be used for Label Propagation on partially annotated datasets in a plug-and-play fashion. Evaluation results indicate that the proposed approach produces high-quality class annotations of bounding boxes. In the D4LA layout analysis dataset, it achieves a mAP of 54.0%, corresponding to 81.6% of fully supervised performance, while using only 10% labelled data. Our work demonstrates the potential of Label Propagation for object detection and lays the groundwork for reducing manual annotation efforts in real-world document processing applications.

Automated pollen identification from microscopy remains a bottleneck in aerobiology, palaeoecology and biodiversity monitoring, because scalable systems must generalise across specimen preparation, scanner settings and geographic origins while retaining palynological interpretability. To address this gap, we present a million-scale multimodal pollen microscopy resource, Pollen AI Atlas, assembled from pure-species whole-slide bright-field images spanning four geographic origins, four scanner settings and 46 taxon labels across 31 botanical families. Seeded by one manually selected exemplar per source slide, token-level mining and filtering produced 1,511,390 released grain detections with 99.6\% proposal precision in expert-curated test regions. Each detection was paired with machine-generated grain-level morphological captions from five open-weight vision-language models, guided by expert-verified palynological anchors, yielding structured descriptions of aperture systems, wall ornamentation, shape and size. Among the evaluated models, Gemma4 provided the most controlled primary caption set, combining tight length control, no leakage and the strongest text-retrieval performance. Baseline benchmarks with frozen visual features reached 88.16\% top-1 accuracy, while cross-regional retrieval showed that caption-derived text embeddings remained robust when image similarity degraded (mAP@20 0.811 versus 0.262). Released data, annotations, captions, splits, code, and weights provide a benchmark for pollen recognition, cross-regional domain adaptation and domain-specific multimodal microscopy learning.

Recent deep learning methods for Landsat and Sentinel-2 reflectance time series reconstruction remain limited by restricted spectral coverage, limited geographic scalability, or patch-based designs with short temporal contexts. We present HLS-GPT, a large-scale generative pretrained Transformer model for reconstructing NASA Harmonized Landsat Sentinel-2 30 m surface reflectance for all bands, any date, and any pixel location. HLS-GPT uses a hierarchical Transformer architecture to handle the different spectral band configurations of Landsat and Sentinel-2 and operates on single-pixel 12-month time series. To capture geographic and seasonal variability, the model was trained with nine years of HLS time series from more than 0.25 million training pixels across the conterminous United States. A random cropping and masking strategy extracts 12-month periods with varying start dates across epochs, masks 50% of valid observations, and trains the model to reconstruct the masked reflectance values from the remaining observations. Evaluation using more than 62,000 independent test pixels shows robust reconstruction under diverse land surface conditions, including complex crop phenology and sparse, irregular observations. Leave-one-observation-out evaluation achieved reconstruction RMSE below 0.026 for all HLS spectral bands, with relative RMSE below 35% for visible bands and below 13% for other bands. Red-edge band errors were comparable to red and near-infrared errors despite the absence of red-edge bands on Landsat. Sensitivity analyses that randomly masked 10% to 90% of test observations showed only modest degradation when 10% to 50% of observations were masked, with all-band RMSE below 0.028. Image reconstruction over nine independent 109 by 109 km CONUS HLS tiles further demonstrates that HLS-GPT outperforms two conventional methods and the NASA-IBM Prithvi model.

The shift from video generation to interactive world modeling places new demands on data: beyond captioned videos, world models require temporally aligned video-action-language trajectories grounded in the actions, camera motion, states, and events that drive future scene changes. However, such data is difficult to obtain at scale. Web video datasets offer broad visual coverage but lack executable actions and reliable states; robotic datasets provide action and state supervision but are costly and limited in scene diversity; and existing simulators often lack large-scale human-driven interaction trajectories. In this paper, we introduce EgoCS-400K, a large-scale replay-grounded egocentric Counter-Strike dataset for world models, built from public professional CS and CS2 match demos that preserve human gameplay trajectories and enable parsing, replaying, rendering, and temporal alignment. We extract player states, view directions, movements, keyboard/button inputs, view-angle changes, weapon usage, game events, and round-level context, and render clean first-person videos from the same trajectories. EgoCS-400K contains over 400,000 first-person videos and 10,000 hours of gameplay from more than 1,000 matches and 40,000 rounds, covering 13 maps and 10 player viewpoints per round. It supports a range of interactive visual modeling tasks, including action-conditioned future prediction, state- and event-aware scene rollout, replay-grounded captioning, and agent egocentric action understanding. By connecting visual observations with human actions, camera motion, game states, and events at scale, EgoCS-400K serves as a practical bridge between passive web videos, controllable game simulation, and costly real-world embodied data.

