We introduce T2Mo, a feed-forward framework for controllable dynamic 3D shape generation conditioned on 3D trajectories and text. Due to the inherent ambiguity of language, generating precisely intended motions using text alone remains challenging. To address this, we adopt 3D trajectories as controllable spatial guidance, specifying the exact paths along which selected points should move. By combining both, T2Mo generates object motions that spatially adhere to the given trajectories while globally reflecting the text semantics. To robustly handle trajectory inputs with arbitrary configurations, ranging from dense to sparse and unevenly distributed, we further propose a shape-grounded trajectory embedding that maps an input trajectory set into a shape-aware token set covering the entire object. We conduct extensive comparisons against text-based baselines and cascaded video-based baselines that combine trajectory-guided video generation with video-to-dynamic mesh generation. Quantitative and qualitative evaluations, along with user studies, demonstrate that our approach produces motions that more faithfully follow the given prompts with higher expressiveness while preserving motion quality.

Vehicle body type is a significant determinant of cyclist injury severity in overtaking crashes, yet automated tools for classifying vehicles into injury-risk-relevant categories from naturalistic roadway video do not exist in the open literature. Standard object detection benchmarks provide only coarse vehicle labels (car, truck, bus, motorcycle), while existing fine-grained recognition systems are trained on controlled imagery and lack evaluation for deployment robustness across recording sites. This paper presents an open-source two-stage computer vision pipeline combining a pre-trained RT-DETR detector for coarse vehicle localization with a fine-tuned Vision Transformer (ViT-Base/16) for six-category body-type classification: passenger car, SUV, pickup truck, minivan, large van, and commercial truck. A confidence-based abstention mechanism withholds Stage 2 predictions when softmax output falls below 0.60, producing unknown labels rather than silent misclassifications. Evaluated on 3,805 annotated overtaking events from a bicycle-lane corridor in Ann Arbor, Michigan (in-distribution), the pipeline achieved 0.94 accuracy with per-class F1 scores from 0.91 (minivan) to 0.97 (SUV). On an independent out-of-distribution evaluation of 311 events from an open cycling dataset without retraining, accuracy was 0.89. Three of four well-represented categories maintained F1 at or above 0.90 under domain shift. The largest degradation was observed for minivan (F1 = 0.72), driven by abstention rate rising from 2.4% to 25.0% rather than active misclassification, consistent with the mechanism propagating genuine model uncertainty. The full pipeline, including inference scripts, training code, evaluation utilities, and model weights, is released as open-source software to support reproducibility and reuse across roadside video archives and cycling safety research.

Recent developments in multi-view image editing with generative models have brought us a step closer toward general 3D content generation and customization. Most existing works focus on rigid or appearance-only edits by utilizing the geometry of the unedited scene. This naturally limits these methods to edits that preserve the underlying scene structure. Other approaches are trained for specific image editing tasks, such as object removal and addition. Despite this progress, general nonrigid edits, i.e., edits that substantially change the scene geometry, remain challenging for existing methods. We propose GeM-NR, a fast and flexible training-free approach for general multi-view consistent image editing, including edits that drastically change the geometry and appearance of the scene. Given an anchor image edited with a chosen backbone editor (such as FLUX, Qwen, BrushNet) and a query unedited image, GeM-NR edits the query image consistently with the anchor edit. The method incorporates multiple stages: (i) depth map estimation, where we propose a strategy to maximize the alignment between the 3D point clouds of the edited and unedited scenes, (ii) projection onto a query viewpoint, and (iii) refinement of the obtained image conditioned on the unedited query. The conditioning-based formulation scales well from two to many views of an object. We demonstrate the ability of our method to handle edits with significant changes in geometry and appearance, something that existing methods struggle with. We perform an extensive evaluation showing that our method improves consistency for a wide variety of edit tasks, including generating 3D representations of the edited scene. Both quantitative and qualitative results indicate the state-of-the-art performance of our method in terms of edit quality as well as geometric and photometric consistency across multiple views.

After the success of 3D Gaussian Splatting (3DGS) for novel view synthesis, many works have explored how to also use it for geometric surface representation. However, extracting accurate geometric information directly from 3DGS remains challenging and can often reduce the appearance rendering quality. In this work, we show that 3DGS in its default form is inheritedly unsuited to represent texture and geometry at the same time, by training with complete ground-truth texture and geometry information. We also propose a simple solution by applying a single additional geometry opacity parameter to each splat, together with an optional transparency-curated optimization pipeline. Our experiments, both with ground-truth and vision foundation model geometric input, show that this change leads to improved rendering and geometry performance on a wide variety of dataset, and especially complex scenes with transparent objects benefit significantly from our method.

Children learn the meanings of words from a continuous, temporally structured stream of egocentric experience. Recent work shows that neural networks can also learn word-referent mappings from a child's egocentric video recordings, but they cycle through the shuffled data for hundreds of epochs, contrasting with how children actually encounter their environment. We introduce BabyCL, a continual multimodal learning framework that processes the SAYCam dataset in a single chronological pass, combining streaming visual representation learning with an image-text contrastive objective. BabyCL combines a multi-stage temporal segmentation of the stream with a dual replay buffer that independently manages visual and multimodal histories, and it is jointly trained with three contrastive losses on a shared backbone. Under a matched optimization budget, BabyCL outperforms streaming learning baselines on the SAYCam Labeled-S 4AFC benchmark, substantially narrowing the gap to an upper bound of offline training. Ablations show that the gains are robust to the length of the online temporal segmentation window and the eviction rule of the replay buffer. Together, these results show that meaningful word-referent mappings can emerge under training conditions much closer to a child's actual experience.

We propose a label-free approach to adapt powerful but generic vision foundation models to specialized scientific domains. Standard supervised fine-tuning is often ill-suited to these settings: labels are scarce, and task-specific training can collapse the model's generality and hurt robustness. We instead leverage metadata to adapt representations to new domains in a self-supervised manner. Our method, FINO, combines a standard self-supervised objective with flexible metadata guidance that handles both highly granular discrete metadata and continuous metadata. It encourages the representation to preserve informative factors while suppressing spurious ones. Across subcellular fluorescence microscopy, Earth observation, wildlife monitoring, and medical imaging, FINO consistently outperforms standard unsupervised domain adaptation and fully supervised adaptation. It also exceeds highly-specialized domain-specific state of the art, while using no task labels for backbone adaptation and only lightweight probes for supervision.

The Nancy Grace Roman Space Telescope (Roman), set for launch as early as September 2026, will conduct wide-field infrared imaging surveys with unprecedented spatial resolution and cadence, enabling the discovery of millions of astronomical transients. Hence, it is necessary to have automated pipelines for generating alerts in place so that the telescope can begin discovering reliable transients and variable objects soon after it is launched. However, no real Roman data currently exist, making the development of such pipelines difficult. In this work, we present a machine learning model $RuBR$ and a general methodology for distinguishing genuine transient and variable detections from spurious (bogus) detections within the RAPID pipeline. In particular, we present three models using this methodology: $RuBR_{comb}$ trained and tested on combined locally injected and OpenUniverse2024 transients, $RuBR_{loc}$ trained on locally injected transients and tested on OpenUniverse2024 transients, and $RuBR_{DA}$ that combines locally injected transients with a fraction of OpenUniverse2024 transients in domain-adaptation mode for training. This paves the way for strategies to adapt the $RuBR_{comb}$ model to real observations in the absence of any ground-truth labels during the early phases of the Roman mission. While the image differencing pipeline continues to be improved, our experimental results demonstrate the effectiveness of the proposed approach and its promise for robust real-bogus classification in the Roman era.

Language-guided photo retouching aims to adjust color and tone while preserving geometry and texture. Recently, diffusion-based retouching shows a superior visual quality, but often struggles with both fidelity issues due to its generative nature and efficiency because of its iterative sampling process. In this work, we propose an efficient and fidelity-preserving retouching method using bilateral space manipulation, which is both compact and content-decoupled. Specifically, instead of directly editing pixels or image latents, our model predicts a low-resolution bilateral grid of affine transforms, which are sliced using a learned guidance map and then applied to the full-resolution image. This approach yields both high fidelity and improved efficiency. To retain strong priors of a pretrained generative model, we distill a multi-step diffusion model into our bilateral grid framework using Variational Score Distillation, complemented by a prompt alignment loss to guide instruction-following behavior. Additionally, we introduce a new benchmark and evaluate our method across multiple dimensions: fidelity, instruction following, and efficiency. Compared to the latest retouch methods, like Gemini-2.5-Flash (Nano-Banana), our method can avoid content drift, significantly improve latency, and generate visually pleasing edits, while maintaining a high level of fidelity. Project page: https://openimaginglab.github.io/InstantRetouch/.