Reliable autonomous driving requires vectorized HD maps that are geometrically accurate, semantically rich, and scalable to long-horizon driving. However, existing public HD map datasets are limited in scale, provide sparse semantic attributes, and lack modalities such as aerial imagery that could enable new research directions. We present HRDX, a large-scale dataset for vector HD-map construction, spanning about 40 hours (1,400 km) of minimally overlapping drives, which is several times larger than prior public HD map datasets. Data is captured using six synchronized surround cameras, a 128-beam LiDAR, and centimeter-level RTK GNSS/IMU, and is further complemented by precisely aligned aerial orthoimagery. Annotations cover 10 vector map classes, complemented with over 20 semantic and topological attributes. To evaluate this richer ontology, we introduce the Composite Score (CS) to jointly assess geometric fidelity and attribute correctness. Benchmark experiments show that HRDX's scale improves online vector-map construction, and that aligned aerial imagery provides a useful structural prior: using aerial imagery at training and/or inference improves geometric map quality, while aerial-augmented teachers can transfer part of this benefit to camera-only students without increasing inference-time sensor requirements. HRDX is intended to support reproducible research on large-scale HD-map learning, multimodal BEV fusion, and training-time privileged information. HRDX dataset and benchmarks are available at https://github.com/honda-research-institute/HRDX

Training computer-use agents (CUAs) -- models that interact with graphical desktops through screenshots and keyboard/mouse actions -- requires large-scale, diverse trajectory data collected in full desktop environments. The largest public resource, AgentNet (22.5K human trajectories), leads to negative transfer when used for supervised fine-tuning (SFT): continuing training UI-TARS 7B on AgentNet causes OSWorld success rate to fall from 26.3% to 8-10%. We present ProCUA-SFT, a dataset of 3.1M step-level SFT samples distilled from 93K synthetic trajectories across 2,484 application combinations. The dataset is produced by a fully automated pipeline that (i) synthesizes grounded tasks on live desktops seeded with real-world content -- 912 spreadsheets from SpreadsheetBench, approximately 10K permissively-licensed presentations from Zenodo10K, and multi-application OSWorld configs -- and (ii) verifies each task's feasibility through binary precondition checking before rollout. A single VLM (Kimi-K2.5) serves as goal generator, precondition judge, and trajectory executor, eliminating planner-actor capability gaps. Each trajectory is expanded into step-prefix samples that exactly reproduce the context layout seen at inference time. Fine-tuning UI-TARS 7B on ProCUA-SFT for one epoch yields 45.0% on OSWorld -- an 18.7 percentage-point improvement over the base model and over 35% above AgentNet-trained counterparts. A subset of ProCUA was incorporated into the training data for the Nemotron 3 Nano Omni model, contributing to its computer-use capabilities.

The current trend of applying transfer learning from convolutional neural networks (CNNs) trained on large datasets can be an overkill when the target application is a custom and delimited problem, with enough data to train a network from scratch. On the other hand, the training of custom and lighter CNNs requires expertise, in the from-scratch case, and or high-end resources, as in the case of hardware-aware neural architecture search (HW NAS), limiting access to the technology by non-habitual NN developers. For this reason, we present ColabNAS, an affordable HW NAS technique for producing lightweight task-specific CNNs. Its novel derivative-free search strategy, inspired by Occam's razor, allows to obtain state-of-the-art results on the Visual Wake Word dataset, a standard TinyML benchmark, in just 3.1 GPU hours using free online GPU services such as Google Colaboratory and Kaggle Kernel.

This paper reviews the NTIRE 2024 challenge on image super-resolution ($\times$4), highlighting the solutions proposed and the outcomes obtained. The challenge involves generating corresponding high-resolution (HR) images, magnified by a factor of four, from low-resolution (LR) inputs using prior information. The LR images originate from bicubic downsampling degradation. The aim of the challenge is to obtain designs/solutions with the most advanced SR performance, with no constraints on computational resources (e.g., model size and FLOPs) or training data. The track of this challenge assesses performance with the PSNR metric on the DIV2K testing dataset. The competition attracted 199 registrants, with 20 teams submitting valid entries. This collective endeavour not only pushes the boundaries of performance in single-image SR but also offers a comprehensive overview of current trends in this field.

This paper presents the NTIRE 2025 image super-resolution ($\times$4) challenge, one of the associated competitions of the 10th NTIRE Workshop at CVPR 2025. The challenge aims to recover high-resolution (HR) images from low-resolution (LR) counterparts generated through bicubic downsampling with a $\times$4 scaling factor. The objective is to develop effective network designs or solutions that achieve state-of-the-art SR performance. To reflect the dual objectives of image SR research, the challenge includes two sub-tracks: (1) a restoration track, emphasizes pixel-wise accuracy and ranks submissions based on PSNR; (2) a perceptual track, focuses on visual realism and ranks results by a perceptual score. A total of 286 participants registered for the competition, with 25 teams submitting valid entries. This report summarizes the challenge design, datasets, evaluation protocol, the main results, and methods of each team. The challenge serves as a benchmark to advance the state of the art and foster progress in image SR.

Long-form omni-modal video understanding requires integrating vision, speech, and ambient audio with coherent long-context reasoning. Existing video benchmarks often trade off temporal scale, modality coverage, open-ended interaction, and interpretable scoring. To address this gap, we introduce LongShOTBench, a long video understanding benchmark designed around three coupled goals: holistic omni-modal integration, intent-driven open-ended interaction, and rubric-level diagnosis. It builds single- and multi-turn questions from real viewing scenarios, with systematic tasks probing visual, speech, ambient-audio, temporal, and cross-modal reasoning. Each item includes a reference answer and a weighted criterion-level rubric, letting evaluation identify which perceptual facts, temporal links, modality-grounding requirements, and reasoning steps are satisfied or missed. All samples are manually verified to improve grounding, clarity, and rubric reliability. We also introduce LongShOTAgent, a training-free omni-modal evidence-seeking agent coupling full-video preprocessing with targeted retrieval, query-adaptive segment refinement, and explicit claim verification over visual, speech, and non-speech audio evidence. Its iterative search-refine-verify loop exposes intermediate evidence and lets modality-specific specialists re-analyze relevant moments before answering. We evaluate 105 video-capable models spanning open-source omni-modal models, vision-language systems, audio LLMs, agentic pipelines and closed-source APIs. Current MLLMs remain far from saturating LongShOTBench, while our LongShOTAgent is the strongest training-free system, reaching 66.64% overall. By releasing the benchmark, leaderboard, and method, we provide a shared, interpretable testbed for advancing long-form omni-modal video reasoning. Code, data, and the leaderboard are available at https://longshot.cvmbzuai.com/.

Vision--language models (VLMs) achieve strong performance on many multimodal benchmarks but remain brittle on spatial reasoning tasks that require aligning abstract overhead representations with egocentric views. We introduce m2sv, a scalable benchmark for map-to-street-view spatial reasoning that asks models to infer camera viewing direction by aligning a north-up overhead map with a Street View image captured at the same real-world intersection. We release m2sv-20k, a geographically diverse benchmark with controlled ambiguity, along with m2sv-sft-11k, a curated set of structured reasoning traces for supervised fine-tuning. Despite strong performance on existing multimodal benchmarks, the best evaluated VLM achieves only 65.2% accuracy on m2sv, below human annotators who reach 72.0% on average (and 95% for an expert) with strong inter-annotator agreement ($κ$ up to 0.76). While supervised fine-tuning and reinforcement learning yield consistent gains, cross-benchmark evaluations reveal limited transfer. Beyond aggregate accuracy, we systematically analyze difficulty in map-to-street-view reasoning using both structural signals and human effort, and conduct an extensive failure analysis of adapted open models. Our findings highlight persistent gaps in geometric alignment, evidence aggregation, and reasoning consistency, motivating future work on grounded spatial reasoning across viewpoints.

Vision backbone networks play a central role in modern computer vision. Enhancing their efficiency directly benefits a wide range of downstream applications. To measure efficiency, many publications rely on MACs (Multiply Accumulate operations) as a predictor of execution time. In this paper, we experimentally demonstrate the shortcomings of such a metric, especially in the context of edge devices. By contrasting the MAC count and execution time of common architectural design elements, we identify key factors for efficient execution and provide insights to optimize backbone design. Based on these insights, we present LowFormer, a novel vision backbone family. LowFormer features a streamlined macro and micro design that includes Lowtention, a lightweight alternative to Multi-Head Self-Attention. Lowtention not only proves more efficient, but also enables superior results on ImageNet. Additionally, we present an edge GPU version of LowFormer, that can further improve upon its baseline's speed on edge GPU and desktop GPU. We demonstrate LowFormer's wide applicability by evaluating it on smaller image classification datasets, as well as adapting it to several downstream tasks, such as object detection, semantic segmentation, image retrieval, and visual object tracking. LowFormer models consistently achieve remarkable speed-ups across various hardware platforms compared to recent state-of-the-art backbones. Code and models are available at https://github.com/altair199797/LowFormer/blob/main/Beyond_MACs.md.