Conventional Generative Adversarial Networks (GANs) for Single Image Super-Resolution (SISR) often struggle with hallucinated artifacts, largely because standard discriminators evaluate overall image naturalness rather than strict conditional realism. To address this, we propose MaCo-GAN, a novel manifold-contrastive GAN framework that replaces the conventional adversarial loss with a supervised contrastive objective. A core component of our method is a dynamic fake sample synthesizer that transforms ground truth (GT) data into a spectrum of challenging, perceptually plausible fake images that strictly maintain low-resolution (LR) correspondence. Utilizing these synthesized samples, we establish a robust contrastive minimax game: the generator is trained to attract its predictions toward on-manifold fakes (low distortion) and repel them from off-manifold fakes (high distortion), while the discriminator optimizes the exact opposite. By simply replacing the adversarial loss of a baseline SR model with our proposed objective, we demonstrate consistent improvements in the perception-distortion trade-off across various benchmarks. Extensive ablation studies validate the effectiveness of our framework and provide deep insights into the dynamics of this conditional contrastive game.

Computer-Aided Design (CAD) underpins modern engineering and manufacturing by enabling the creation of precise, editable 3D models. However, CAD research typically studies tasks in isolation, and multi-modal, multi-task learning for CAD is hindered by the absence of a unified benchmark. To address this gap, we introduce UniCAD, a comprehensive benchmark for multi-modal CAD learning that covers point-to-CAD reconstruction, text/image-to-CAD generation, and CAD question answering across diverse input modalities. Alongside the benchmark, we present UniCAD-MLLM, a universal multi-modal large language model that ingests text, images, sketches, and point clouds and performs these heterogeneous tasks in an end-to-end fashion within a single framework. Extensive experiments on the UniCAD and Fusion360 benchmarks demonstrate that UniCAD-MLLM achieves state-of-the-art performance across all tasks, outperforming existing task-specific and multi-task baselines. We will release the dataset, code, and pretrained models to accelerate future research.

Long-horizon online visual mapping is a core capability for robot perception, requiring continuous camera-motion and scene-geometry estimation from visual streams under bounded memory and computation. Recent feed-forward 3D reconstruction models provide strong geometric priors, but their streaming variants often predict poses in a fixed coordinate system tied to the first frame or a persistent scene memory. This fixed-gauge design leads to train--test mismatch, attention bias toward early anchors, and accumulated drift on sequences much longer than those seen during training. We propose \emph{Anchor3R}, a streaming 3D reconstruction framework that treats feed-forward reconstruction as current-centric local measurement prediction rather than persistent global-gauge regression. At each time step, Anchor3R predicts window-relative poses and a local pointmap in the current-frame coordinate system, turning streaming reconstruction into relative-pose measurement generation. These measurements support online pose updates, while loop-closure reinsertion and motion averaging align the trajectory and transform local pointmaps into a coherent global reconstruction. Experiments on indoor, outdoor, driving, and RGB-D benchmarks show that Anchor3R improves long-horizon pose accuracy and dense reconstruction quality over existing streaming baselines, while supporting bounded-memory online inference.

Generative visual models fundamentally struggle with precise spatial control. This arises from a core disconnect: models can process textual descriptions of space but cannot directly map numerical coordinates onto the 2D image canvas. We introduce MetaPoint, a method that bridges this gap by representing a continuous 2D coordinate as a single, special token. Crucially, MetaPoint requires no new architectural components; it directly leverages the model's inherent positional encoding schemes to interpret these coordinates, treating our token as a virtual point on the canvas. This lightweight approach enables pixel-level control of an object's position with one token or its bounding box with two, all without requiring architectural changes or bespoke attention masking. The MetaPoint tokens are designed to be compositional, serving as spatial primitives. This allows a planner agent to decompose a high-level user request into a structured sequence of primitives for the generator. By providing a simple, precise, and scalable building block for spatial control, MetaPoint unlocks more powerful compositional generative agents and enables intuitive, interactive editing systems.

Popular initiatives and referendums are central to Swiss democracy, yet the validation of handwritten signature lists remains a labor-intensive manual process. This paper investigates the potential of automated document analysis methods, including OCR and AI-based handwriting analysis, to support this task. We propose a pipeline combining template-based line segmentation with text recognition and writer retrieval techniques, evaluated on a dataset of 443 handwritten entries from 418 writers. Results show that OCR struggles with out-of-vocabulary handwriting, with a CER of 29.6% for first names. In contrast, writer retrieval performs more robustly, reaching an mAP of 50.6%. Furthermore, our experiments indicate that off-the-shelf OCR systems are not sufficiently reliable for transcription of handwritten signature data, particularly for short, out-of-vocabulary entries such as names or addresses. However, writer retrieval methods can effectively identify visually similar entries across signature lists, making them a suitable tool for supporting the detection of potential duplicate submissions based on handwriting similarity.

Cross-view geo-localization estimates the geographic location of a ground image by matching it against an aerial image database. Existing methods tackle this through either large-scale retrieval or precise pose estimation, but not both: retrieval-based methods enable wide-area search at the cost of localization accuracy, while pose estimation methods achieve high precision within only a narrow search space. Naively cascading these pipelines introduces error propagation and inconsistent feature representations. We formulate cross-view geo-localization as a unified problem requiring simultaneous city-scale retrieval and precise 3-DoF pose estimation. We propose CIPER (Cross-view Image-retrieval and Pose-estimation transformER), a single architecture that jointly performs both tasks through mutually beneficial feature learning. CIPER uses a shared transformer encoder with task-specific tokens to disentangle global retrieval features from spatial localization cues. To bridge the large domain gap between ground and aerial views, we introduce a two-way transformer pose decoder that uses ground features as spatial queries for bidirectional cross-attention. A set prediction strategy further enables stable 3-DoF regression under a unified multi-task objective. Experiments on VIGOR, KITTI, and Ford Multi-AV demonstrate competitive performance, especially under limited field-of-view and arbitrary orientation conditions. Code is available at https://github.com/yurimjeon1892/CIPER.

As multi-modal models advance towards long-form video understanding, memory emerges as a critical capability. Despite substantial efforts in developing video datasets and benchmarks, existing works primarily focus on perception and reasoning, without systematically evaluating memory: what models retain, how faithfully information is preserved, and how robust memory remains under interference. To address this gap, we introduce M$^3$Eval, the first comprehensive evaluation framework and benchmark for probing different memory dimensions in multi-modal models. Grounded in cognitive psychology, our design features carefully constructed tasks that isolate key aspects of memory. Leveraging M$^3$Eval, we conduct extensive experiments across representative multi-modal models, revealing consistent weaknesses and distinctive behaviors. We find that models struggle to maintain disentangled representations when processing parallel video streams, exhibit interference patterns differing substantially from those observed in human memory, ground memory sources more reliably in the spatial domain than the temporal domain, and demonstrate limited symbolic memory. Collectively, our benchmark provides a valuable resource for future research, while our findings highlight memory as a fundamental yet underexplored capability and offer insights for designing more effective memory mechanisms in multi-modal models. Our code and dataset are available at https://pku-value-lab.github.io/m3eval-homepage.

The handling and assembly of instruments during surgery imposes high cognitive demands on scrub nurses, particularly when instruments are unfamiliar. We present a supporting guidance system for surgical instrumentation that combines multi-camera 6D pose estimation with augmented reality in-situ visualization on a head-mounted display without the requirement for additional markers. Pose estimation and consecutive camera calibration are achieved through known objects. The 6D pose estimation network is trained purely on synthetic data, aiming for better generalizability and real-world applicability. The AR guidance displays tooltip localization cues and step-wise assembly animations. Via gaze-based selection and a foot pedal, users can switch between assembly steps in intraoperative use. In a technical evaluation, our approach outperforms state-of-art 6D pose estimation. A user study with 29 scrub nurses was conducted in a surgical simulation of knee arthroplasty, comparing the system against a paper manual. AR guidance significantly reduced the perceived workload compared. Objectively, AR guidance reduced task completion time by 21.3\% (4.76 minutes). Specifically, scrub nurses less experienced with the instrument set benefited when using the system. Error frequencies were comparable between conditions. Qualitative feedback highlighted improved process clarity, reduced information overload, and perceived independence. To summarize, our marker-free multi-camera AR guidance approach for surgical instruments can, subjectively and objectively, improve intraoperative instrumentation performance, particularly for untrained scrub nurses.

Recent studies have explored Vision-Language Models (VLMs) for food analysis. However, most existing methods rely primarily on supervised fine-tuning (SFT), which often limits reasoning and generalization capabilities. Moreover, high-quality large-scale nutritional annotations remain scarce. To address these issues, we introduce CalorieBench-80K, a large-scale benchmark with curated calorie labels and dietary advice annotations. To the best of our knowledge, it is the first food image benchmark to incorporate Chain-of-Thought (CoT) annotations for calorie reasoning. We also propose Food-R1, a unified food VLM trained in a multi-task learning paradigm to equip the model with broad capabilities. Food-R1 undergoes CoT-based cold-start instruction tuning, followed by reinforcement fine-tuning (RFT) using Group Relative Policy Optimization (GRPO) to improve reasoning and performance. Experiments on CalorieBench-80K and representative benchmarks show that Food-R1 consistently outperforms strong baselines across food-related tasks. The code, model weights, and benchmark annotations are available at the project repository.

We envision a proactive multi-modal assistant system which gives users real-time step-by-step guidance on a procedural task, autonomously deciding \textit{when} to interrupt, and \textit{how} to coach. However, progress is limited by the absence of large-scale, cross-domain benchmarks that reflect realistic conditions, particularly the common case in which users deviate from the expected step sequence. We address this gap with four contributions: \textbf{(1)}~we release \textbf{EgoProactive}, a large-scale wearable-egocentric dataset for proactive procedural assistance with explicit Out-of-Plan (OOP) annotations and recovery steps; \textbf{(2)}~we augment five established benchmarks (Ego4D, EPIC-KITCHENS, EgoExo4D, HoloAssist, HowTo100M) into \textbf{Pro\textsuperscript{2}Bench} under a unified proactive-guidance schema; \textbf{(3)}~we propose a \textbf{decoupled planner--interaction architecture} specialized for procedural state, visual cues, and recovery injection; \textbf{(4)}~we introduce a post-training recipe that transfers across model families, validated by cross-backbone replication on Llama~4 and Qwen-3.6-VL. In extensive experiments, our trained Llama-4 system substantially improves objective intervention quality over strong proprietary baselines (Claude Opus~4.6, Gemini~3.1~Pro, GPT~5.2) and open-weight baselines (Qwen3~VL~235B) baselines across all six datasets. Oracle-plan experiments further show that, when plan quality is controlled, the trained duplex model produces high-quality guidance and large gains on Out-of-Plan recovery.

Video panoptic segmentation (VPS) aims to jointly detect, segment, and track all objects while partitioning the video into semantically consistent regions. We introduce the task setting of unsupervised VPS, omitting any human supervision. Existing unsupervised scene understanding works mainly focused on image segmentation tasks; the video domain remains underexplored. We propose VideoCUPS, the first unsupervised VPS approach. VideoCUPS generates temporally consistent panoptic video pseudo-labels from scene-centric videos by exploiting unsupervised depth, motion, and visual cues. Training on these pseudo-labels using a novel Video DropLoss yields an accurate, unsupervised VPS model. To benchmark progress, we introduce a comprehensive evaluation protocol and four competitive baselines, extending state-of-the-art unsupervised panoptic image and instance video segmentation models to VPS. VideoCUPS outperforms all baselines and demonstrates strong label-efficient learning. With VideoCUPS, our evaluation protocol, and baselines, we provide a strong foundation for future research on unsupervised VPS.

Current prompt-based and adapter-based tuning of vision-language models (VLMs) is attractive for medical imaging, where clinical data sensitivity favors frozen backbones and annotations are limited. However, these methods typically optimize only the ground-truth class, treating all other classes as equally incorrect, ignoring clinically meaningful class relations and yielding unstable decision boundaries in limited-supervision settings. We propose Omni-Geometry Knowledge Distillation (OGKD), a new framework that injects class-relation structure into the teacher to produce directional targets that preserve the ground truth while respecting inter-class geometry. Using these targets, we develop two distillation losses: Global Geometry-Aware Distillation (GAD) operates on the global image token, and Label-Guided Geometry Distillation (LGD) applies the same geometry to attentive patch tokens to improve fine-grained alignment. Across comprehensive experiments and analyses on 11 widely-used medical datasets for base-to-novel and few-shot evaluations, our OGKD achieves substantially better performance, consistently improving accuracy by an average absolute gain of 1.7%-2.8% over all prior state-of-the-art VLM adaptation counterparts. It also robustly generalizes to unseen classes and yields more reliable predictions than other approaches. Our code is available at https://github.com/tientrandinh/OGKD.

Breast cancer remains a leading cause of cancer-related mortality among women. Its clinical management requires multimodal reasoning across a clinical workflow that spans \textit{screening}, \textit{diagnosis} and \textit{treatment planning}, where each stage involves distinct imaging modalities, task objectives, and reasoning patterns. However, constrained by data scarcity and model versatility, existing medical MLLMs are typically evaluated on isolated modalities or narrow task families, limiting their ability to support workflow-level clinical reasoning. In this work, we first introduce \textbf{BreastStage}, a workflow-aligned breast imaging instruction corpus comprising 1.86M instruction-following pairs curated from 17 sub-datasets across 5 imaging modalities and 136 task templates. Its held-out split, \textbf{BreastStage-Bench}, provides a comprehensive benchmark for evaluating multimodal reasoning across the breast cancer care continuum. Building on this corpus, we propose \textbf{BreastGPT}, a unified MLLM equipped with a dual-branch visual encoder and concept-preserving token compression to bridge the scale gap between standard radiology and gigapixel pathology. On BreastStage-Bench, BreastGPT achieves 75.66\% closed-ended accuracy and 89.92\% open-ended score, outperforming both general-purpose and medical-specific MLLMs across clinical stages and task formats. These results suggest that workflow-aligned data and cross-scale visual modeling are critical for clinically grounded medical MLLMs. All data, code, and model checkpoints are released at https://yangyy-liu.github.io/BreastGPT.io.

Anatomical landmark detection is a fundamental task in medical image analysis supporting a wide range of diagnostic and interventional workflows. Although recent methods have achieved sub-millimetric localisation, accuracy alone is not sufficient for clinical deployment, requiring reliability and robustness in prediction. Despite its clinical relevance, the impact of representation learning in this context is still underexplored. In this work, we introduce CDPM-align, a multi-scale guidance-aligned conditional diffusion pre-training for anatomical landmark detection. Our experimental setup focuses on a few images and a few annotation regimes. Specifically, we employ three popular heterogeneous small-scale benchmark datasets for representation learning via conditional generative pre-training. Furthermore, we consider low-annotation scenarios for the downstream task of landmark detection, with 10 and 25 annotated images, reflecting realistic trade-offs between clinical effort and resource constraints for annotations. Our results confirm that generative pre-training enables the model to learn a robust representation. This improves both accuracy and uncertainty on the downstream tasks, advancing towards safe and efficient clinical deployment.

Generating compact polygonal models from point clouds is a key problem in 3D vision and computer graphics. However, due to inherent limitations of LiDAR scanning (e.g. range constraints and occlusions), critical scene information is often missing, leading to degraded reconstruction accuracy. To address this, we propose a plane assembling strategy that effectively recovers missing details while maintaining model compactness. We classify all the planes extracted from the scene into three categories: highly visible, barely visible, and invisible. The invisible planes, which are recovered by scene structure analysis, indicate the missing details. The three types of planes correspond to the three growth priorities. Each plane grows according to the priority level, and the space is partitioned progressively, namely, the hierarchical partition. Subsequently, we generate a watertight polygonal mesh from the partition via a min-cut-based optimization. Finally, comparisons on public datasets show the effectiveness and superiority of our method against mainstream approaches. The project page is available at https://hsr-3dv.github.io/.