Spatiotemporal intelligence in autonomous driving (AD) requires an agent to integrate multi-view observations into a coherent scene representation, maintain object continuity across viewpoints and time, and reason about spatial relations, interactions, and future dynamics. However, existing AD vision-language benchmarks largely focus on single-view, static, ego-centric, or single-source question answering, leaving it unclear whether current Vision-Language Models (VLMs) can truly construct and reason over dynamic driving scenes. We introduce DriveSpatial, a benchmark of 15.6K human-verified QA pairs across 20 tasks from five large-scale AD datasets. DriveSpatial evaluates four abilities: Cognitive Scene Construction, Multi-view Relational Understanding, Temporal Reasoning, and Generalization. Unlike prior benchmarks, DriveSpatial is generated from a dynamic multi-relational scene graph that encodes object states, spatial relations, interactions, camera visibility, and temporal correspondences, enabling QA pairs that enforce genuine cross-view and spatiotemporal reasoning. Evaluating 15 representative VLMs reveals a substantial human-model gap: the strongest model trails humans by 28.4 points, with Cognitive Scene Construction emerging as the key bottleneck. Further diagnostics show that language-only prompting is insufficient, while explicit BEV grounding consistently improves performance. These results suggest that current VLMs lack the scene-construction ability needed for reliable spatiotemporal driving intelligence. DriveSpatial and its construction pipeline will be released to support future research.

Micro-actions are short-duration, low-amplitude subtle body movements at the whole-body level that can reveal latent intentions, involuntary reactions, and fine-grained affective changes. Our previous MA-52 benchmark has provided an important foundation for micro-action recognition, but it remains limited in scale, scene diversity, task coverage, and evaluation protocols. To advance micro-action analysis toward more realistic and comprehensive settings, we introduce MMA-82, a large-scale multi-domain extension of MA-52. MMA-82 expands the label space from 52 to 82 fine-grained micro-action categories and covers four distinct domains, including laboratory interviews, street interviews, psychiatric patient interviews, and emotion-rich television videos, resulting in 77,856 annotated instances from 454 subjects. Built upon MMA-82, we establish two core tasks: Micro-Action Recognition and Multi-label Micro-Action Detection. For recognition, we further define in-domain and cross-domain protocols, including few-shot and zero-shot settings, to evaluate model robustness, transferability, and generalization. Extensive experiments show that current methods still struggle with realistic micro-action understanding, especially under domain shift, long-tailed category distributions, and complex temporal localization. Beyond benchmarking, we investigate the relationship between micro-actions and emotion, showing that micro-actions are strongly associated with emotional states and provide complementary cues to facial micro-expressions for improved emotion recognition. These results demonstrate that MMA-82 serves as a comprehensive and challenging benchmark for realistic micro-action analysis and a valuable resource for human-centered AI. MMA-82 is available at https://lpynow.github.io/MMA-82-AIM/.

Industrial products such as valves and circuit breakers are defined by dense technical specifications that govern procurement, compatibility, and safety across supply chains. These specifications are scattered across multiple heterogeneous product images, including specification tables, nameplates, and technical drawings, yet whether Multimodal Large Language Models (MLLMs) can reliably recover them remains underexplored. To fill this gap, we introduce IndustryBench-MIPU, the first large-scale benchmark for multi-image industrial product understanding, built around structured attribute extraction -- recovering property-value pairs from product images. This task jointly probes text recognition on specification tables and nameplates, visual reasoning over technical drawings, domain knowledge to decode industrial terminology, and cross-image evidence integration to assemble scattered specifications. Concretely, the benchmark comprises 4,559 products across 27,652 images with 103,703 annotations spanning 18 industrial categories, constructed through multi-model consensus and three-tier quality assurance. Evaluating nine MLLMs under both single-image and product-level multi-image settings reveals a stark completeness gap: models achieve high precision (86--94%) but the best recovers only 49.9% of product-level attributes; moving from single-image to multi-image extraction costs 15--34 percentage points of recall. Multi-image completeness, not single-image accuracy, is the core bottleneck. Dataset and code are publicly available.