Traditional Chinese Medicine (TCM) ocular inspection provides empirical cues for assessing scleral surface anomalies, but its clinical use remains subjective and difficult to quantify. To support intelligent and quantifiable ocular inspection, this study presents the TCM-inspired Artificial Intelligence Ocular Auxiliary Diagnosis System (TAO) and focuses on pixel-level scleral surface anomaly segmentation. For clinical and user-acquired images affected by multi-source distributional discrepancies, diverse anomaly morphologies, and scleral specular reflection (SSR), we propose HD-DinoMoE, a class-aware hierarchical dual mixture-of-experts network. HD-DinoMoE combines class-aware dual-stream DINOv3 feature fusion with class-specific multi-expert decoding to segment Vessels, Yellow and Black Spots, and Blood Spots. A three-stage backbone-frozen routing strategy stabilizes dual-backbone adaptation; Progressive Confidence Penalty (PCP) Loss reduces high-confidence false positives and segmentation leakage in SSR regions; and Class-Aware Adaptive Sample Weighting (CA-ASW) balances sample- and class-level training contributions. We further construct the Multi-label Scleral Anomaly Segmentation Dataset (ML-SASD), a new benchmark with Clinical, Wild, and Mix settings and pixel-wise annotations for three anomaly categories. On ML-SASD-Mix, HD-DinoMoE achieves a mean Dice of 72.11% and a mean Intersection-over-Union of 58.44%, while maintaining favorable boundary localization and specular-region false-positive control. It also shows competitive generalization on the Vessels subset of the public SBVPI dataset. These results indicate that HD-DinoMoE provides a feasible segmentation solution for TAO under complex acquisition scenarios. The code and data access information are available at https://github.com/FX-CMX/HD-DinoMoE.

Face aging plays an important role in long-term biometric analysis, cross-age identity verification, and forensic identity analysis. Since the same subject may exhibit multiple plausible appearances at a target age due to genetic, environmental, and lifestyle factors, face aging is inherently a one-to-many generation problem. However, pluralism alone is insufficient for reliable face aging: a model should provide appearance-level candidate diversity within each age group while maintaining sequence-level ordinal reliability across ordered age groups. Existing deterministic aging methods can synthesize visually plausible age-progressed faces, but usually lack stochastic diversity. In contrast, pluralistic aging methods introduce local appearance variations, but often fail to explicitly regulate the identity evolution of the full aging sequence. In this paper, we propose \textbf{DiverAge}, a hierarchical pluralistic face aging framework based on diffusion autoencoding. DiverAge preserves appearance-level diversity through stochastic diffusion decoding and age-conditioned semantic modulation. To improve sequence-level reliability, we introduce a Cross-age Identity Relation Regulator (CARR), an inference-time guidance strategy that jointly denoises multiple target age groups. CARR is guided by a Cross-age Identity Similarity (CIS) prior estimated from real same-identity cross-age pairs, and suppresses excessive cross-age identity drift through one-sided sampling-time guidance without modifying the training objective or introducing extra trainable parameters. Experiments demonstrate that DiverAge improves sequence-level ordinal reliability while maintaining identity preservation, age accuracy, image quality, and appearance-level diversity.

Selection is a core operation in interactive image editing. To be practical, a user should be able to specify and disambiguate the desired selection region through either text or click-based interactions, and the system should support selecting not only objects but also other criteria, such as materials. Material-based selection is valuable for tasks like re-texturing surfaces or editing instances of a specific material. However, existing vision-language-model (VLM) based selection methods are object-centric and typically support a single interaction modality, limiting their applicability. In this work, we thus present Mask Any Object And Material (MAOAM), a unified selection framework that enables precise object and material-level selection across both text- and click-based interactions. MAOAM leverages a VLM with a segmentation head to produce pixel-accurate masks from user prompts: the VLM interprets the user's selection intent (object or material-level) and encodes visual entities, attributes, and spatial relations, while the segmentation head decodes the output token into a mask. A key challenge is the lack of material selection datasets with text annotations. We propose a scalable data generation pipeline: we collect real and synthetic images with material masks, and leverage VLMs to generate material descriptions with rich visual-semantics. We train MAOAM with a multi-task objective over click and text-based selection, along with an auxiliary VQA task derived from the material descriptions to facilitate deeper material understanding. Despite being trained with uni-modal prompts, our model exhibits an emergent improvement in selection when combining text and clicks at inference, enabling flexible image editing workflows. Experiments demonstrate accurate and coherent selections across diverse objects, materials, and interaction scenarios, highlighting robustness in practice.

The selection of an appropriate 3D representation is a fundamental design decision that dictates the efficiency, quality, and capabilities of modern computer vision and graphics pipelines for tasks such as 3D reconstruction, novel-view synthesis and rendering, shape and motion analysis, recognition, and generation. While traditional representations (\eg meshes, point clouds, and volumetric grids) remain standard outputs of 3D sensors (\eg LiDAR and 3D scanners) and are widely used in downstream applications (\eg editing and simulation), recent neural and primitive-based representations (\eg 3D Gaussian Splatting) offer compact and differentiable alternatives opening a wide range of opportunities in applications such as games, AR/VR, autonomous driving, robot navigation, and medical imaging, to name a few. The goal of this paper is to survey the main families of 3D representations from discrete explicit formats to continuous implicit fields based either on neural rendering or primitive splatting. For each type of representation, we present the general formulation and its variants, discuss its benefits and limitations, and highlight key applications. We conclude the paper by outlining the open challenges and potential directions for future research. Distinct from recent surveys that broadly cover 3D object and scene reconstruction, this paper provides a focused analysis on the evolution of 3D representations themselves. We specifically emphasize the paradigm shift toward implicit representations, offering a novel perspective on how these emerging formats fundamentally alter 3D/4D workflows.

We introduce IRIS-GAN, a specialist forensic detector for synthetic face images under cross-generator shift. Rather than addressing universal synthetic-image detection, we focus on faces generated by generative adversarial networks (GANs), which are state-of-the-art in deepfake content, and train the detector through staged exposure to increasingly demanding GAN families while retaining earlier generators. The final model reaches fake-detection rates above 99% across the GAN families considered and classifies an external real-face dataset with 98.9% accuracy. Grad-CAM analysis further reveals measurable generator-dependent spatial response patterns, which remain informative for a secondary heatmap-only classifier. Out-of-family tests on diffusion-generated faces confirm that IRIS-GAN is a specialist detector, with some capability to reach non-GAN deepfakes. These results establish staged training as an effective strategy for robust GAN-face forensics.

Native GPU kernel generation turns high-level tensor programs into executable, efficient low-level code. Existing Large Language Models (LLMs) struggle with this task, while execution-based reinforcement learning suffers from sparse rewards, reward hacking, and training instability. We present MusaCoder, a full-stack training framework for native GPU kernel generation on CUDA and MUSA backends. MusaCoder combines progressive kernel-oriented data synthesis, diversity-preserving rejection fine-tuning, and execution-feedback Reinforcement Learning (RL) through MooreEval, a distributed verifier and reward environment. To stabilize RL, MusaCoder introduces PrimeEcho for first-turn-anchored multi-turn rewards, Buffered Dynamic Retry for recovering signals from all-failed hard samples, and MirrorPop for off-policy sequence filtering. Experiments on KernelBench and a MUSA-ported variant show that MusaCoder outperforms strong open-source and proprietary baselines in both correctness and empirical speedup, with the 9B model matching or exceeding frontier closed-source models and the 27B model establishing a new state of the art. These results demonstrate not only the effectiveness of full-stack execution-feedback training for native kernel generation, but also the capability of Moore Threads GPUs to support the complete LLM post-training stack, providing a practical foundation for large-model training and optimization on emerging accelerators.

Contrastive audio-language models such as CLAP enable zero-shot audio classification: a sound is labelled by matching its embedding to text prompt embeddings, with no labelled audio. This matching breaks down under acoustic noise, where accuracy and mAP fall by 12-30 percentage points at 0 dB SNR on standard benchmarks. We propose Drift Augmented Scoring (DAS), a small per-class bonus added to the cosine score. The bonus rewards a class when the noisy audio embedding drifts in the direction that the class's noise-conditioned text prompts predict. It is derived from text alone, computed once and cached, and adds a single inner product per class at inference, with no gradients and no test-time batch. On a LAION CLAP backbone, we compare DAS against the four variants of Acevedo et al.'s concurrent method on UrbanSound8K and the full FSD50K eval set, mixing each clip with urban acoustic scene noise across a range of SNRs. DAS improves the metric on every test condition: by +2.60 to +5.75 accuracy points on UrbanSound8K and +1.50 to +1.74 mAP points on FSD50K.

Accurate Autism Spectrum Disorder (ASD) screening for school-age children is crucial to identify cases that may have been missed earlier and to enable timely interventions supporting social, cognitive, and academic development. Current ASD screening relies on subjective assessments and 2D analysis methods that fail to capture spatial displacement patterns characteristic of ASD behaviors. In this study, a novel 3D temporal analysis framework is presented, built on top of DECA (Detailed Expression Capture and Animation), a 3D modeling framework, to extract comprehensive head pose parameters (including translational components $T_x, T_y, T_z$) and facial expressions independent of pose variations. LSTM and GRU-based temporal classifiers were trained on the extracted 3D features from video data collected from 39 participants (19 ASD, 20 TD) aged 7-12 years during Virtual Reality-Continuous Performance Test tasks. The GRU-based models demonstrated superior performance, with 3D head pose features achieving 83.9\% accuracy and 3D facial features reaching 81.4\% accuracy, outperforming 2D baseline approaches by 10.7\% and 7.5\%, respectively. Furthermore, multimodal fusion of 3D head pose and facial features with PCA-based dimensionality reduction achieved the highest accuracy of 84.6\%, outperforming unimodal approaches. This work establishes a foundation for objective, automated screening tools addressing current diagnostic limitations in ASD identification for school-age populations.

CutMix has become the de facto standard mixing augmentation, yet its label assignment rests on a flawed assumption: The area of the pasted patch faithfully reflects its semantic contribution to the mixed image. In practice, however, patches frequently land on background regions, assigning label credit to classes whose objects are not visible. The mean discrepancy of the CutMix label and the semantic object area is $21.5\%$. In $17\%$ of samples an image contributes zero visible object pixels yet receives nonzero label weight. We propose Object-Aware CutMix (OA-CutMix), which corrects this bias by replacing the area-based CutMix weight with one derived from precomputed segmentation masks, assigning labels in proportion to the visible object area each image contributes to the mix. The image mixing procedure is left entirely unchanged. We evaluate OA-CutMix against 10+ static and dynamic mixing methods across 4 architectures and 6 datasets. OA-CutMix consistently achieves the highest accuracy over all tasks, outperforming even dynamic mixing methods, but at a fraction of the training-time cost. Improvements are largest for small objects, where the label bias from CutMix is greatest. Thus, correcting the label is sufficient to match or exceed the performance of methods modifying the image mixing algorithm.

LLMs and agentic systems are increasingly deployed in social environments, making normative competence critical for safe and appropriate behavior. However, existing approaches either assess normative judgment in text alone or reduce it to choosing among a fixed set of candidate actions. We argue both are insufficient. In practice, agents are never handed a menu of options; they must identify a reasonable action from scratch, grounded in visible facts and supported by inspectable reasons. We introduce NoRA, a visual first-person video benchmark that requires models to generate candidate next actions and justify each through an explicit fact-reason-action support graph. The benchmark comprises 1,420 annotated video clips, including HumanGold-190 and LLMSilver-1230 splits. Each instance is evaluated through action alignment, factual grounding, and support binding, aggregated into a single grounded reasonableness score. We benchmark 12 multimodal systems under direct, deliberate, and structured prompting regimes, finding that current VLMs frequently recover plausible actions and relevant scene facts, but consistently struggle to construct the full reasonable action space and bind selected actions to the correct local support. NoRA makes this gap measurable, shifting the evaluation question from whether a model can pick an action to whether it can justify an appropriate action for the right visible reasons.

We present Flash Cubical, a highly efficient computation of cubical persistence on a V-filtration for 2D and 3D images over $\mathbb{F}_2$. The implementation is built around three core ideas. First, cubical complexes satisfy properties that allow for the computation of persistence of the highest dimension via union-find and duality. Second, pruning of certain edges allows for a fast and efficient implementation of union-find. Third, the use of a lookup table, which exploits the regularity of cubical complexes to pre-compute local information. This avoids the need to compute local information at run time. To the best of our knowledge, this is the most efficient implementation of cubical persistence with a V-filtration, both in terms of time and memory costs. Although the paper focuses on persistence for V-filtration cubical complexes, the underlying ideas generalise naturally to T-filtrations on cubical complexes and suggest promising directions for other complexes.

Custom diffusion models (CDMs) have garnered significant interest owing to their remarkable capacity for generating personalized concepts. However, the majority of CDMs unrealistically presume that the user's collection of personalized concepts is static and incapable of incremental growth over time. Furthermore, they exhibit significant catastrophic forgetting and concept neglect of previously learned concepts when incrementally learning a sequence of new ones. To resolve the above challenges, we develop a novel Continually Customizable Diffusion Model (CCDM), enabling users to perform concept-incremental versatile customization. Specifically, we design an attribute-decoupled LoRA (AD-LoRA) module and a relevance-guided AD-LoRA aggregation strategy to mitigate catastrophic forgetting. They can preserve concept-specific attributes of each task and leverage beneficial inter-task correlations to enhance the continual learning of new customization tasks. Additionally, to address the challenge of concept neglect, we propose a controllable regional context synthesis strategy that performs multi-concept composition in alignment with user-provided conditions. This strategy enhances the overall consistency in multi-concept synthesis by guaranteeing semantic independence between user-defined regions and their smooth boundary transitions. Experiments show our CCDM exhibits significant improvements over baseline methods.

Gastric cancer remains a major cause of cancer mortality, yet its histological and molecular heterogeneity complicates diagnosis and risk stratification. General-purpose pathology foundation models (PFMs) often plateau on fine-grained endpoints central to gastric cancer care, and few have undergone rigorous prospective validation or clinical reader studies. We present GRACE, a Gastric-specific foundation model for Real-world Assessment and Clinical dEcision support. GRACE was developed from multicenter gastric pathology datasets totaling 48,364 primarily HE-stained whole-slide images from 37,493 patients. When evaluated on 28 clinically relevant tasks, GRACE consistently outperformed representative pancancer PFMs, achieving a macro-AUC of 0.9188, with strong performance for precancerous lesion diagnosis (macro-AUC 0.9322), tumor histopathological assessment (macro-AUC 0.9119), molecular profiling (macro-AUC 0.8682), and prognostic prediction. Beyond benchmarking, GRACE's translational value was substantiated through a rigorous evidence chain. Under safety-gated criteria requiring 100% NPV for rule-out and 100% PPV for rule-in, GRACE streamlined review for up to 69.6% of malignancy-diagnosis cases and triaged 46.8% of MMR-IHC follow-up requests. This translational feasibility was further strengthened by a randomized crossover reader study of pathologist-AI collaboration. With GRACE assistance, diagnostic accuracy improved from 82.0% to 89.9%, yielding nearly twofold higher adjusted odds of a correct diagnosis (OR 1.987) alongside concurrent gains in sensitivity and specificity. AI assistance also reduced diagnostic time by 14.9%, elevated diagnostic confidence by 9.0%, and markedly improved inter-rater agreement. When calibrated to maintain non-inferior performance to senior pathologists, the AI-assisted workflow could triage 60.7% of atrophy and 82.7% of intestinal metaplasia cases.

Visual localization -- estimating a camera pose within a pre-existing map -- is a fundamental problem in computer vision. Floorplans are an attractive map representation: they are readily available for most buildings, compact, and inherently invariant to visual appearance changes. However, bridging the severe domain gap between camera observations and floorplan geometry remains challenging. Existing methods address this gap through data-driven learning, yet they require large-scale training data and environment-specific retraining, limiting their practical deployment. We propose a zero-shot floorplan localization method that generalizes to novel environments without any retraining. Our key insight is that dominant geometric primitives -- lines and circles -- are ubiquitous in human-made environments and provide appearance-invariant structural constraints. We extract these primitives from a bird's-eye-view (BEV) projection of monocular 3D reconstructions and match them to the floorplan via dedicated minimal solvers within a robust estimation framework. Experiments on both simulated and real-world datasets show that our approach outperforms state-of-the-art learning-based methods on unseen environments, while using a single fixed set of hyperparameters across all experiments. The source code will be made publicly available.