Fetal brain tissue segmentation from magnetic resonance imaging (MRI) is crucial for studying neurodevelopment, but remains challenging due to data heterogeneity and limited annotations. Domain randomization (DR) has recently emerged as a promising strategy for single-source domain generalization by synthesizing training images with randomized artifacts, contrast, and resolution. In this work, we investigate how to maximize the out-of-domain (OOD) generalization of DR-based methods. We evaluate several synthetic data generation strategies for DR, with a particular focus on our recently proposed framework, FetalSynthSeg. We show that simple Gaussian mixture-based intensity modeling outperforms more complex physics-based simulations, and that intensity clustering (subdividing tissue classes based on intensity) improves OOD robustness. Evaluated on 348 fetal subjects from four sites spanning 0.55-3T and both T1w and T2w contrasts, FetalSynthSeg reaches state-of-the-art performance on several FeTA 2024 testing datasets (80-85 Dice score) and, for the first time, offers robust segmentation on modalities other than T2w for fetal brain segmentation (80 Dice on dHCP-T1w dataset). Compared with state-of-the-art methods such as BOUNTI, nnU-Net ensemble, and the FeTA 2024 winner, FetalSynthSeg delivers comparable or superior accuracy while maintaining strong robustness across domain shifts. Our code, model weights, and Docker image ready for easy inference are available at https://hub.docker.com/r/vzalevskyi/fetalsynthseg.

Incorporating multiple modalities into large language models (LLMs) is a powerful way to enhance their understanding of non-textual data, enabling them to perform multimodal tasks. Vision language models (VLMs) form the fastest growing category of multimodal models because of their many practical use cases, including in healthcare, robotics, and accessibility. Unfortunately, even though different VLMs in the literature demonstrate impressive visual capabilities in different benchmarks, they are handcrafted by human experts; there is no automated framework to create task-specific multimodal models. We introduce Mordal, an automated multimodal model search framework that efficiently finds the best VLM for a user-defined task without manual intervention. Mordal achieves this both by reducing the number of candidates to consider during the search process and by minimizing the time required to evaluate each remaining candidate. Our evaluation shows that Mordal can find the best VLM for a given problem using $8.9\times$--$11.6\times$ lower GPU hours than grid search. We have also discovered that Mordal achieves about 69\% higher weighted Kendall's $τ$ on average than the state-of-the-art model selection method across diverse tasks.

Continual Test-time adaptation (CTTA) continuously adapts the deployed model on every incoming batch of data. While achieving optimal accuracy, existing CTTA approaches present poor real-world applicability on resource-constrained edge devices, due to the substantial memory overhead and energy consumption. In this work, we first introduce a novel paradigm -- on-demand TTA -- which triggers adaptation only when a significant domain shift is detected. Then, we present OD-TTA, an on-demand TTA framework for accurate and efficient adaptation on edge devices. OD-TTA comprises three innovative techniques: 1) a lightweight domain shift detection mechanism to activate TTA only when it is needed, drastically reducing the overall computation overhead, 2) a source domain selection module that chooses an appropriate source model for adaptation, ensuring high and robust accuracy, 3) a decoupled Batch Normalization (BN) update scheme to enable memory-efficient adaptation with small batch sizes. Extensive experiments show that OD-TTA achieves comparable and even better performance while reducing the energy and computation overhead remarkably, making TTA a practical reality.

The data processing inequality is an information-theoretic principle stating that the information content of a signal cannot be increased by processing the observations. In particular, it suggests that there is no benefit in enhancing the signal or encoding it before addressing a classification problem. This assertion can be proven to be true for the case of the optimal Bayes classifier. However, in practice, it is common to perform "low-level" tasks before "high-level" downstream tasks despite the overwhelming capabilities of modern deep neural networks. In this paper, we aim to understand when and why low-level processing can be beneficial for classification. We present a comprehensive theoretical study of a binary classification setup, where we consider a classifier that is tightly connected to the optimal Bayes classifier and converges to it as the number of training samples increases. We prove that for any finite number of training samples, there exists a pre-classification processing that improves the classification accuracy. We also explore the effect of class separation, training set size, and class balance on the relative gain from this procedure. We support our theory with an empirical investigation of the theoretical setup. Finally, we conduct an empirical study where we investigate the effect of denoising and encoding on the performance of practical deep classifiers on benchmark datasets. Specifically, we vary the size and class distribution of the training set, and the noise level, and demonstrate trends that are consistent with our theoretical results.