Text-to-video (T2V) models trained on large-scale web data can generate undesired content, motivating interventions that reduce harmful outputs without sacrificing visual quality. Activation steering offers an attractive mechanistic alternative to finetuning and prompt filtering, but existing T2V steering methods remain limited, typically applying coarse, non-anticipative interventions that can lead to oversteering and content degradation. To close this gap, we propose Latent Activation Linear-Quadratic Regulator (LA-LQR), a reduced-order optimal control framework for minimally invasive T2V steering. LA-LQR formulates T2V inference as a dynamical system and computes closed-loop feedback interventions that steer activations toward desired feature setpoints while penalizing unnecessary perturbations. To make optimal control feasible for high-dimensional video activations, we project activations onto a low-dimensional, task-relevant subspace derived from contrastive prompt pairs, estimate local linear dynamics in this latent space, and solve a latent LQR problem to obtain timestep- and layer-specific steering signals. We provide theoretical bounds relating latent setpoint tracking to raw activation-space feature control, and empirically validate the fidelity of the reduced latent dynamics. On concept steering and video safety benchmarks, LA-LQR reduces unsafe generations relative to baselines, while preserving prompt fidelity and visual quality.

Reliable evaluation of human motion understanding is fundamental to advancing embodied AI, robotics, and animation. However, existing benchmarks suffer from coarse semantic granularity, undifferentiated difficulty, limited annotation quality, and pervasive answer ambiguity, leaving them unable to diagnose where current models fail. To bridge this gap, we introduce NextMotionQA, a comprehensive benchmark that leverages vision-language models (VLMs) for semi-automated, expert-verified dataset. NextMotionQA features three complementary tasks: multiple-choice question answering, video captioning, and fine-grained error correction. Each task is systematically structured across three core semantic axes and stratified into three task complexity levels. Our extensive evaluation of twelve representative VLMs uncovers critical capability gaps and weakness that remain invisible under conventional, single-task evaluations. In a complementary direction, recent work has begun using VLMs as judges for text-to-motion evaluation; we ask whether they show the same degradation under harder tasks. We find that VLMs align strongly with expert ratings on coarse criteria (Cohen's κ=0.70) but break down on fine-grained, part-level judgment (κ=0.10), validating the paradigm in its strong regime while clarifying its limits.

Understanding the relationship between deep visual representations and the human visual system is a fundamental challenge in computational neuroscience. While modern vision models achieve strong performance in image recognition, their correspondence with the hierarchical organization of the human visual cortex remains an open question. In this study, we propose CHASMBrain, a novel hierarchical two-stage framework for image-to-fMRI encoding. Our architecture leverages a dual-stream Mamba design to explicitly separate and process global semantic tokens and local spatial patches, motivated by the functional organization of the visual cortex. A coarse-to-fine strategy is employed: Stage 1 predicts denoised ROI-level activations, while Stage 2 refines these coarse responses into full voxel-level predictions using a Mamba-VAE. Experiments on the Natural Scenes Dataset (NSD) demonstrate that our method achieves a Pearson correlation of 0.429 and an MSE of 0.261, outperforming all evaluated baselines including ridge regression and DINOv2 linear probes. Beyond predictive performance, causal branch-ablation experiments reveal an asymmetric specialization: the patch stream is specifically locked to early visual cortex (retinotopic regions), while the CLS stream contributes broader semantic context to higher-order areas -- a correspondence that holds causally, not merely correlationally. Cross-subject transfer experiments further show that the learned backbone generalizes across individuals with minimal per-subject adaptation, suggesting the model captures a shared, subject-agnostic visual representation.

The robustness of deep neural networks is crucial for safety-critical deployments, yet existing evaluation methods are often attack-dependent and lack interpretability. We propose a principled, attack-agnostic robustness metric based on the spectral norm of the Fisher Information Matrix (FIM), which quantifies the worst-case sensitivity of the model's output distribution to input perturbations. Theoretically, we establish that the FIM equals the variance of the input Jacobian and derive closed-form spectral bounds for common architectures, including VGG, ResNet, DenseNet, and Transformer, providing the first theoretical robustness ranking. To enable scalable evaluation, we develop efficient algorithms, including power iteration and Hutchinson-based estimation, that support both white-box and black-box settings. Extensive experiments across multiple datasets, including CIFAR, ImageNet, and medical images, and across multiple architectures show a strong correlation between our metric and adversarial vulnerability. Our framework serves as an interpretable diagnostic tool that complements attack-based evaluations, offering insights into architectural sensitivity and guiding the design of more robust models. Code is available at: https://github.com/franz-chang/SRP/.

Whether attention maps from pathology foundation models capture genuine biology remains unknown, yet this question is critical for clinical trust and regulatory approval. We propose a spatial transcriptomics-based framework for orthogonal, hypothesis-free evaluation of attention and apply it to five pathology foundation models (CONCH v1.5, UNI v2, Virchow2, GigaPath, H-Optimus-1) and a ResNet50 baseline. Using attention-based multiple instance learning, we train single-task and multi-task models to predict five molecular alterations in glioblastoma on the CPTAC cohort, validate on an independent TCGA cohort, and evaluate biological coherence of attention maps against 87 transcriptional signatures using co-registered Visium spatial transcriptomics data from 18 samples. Internally, no single encoder dominates across all tasks, and external validation inverts internal performance rankings. Attention maps show a five-fold enrichment gradient from pathways (Cohen's d=0.329) to individual genes (d=0.055), indicating that attention captures emergent multi-gene transcriptional programs rather than individual molecular events. Spatially smooth attention maps do not imply biological coherence, and different encoders attend to distinct biological compartments. Our framework provides objective, quantitative assessment of what foundation models learn from histopathology, moving the field beyond qualitative saliency map review.

Large-scale video generation models have made remarkable progress in semantic consistency and visual quality, producing videos that are increasingly coherent and visually convincing. Nevertheless, the dynamics induced by pixel-level fitting do not naturally accommodate the regularities that govern real-world motion and interaction, resulting in persistent shortcomings in physical plausibility. To address this limitation, we propose \textbf{PILA} (Physics-Informed Latent Alignment), a framework that injects physics-structured latent guidance into the frozen flow-matching dynamics of pretrained video models. Specifically, PILA first employs anchored field estimation to map frozen-generator latents into an operational physical attribute bank organized by field-proxy slots, using observable motion as a kinematic anchor for constructing less directly observed proxies. To handle the heterogeneity of real-world dynamics, PILA adopts a mixture-of-experts design over physical categories. Label-prior masked expert routing selects category-specific operator experts, whose refinements are regularized by operational residuals abstracted from physical relations. Finally, the refined proxies are fused into the physical attribute bank and decoded into a correction to the flow-matching vector field, injecting physics-aware guidance while preserving the visual prior of the pretrained backbone. With staged adapter training on Wan 2.1-1.3B and direct transfer of the learned adapter to Wan 2.2-14B, PILA achieves state-of-the-art results on VBench-2.0, VideoPhy-2, and PhyGenBench in both visual quality and benchmark-measured physical plausibility.

Ischemic stroke is a major global disease. Treatment decisions are highly time-sensitive, as eligibility for reperfusion therapies relies on the interval between stroke onset and intervention. However, the true onset time is often uncertain in clinical practice, necessitating imaging-based assessment of tissue age as a surrogate marker. Early ischemic changes on routinely acquired non-contrast CT (NCCT) are often subtle, and real-world clinical datasets exhibit pronounced onset-time class imbalance and center-scanner-related heterogeneity. In this work, we propose StrokeTimer, a fully automated framework for onset-time estimation in acute ischemic stroke. StrokeTimer integrates self-supervised disentanglement learning with energy-guided contrastive learning to capture subtle ischemic patterns while addressing long-tailed data distributions under acquisition variability. Onset time is categorized into three clinically relevant windows: <4.5 h, 4.5-6 h, and >6 h. Experimental results on a large multi-center NCCT dataset from two national cohorts, MR CLEAN Registry and MR CLEAN LATE, show that StrokeTimer achieves a macro AUC of 0.69 and a macro F1-score of 0.57, improving the strongest baseline by nearly 50% (p < 0.005). In this realistic, challenging setting, representative baseline approaches exhibit near-chance macro performance. Model explanations further highlight subtle gray-white matter blurring and hypodense regions consistent with established radiological biomarkers. These findings demonstrate the potential of StrokeTimer to support treatment decision-making in acute ischemic stroke. Code is available at https://github.com/BrainVas/StrokeTimer.