In this work, we aim to develop effective data synthesis techniques that autonomously synthesize multimodal training data for enhancing MLLMs in solving complex real-world tasks. To this end, we propose Collective Adversarial Data Synthesis (CADS), a novel and general approach to synthesize high-quality, diverse and challenging multimodal data for MLLMs. The core idea of CADS is to leverage collective intelligence to ensure high-quality and diverse generation, while exploring adversarial learning to synthesize challenging samples for effectively driving model improvement. Specifically, CADS operates with two cyclic phases, i.e., Collective Adversarial Data Generation (CAD-Generate) and Collective Adversarial Data Judgment (CAD-Judge). CAD-Generate leverages collective knowledge to jointly generate new and diverse multimodal data, while CAD-Judge collaboratively assesses the quality of synthesized data. In addition, CADS introduces an Adversarial Context Optimization mechanism to optimize the generation context to encourage challenging and high-value data generation. With CADS, we construct MMSynthetic-20K and train our model R1-SyntheticVL, which demonstrates superior performance on various benchmarks.

Mixed reality applications can be designed for hand rehabilitation. Augmented reality (AR) head mounted displays (HMDs) specifically allow for ecologically valid tasks because individuals can see their real environment and interact with real objects while receiving additional cues on the HMD. While these applications rely on accurate hand pose estimation, there is a gap in investigating the influence of hand impairment or occlusion from real-object interactions on pose estimation accuracy. Further, comparisons between AR HMD predictions and state-of-the-art pose estimation methods have not been established. The current study assessed pose estimation accuracy of the HoloLens 2 HMD and state-of-the-art pose estimation algorithms (WiLoR, HaMeR, WildHands, and MediaPipe) while individuals with cervical spinal cord injury (cSCI; n = 13, Neurological Level of Injury: C3-C6; American Spinal Injury Association Impairment Scale: A-D) and 15 uninjured controls interacted with clear and opaque objects. Ground truth estimates of 3D joint positions were generated via triangulation from a multi-camera setup. Pose estimation accuracy did not differ between the cSCI and uninjured control groups suggesting that 3D joint predictions from the HoloLens 2 and pose estimation algorithms can generalize to populations with hand impairment. Further, clear objects provided a small accuracy advantage over opaque objects (0.1 mm) and predictions from both WiLoR and HaMeR were slightly more accurate than the HoloLens 2 (2 mm). Overall, these results suggest that the HoloLens 2 may be viable for hand rehabilitation applications and the dataset generated can be used to refine pose estimation methods for hand-impaired populations.

Optical remote sensing imagery is frequently degraded by cloud and cloud-shadow contamination, which limits its reliability for near-real-time land use and land cover (LULC) mapping. Although synthetic aperture radar (SAR) can provide cloud-penetrating structural information, existing SAR-optical fusion methods often assume reliable optical observations and insufficiently address the semantic uncertainty introduced by cloud contamination. To address this issue, we propose CloudLULC-Net, an end-to-end heterogeneous SAR-optical fusion framework that directly predicts LULC maps from cloud-contaminated Sentinel-2 imagery and temporally adjacent Sentinel-1 SAR observations. The proposed network incorporates optical reliability modulation to suppress unreliable optical responses, heterogeneous information adaptive aggregation to model high-order spatial-channel interactions between optical and SAR representations, and a unified semantic mapping transformer to organize fused features in a LULC-oriented latent space. A semantic anchor-guided optimization strategy is further introduced to improve the consistency of intermediate semantic representations. To support this task, we construct CloudLULC-Set, a large-scale benchmark dataset containing 40,223 curated SAR-optical-label triplets with pixel-level LULC annotations across diverse geographic regions and cloud conditions. Experimental results show that CloudLULC-Net achieves an OA of 86.60%, an F1-score of 83.29%, and an mIoU of 73.51%, outperforming representative heterogeneous reconstruction-first and end-to-end SAR-optical mapping methods. Comparisons with existing global LULC products and analyses under different cloud-cover levels further demonstrate the robustness and practical value of CloudLULC-Net for target-date LULC mapping in cloud-prone regions.The project is publicly available at: https://github.com/RSIIPAC/CloudLULC