This work presents a data-efficient variant of the Attention-Based Dual-Branch Complex Feature Fusion Network (CFFN) for hyperspectral image classification. The proposed model, termed DE-CFFN, retains the original two-stream structure: the Real-Valued Neural Network (RVNN) processes standard hyperspectral patches, while the Complex-Valued Neural Network (CVNN) handles their Fourier-transformed counterparts. The main contribution of this work lies in the feature extraction process and architectural enhancement. Factor Analysis is used for dimensionality reduction, offering improved latent feature representation over Principal Component Analysis. Additionally, both the RVNN and CVNN streams are structurally modified by successively halving the number of filters in the 3D convolutional layers to reduce complexity. The outputs of both branches are concatenated and passed through a Squeeze and Excitation (SE) block to enhance joint feature representation. Evaluated on the Pavia University and Salinas datasets, DE-CFFN achieves classification performance comparable to CFFN, while significantly reducing model size, memory consumption, and inference latency, making it suitable for real-time hyperspectral imaging applications.

AI-generated videos are becoming increasingly realistic, raising serious concerns about misinformation, content authenticity, and media trust. Reliable AI-generated video detection is therefore essential for multimedia forensics, yet remains challenging due to the need to capture spatial artifacts, temporal dynamics, and generalize to evolving generative models. In this paper, we explore reconstruction error as a discriminative forensic cue for AI-generated video detection. By reconstructing input videos with a pretrained WF-VAE, we observe that real and generated videos exhibit distinguishable frame-wise reconstruction error patterns, suggesting that reconstruction errors can reveal their distributional discrepancies. However, extending reconstruction-based image detection to videos is non-trivial, since video reconstruction errors are temporally organized across frames and require semantic context for effective interpretation. To address these challenges, we propose ReConFuse, a reconstruction-guided semantic fusion framework for video-level AI-generated video detection. ReConFuse extracts reconstruction error cues from WF-VAE reconstructed videos, aligns them with multi-frame semantic features, and uses a Mamba-based module to model temporal evolution for video-level classification. Experiments across multiple generators and evaluation settings demonstrate the effectiveness and strong generalization ability of ReConFuse.

Semantic segmentation in medical imaging is a critical yet challenging task due to data scarcity and high variability across modalities. While foundation models like the Segment Anything Model (SAM) show promise, they often struggle with medical images without specific adaptation. Moreover, point prompts, despite being the most natural form of user interaction, provide insufficient spatial context for reliable segmentation, particularly when target structures are irregular or poorly contrasted. In this paper, we propose an enhanced segmentation framework that integrates a lightweight Box Predictor module into the MedSAM architecture. The Box Predictor estimates an approximate bounding box from a single user click using localized image embedding features, providing spatial guidance that reduces the ambiguity of point prompts, while introducing only 1.6M additional parameters and negligible inference overhead. We introduce a two-stage training pipeline where the Box Predictor is trained independently before being integrated into MedSAM. To validate the generalization capability of our method, we conduct extensive evaluations on four diverse datasets (FLARE22, BRISC, BUSI, LungSegDB) spanning distinct imaging modalities, including CT, MRI, and Ultrasound. Our method improves segmentation accuracy and robustness across varied anatomical structures and imaging domains, achieving Dice scores of 0.89 (BUSI), 0.93 (FLARE22), 0.88 (BRISC), and 0.98 (LungSegDB). Code is available at https://github.com/Amirhosseinmovahedi/MedSAM-BoxPredictor

GUI agents today assume a static screen, where the world is frozen between two actions. However, real interfaces such as short-video applications violate this assumption, as their content keeps playing, and a competent user must decide what to watch and for how long. We formalize this task as Living-Screen-Native GUI agents and introduce LivingScreen, the first benchmark instantiating it on short-video platforms, with a faithful browser-based environment, a three-tier task suite, and metrics that jointly score accuracy and information efficiency. Evaluating extensive frontier models, we find that none reaches the human cost-accuracy performance, and that their dominant failure mode is over- and under-observation, pointing to observation control as a missing capability axis for future GUI agents. All data and code will be available at https://github.com/BITHLP/LivingScreen.

Measuring the angle between bone structures is a routine task in medical image analysis and provides a key quantitative parameter for diagnosis and treatment planning. Automated methods can reduce time and cost while improving reproducibility. In this work, we address automatic bone pose estimation using a learning-based point candidate proposal followed by a line model to extract axis parameters. Since conventional line models such as least squares are sensitive to outliers, we incorporate false-positive reduction strategies and robust fitting techniques, such as RANSAC and Hough transforms, to improve robustness. We evaluate our method on three clinically relevant paediatric angle estimation tasks: fracture fragment assessment in radiographs and ultrasound and developmental dysplasia of the hip evaluation in ultrasound using the Graf method. Our approach achieves mean errors of $4.1^\circ$, $5.4^\circ$, and $5.51^\circ$, respectively, not only remaining within the expected clinical observer variability, but also significantly outperforming landmark-based methods. Our code and annotations for fracture angle assessment in radiographs are publicly available on GitHub.

Early and accurate detection of Alzheimer's disease (AD) is important for timely intervention and disease management. Generalized Eigenvalue Proximal Support Vector Machine (GEPSVM) and its Universum-based variants have shown promising results for AD classification. However, existing methods treat Universum samples as independent points and do not consider the geometric relationships among them. This paper proposes two graph-guided Universum learning models, namely UG-GEPSVM and IUG-GEPSVM, for AD versus cognitively normal (CN) classification using structural MRI data. In the proposed framework, mild cognitive impairment (MCI) subjects are used as Universum data to provide intermediate information between AD and CN classes. A graph is constructed over the Universum samples using Gaussian similarity, Minimum Spanning Tree connectivity, and multi-hop propagation. From this graph, a Laplacian matrix is derived that captures the geometric structure of the MCI samples. This Laplacian-based regularization is incorporated into the learning process in place of the conventional independent Universum penalty term. UG-GEPSVM integrates this regularization into the generalized eigenvalue formulation, while IUG-GEPSVM extends the numerically stable improved GEPSVM framework using a standard eigenvalue formulation. Experiments on ADNI MRI dataset variants using ICA- and PCA-based features at five different noise levels show that both proposed models consistently outperform existing GEPSVM and Universum-based methods. UG-GEPSVM achieves the highest average AUC of 88.07% and maintains stable performance under increasing noise levels. Statistical tests further confirm the significance of the observed improvements.

Autoregressive mesh generation has gained attention by tokenizing meshes into sequences and training models in a language-modeling fashion. However, existing approaches suffer from two fundamental limitations: (i) low tokenization efficiency, which yields long token sequences and prevents scaling to high-poly meshes, and (ii) absence of geometry-aware guidance, as generation is conditioned only on global shape embeddings rather than local surface cues. We introduce MeshWeaver, an autoregressive framework that treats mesh generation as a surface weaving process by directly predicting the next vertex instead of independent coordinates. At its core is a multi-level sparse-voxel encoder that injects geometric context into the generative process in three complementary ways: providing voxel features as vertex representations, guiding token prediction via cross-attention to voxel features, and serving as a structural scaffold that constrains generation around the input surface. Our hierarchical design enables coarse-to-fine vertex prediction in a single decoding step, while tightly coupling the generative model with 3D geometry. Extensive experiments demonstrate that MeshWeaver achieves a state-of-the-art compression ratio of 18%, can generate meshes with up to 16K faces, and significantly improves geometric fidelity over prior approaches.