We present a survey on 4D generation and reconstruction, a fast-evolving subfield of computer graphics whose developments have been propelled by recent advances in neural fields, geometric and motion deep learning, as well as 3D generative artificial intelligence (GenAI). While our survey is not the first of its kind, we build our coverage of the domain from a unique and distinctive perspective of 4D representations, to model 3D geometry evolving over time while exhibiting motion and interaction. Specifically, instead of offering an exhaustive enumeration of many works, we take a more selective approach by focusing on representative works to highlight both the desirable properties and ensuing challenges of each representation under different computation, application, and data scenarios. The main take-away message we aim to convey to the readers is on how to select and then customize the appropriate 4D representations for their tasks. Organizationally, we separate the 4D representations based on three key pillars: geometry, motion, and interaction. Our discourse will not only encompass the most popular representations of today, such as neural radiance fields (NeRFs) and 3D Gaussian Splatting (3DGS), but also bring attention to relatively under-explored representations in the 4D context, such as structured models and long-range motions. Throughout our survey, we will reprise the role of large language models (LLMs) and video foundational models (VFMs) in a variety of 4D applications, while steering our discussion towards their current limitations and how they can be addressed. We also provide a dedicated coverage on what 4D datasets are currently available, as well as what is lacking, in driving the subfield forward. Project page:https://mingrui-zhao.github.io/4DRep-GMI/

The study of representations is widespread across fields, including neuroscience, psychology, and artificial intelligence. While representations are often studied and compared through similarities between stimuli, current methods provide only limited access to the dimensions that shape these representations and are often limited in interpretability. To overcome these challenges, here we introduce Similarity-Based Representation Factorization (SRF), a general computational method for recovering low-dimensional, non-negative, interpretable embeddings from similarity matrices derived from measured data. Across simulations and many neural, behavioral, and computational datasets, SRF recovers interpretable dimensions from diverse forms of representational data, even for very sparsely sampled, incomplete data. The dimensions derived from these datasets match those obtained by task-specific models, predict independent behavioral properties, improve exploratory analysis, and offer higher power for confirmatory hypothesis testing than comparing similarity matrices. Together, these results establish SRF as a general-purpose method with broad applications for uncovering, understanding, and using the dimensions underlying representations.

World Model, the algorithmic simulator of the real-world environment which biological agents experience and act upon, has been an emerging topic in recent years due to the rising need to develop virtual agents with artificial (general) intelligence. There has been much discussion on what a world model really is, how to build it, how to use it, and how to evaluate it. In this essay, starting from the imagination in the famed Sci-Fi classic Dune, and drawing inspiration from the concept of ``hypothetical thinking'' in psychology literature, we argue the primary goal of a world model to be {\it simulating all actionable possibilities of the real world for purposeful reasoning and acting}. We examine the key design dimensions of world modeling: data, representation, architecture, learning objective, and usage, surveying existing approaches and analyzing their tradeoffs. Building on this examination, we propose a new Generative Latent Prediction (GLP) architecture for a general-purpose world model, based on stateful, hierarchical, multi-level, and mixed continuous/discrete representations, and a generative and self-supervised learning framework, with an outlook of a Physical, Agentic, and Nested (PAN) AGI system enabled by such a model.

The quality of the user experience has become one of the most important aspects in todays world, as it directly influences individuals willingness to continue using or abandon a product or service. In this context, video conferencing applications (VCAs), which experienced widespread adoption following the COVID-19 pandemic, must deliver excellent performance to remain competitive in an increasingly crowded market. Although content providers (CPs) such as Zoom, WhatsApp, Telegram, and Google Meet can assess conversation quality by comparing transmitted and received data. The widespread use of end-to-end encryption in VCAs makes quality-of-experience (QoE) evaluation by internet service providers (ISPs) far more challenging. Since ISPs do not have access to the encrypted content, they must rely on passive measurements of unencrypted traffic characteristics on the data path. In this work, we present a simple yet effective QoE prediction framework based on an almost stock convolutional neural network (CNN) architecture that uses only the packet sizes extracted from the communication between two participants in a video conferencing (VC) call to predict two QoE metrics: BRISQUE and MOS. The proposed framework is simple, easy to implement, and does not require high-end computational resources, yet it provides superior prediction performance, as shown in our experiments on two custom datasets collected from WhatsApp and Zoom, which achieve substantial improvements over previous models for the QoE prediction task.

Rich and accurate medical image segmentation is poised to underpin the next generation of AI-defined clinical practice by delineating critical anatomy for pre-operative planning, guiding real-time intra-operative navigation, and supporting precise post-operative assessment. However, commonly used learning methods for medical and surgical imaging segmentation tasks penalise all errors equivalently and thus fail to exploit any inter-class semantics in the label space. This becomes particularly problematic as the cardinality and richness of labels increases to include subtly different classes. In this work, we propose two tree-based semantic loss functions which take advantage of a hierarchical organisation of the labels. We further incorporate our losses in a recently proposed approach for training with sparse, background-free annotations to extend the applicability of our proposed losses. Extensive experiments are reported on two medical and surgical imaging segmentation tasks, namely head MRI for whole brain parcellation with full supervision and neurosurgical hyperspectral imaging for scene understanding with sparse annotations. Results demonstrate consistent improvements over the evaluated task-specific baselines, with the strongest support for the Wasserstein-based compound loss in whole-brain parcellation and for hierarchy-weighted top-level supervision in the sparse HSI setting.

Safe autonomous agents and mobile robots need fast real time 3D perception, especially for vulnerable road users (VRUs) such as pedestrians. We introduce a new bird's eye view (BEV) encoding, which maps the full 3D LiDAR point cloud into a light-weight 2D BEV tensor with three height bands. We explicitly reformulate 3D detection as a 2D detection problem and then reconstruct 3D boxes from the BEV outputs. A single network detects cars, pedestrians, and cyclists in one pass. The backbone uses area attention at deep stages, a hierarchical bidirectional neck over P1 to P4 fuses context and detail, and the head predicts oriented boxes with distribution focal learning for side offsets and a rotated IoU loss. Training applies a small vertical re bin and a mild reflectance jitter in channel space to resist memorization. We use an interquartile range (IQR) filter to remove noisy and outlier LiDAR points during 3D reconstruction. On KITTI dataset, TriBand-BEV attains 58.7/52.6/47.2 pedestrian BEV AP(%) for easy, moderate, and hard at 49 FPS on a single consumer GPU, surpassing Complex-YOLO, with gains of +12.6%, +7.5%, and +3.1%. Qualitative scenes show stable detection under occlusion. The pipeline is compact and ready for real time robotic deployment. Our source code is publicly available on GitHub.

Tuning of gate-defined semiconductor quantum dots (QDs) is a major bottleneck for scaling spin qubit technologies. We present a deep learning (DL) driven, semantic-segmentation pipeline that performs charge auto-tuning by locating transition lines in full charge stability diagrams (CSDs) and returns gate voltage targets for the single charge regime. We assemble and manually annotate a large, heterogeneous dataset of 1015 experimental CSDs measured from silicon QD devices, spanning nine design geometries, multiple wafers, and fabrication runs. A U-Net style convolutional neural network (CNN) with a MobileNetV2 encoder is trained and validated through five-fold group cross validation. Our model achieves an overall offline tuning success of 80.0% in locating the single-charge regime, with peak performance exceeding 88% for some designs. We analyze dominant failure modes and propose targeted mitigations. Finally, wide-range diagram segmentation also naturally enables scalable physic-based feature extraction that can feed back to fabrication and design workflows and outline a roadmap for real-time integration in a cryogenic wafer prober. Overall, our results show that neural network (NN) based wide-diagram segmentation is a practical step toward automated, high-throughput charge tuning for silicon QD qubits.

Dynamic extensions of 3D Gaussian Splatting (3DGS) achieve high-quality reconstructions through neural motion fields, but per-Gaussian neural inference makes these models computationally expensive. Building on DeformableGS, we introduce Speedy Deformable 3D Gaussian Splatting (SpeeDe3DGS), which bridges this efficiency-fidelity gap through three complementary modules: Temporal Sensitivity Pruning (TSP) removes low-impact Gaussians via temporally aggregated sensitivity analysis, Temporal Sensitivity Sampling (TSS) perturbs timestamps to suppress floaters and improve temporal coherence, and GroupFlow distills the learned deformation field into shared SE(3) transformations for efficient groupwise motion. On the 50 dynamic scenes in MonoDyGauBench, integrating TSP and TSS into DeformableGS accelerates rendering by 6.78$\times$ on average while maintaining neural-field fidelity and using 10$\times$ fewer primitives. Adding GroupFlow culminates in 13.71$\times$ faster rendering and 2.53$\times$ shorter training, surpassing all baselines in speed while preserving superior image quality.