The real-time hardships of video processing seriously limit the usage of Automatic License Plate Recognition (ALPR) with application in dynamic traffic monitoring settings. High-fidelity recognition of unconstrained variables, e.g. drastic variations in illumination, acute camera scans, high vehicle speeds, and harsh physical concealment, is a problem that often leads to disjointed tracking paths and poor Optical Character Recognition (OCR) rates. In order to mitigate these weaknesses, the study proposes a 5 stage, end-to-end algorithmic pipeline, encompassing a smooth transition between deep learning based object detection, multi-object tracking which is kinematic in nature, and geometry temporal data interpolation. The suggested architecture takes advantage of a very powerful YOLOv8 nano model to localize the vehicle at the first stage and then Simple Online and Realtime Tracking (SORT) algorithm is used to build spatial-temporal links between frames. Another, more specific typology of YOLOv8 object detectors the license plate area, channeling the sliced array to an EasyOCR chain under the limitations of positional syntax verification. More importantly, an offline interpolation mechanism of temporal bounding box is initiated to recast fragmented paths.

Object detection is a safety-critical component of autonomous driving. It is essential to quantify the uncertainty in bounding-box predictions for safety assurance. Post hoc uncertainty quantification without retraining aligns with real-world deployment requirements; therefore, we employ the Laplace approximation. Because instance-level uncertainty is needed, linearized inference methods that require multiple backpropagations are not time-efficient, and sampling-based methods are not fully post hoc. We propose Monte-Carlo generalized linearized model (MC-GLM), which provides instance-level and approximately post hoc uncertainty quantification. The number of samples required in the Monte Carlo step is constant and independent of the number of output instances, so it can be parallelized. Experiments on the nuScenes dataset with the CenterPoint detector validate the effectiveness of our method, and the resulting uncertainties exhibit good quality.

Vision-Language Models (VLMs) struggle when applied to medical image-text data, yet the tools available to diagnose this failure remain limited. Existing representation alignment metrics are symmetric, collapsing both modalities into a single score and hiding which modality drives cross-modal degradation. We introduce the Spectral Alignment Score (SAS), an asymmetric metric that projects both modalities onto the principal eigenbasis of an anchor modality and computes eigenvalue-weighted per-eigenmode correlations, resulting in directional scores whose difference quantifies modality information imbalance. We embed SAS within a benchmarking framework evaluating 15 VLMs across natural and medical image-text datasets alongside 6 alignment metrics and bidirectional retrieval. Our experiments show that medical images retain richer structural information than their paired clinical reports, a directional asymmetry invisible to all competing metrics, and that SAS achieves the strongest zero-label correlation with retrieval performance in the medical domain, positioning it as a practical diagnostic tool for clinical deployment. Code is available at this URL: https://github.com/iamalegambetti/medical-vlms-assessment.

Composed Image Retrieval (CIR) represents a challenging retrieval task that targets locating specific images through multimodal inputs. Despite recent progress in CIR techniques, prior approaches often overlook cases where images appear visually alike yet differ in attributes, potentially undermining both multimodal feature fusion and similarity modeling. To mitigate this limitation, we design a unified representation of cross-modal features based on attribute prototypes. Nevertheless, the task is far from straightforward, owing to three core issues: (1) entanglement in attribute-level semantics, (2) inconsistency across modalities, and (3) supervised signal missing. To tackle the above obstacles, we introduce a COMposed image retrieval network guided By attrIbute-based NEighbor Relations (COMBINER). Specifically, we first design an Adaptive Semantic Disentanglement module, which is capable of disentangling attribute features based on multimodal primitive features. Secondly, we propose a Unified Prototype-based Composition module, which can construct cross-modal unified prototypes (CUP) and facilitate multimodal feature composition. Finally, we introduce a Dual Relations Modeling module, which can mine pairwise and neighbor relations based on attribute similarity. Compared to traditional neighbor relations modeling CIR methods, COMBINER represents the first study addressing the phenomenon of visually similar but attribute-unrelated samples. It achieves a more accurate understanding of the semantic relations among samples by employing an attribute prototype-based similarity metric. Comprehensive experiments conducted on three benchmark datasets confirm the effectiveness of our proposed COMBINER. The implementation of our method will be accessed at https://github.com/Lee-zixu/COMBINER

Although dynamic 3D (i.e., 4D) reconstruction from a monocular dynamic camera has recently advanced, it remains fundamentally limited by depth ambiguity. In this paper, we focus on an alternative practical way, i.e., sparse dynamic camera setup, where a handful of independently moving cameras capture the same subjects. While keeping capture costs low, this setup introduces multi-view constraints and remains practical for real-world video production such as sports, concerts, and TV shows. Despite its potential, our experiments show that naive extensions of existing monocular or dense-fixed camera-based methods are insufficient since they fail to resolve the complex spatiotemporal inconsistencies across views and time. To fill this gap, we propose a simple yet effective 3D track initialization method designed to ensure spatiotemporal consistency by integrating inter-camera feature matching with intra-camera point tracking. Additionally, we incorporate a noise-robust depth-ordering regularization loss and a spatiotemporally diverse batch sampling strategy to enhance optimization stability and cross-view generalization. Furthermore, to address the lack of standardized benchmarks for this task, we introduce LetCamsGo, a new real-world video dataset with 5 sequences across 4 diverse environments, recorded by three independently moving cameras and one fixed camera. Comprehensive benchmarking on LetCamsGo demonstrated that our proposed framework improves 4D reconstruction quality in dynamic regions compared with baselines, paving the way for a low-cost 4D reconstruction paradigm in the wild.

With the widespread adoption of multi-modal communication platforms, long-form dialogues interleaving text and images have become increasingly common. Users often need to retrieve coherent dialogue fragments related to specific topics, rather than isolated utterances. We propose Fine-grained Fragment Retrieval (FFR), which locates semantically relevant multi-utterance, multi-image fragments in multi-modal long-form dialogues. We explore two settings: (1) FFR within Single-Dialogue, retrieving fragments from a given dialogue; and (2) FFR within Dialogue Corpus, retrieving from a large-scale corpus for open-domain scenarios. For (1), we introduce F2RVLM, a generation-based retrieval model trained with reinforcement learning, using multi-objective rewards and difficulty-aware curriculum sampling to enhance fragment coherence. For (2), we develop FFRS, a two-stage system combining offline fragment-level indexing with online retrieval. Specifically, each dialogue is decomposed into minimal semantic fragments encoded by a Fragment Embedding Model (FEM) into a vector database; at inference, FEM rapidly recalls Top-K candidates, and F2RVLM performs fine-grained reasoning to identify the most relevant sub-content. To support FFR, we construct MLDR, the longest multi-modal dialogue retrieval dataset to date, and a WeChat-based real-world test set. Experiments on both benchmarks demonstrate that F2RVLM and FFRS consistently achieve superior performance across single-dialogue and corpus-level FFR.

Recent advances in generative image editing have improved the realism and controllability of localized image manipulation, raising new challenges for image manipulation detection and localization (IMDL). However, existing IMDL benchmarks still have limitations in visual realism, manipulation diversity, and generator coverage, making it difficult to reflect recent trends in image manipulation. To address these limitations, we introduce Impostor, a high-quality AI-edited image manipulation localization dataset containing 100K manipulated images. Impostor is constructed by CraftAgent, a closed-loop agent framework that integrates scene perception, editing planning, manipulation execution, quality validation, and iterative reflection to automatically generate diverse and visually realistic manipulated images. Moreover, Impostor contains images generated by seven recent AIGC models across three manipulation types and includes multiple manipulated regions, providing a more comprehensive benchmark for AIGC-based IMDL. Furthermore, we propose PhaseAware-Net (PANet), a semantic-forensic framework that introduces local phase modeling and semantic-forensic consistency learning to better localize semantically plausible yet forensically disrupted manipulated regions. Extensive experiments show that Impostor poses significant challenges to existing large vision-language models (LVLMs) and specialized IMDL methods, while PANet achieves superior performance on Impostor and multiple public benchmarks.

Few-shot class-incremental learning (FSCIL) in synthetic aperture radar imagery presents unique challenges due to severe data scarcity and SAR-specific variability. In particular, strong azimuth sensitivity in SAR induces large intra-class variation and inter-class confusion, and FSCIL sequential updates further lead to catastrophic forgetting of previously learned classes. Inspired by neural collapse, we propose an optical-guided SAR FSCIL framework, which derives orthogonal feature subspaces from a data-rich optical ATR dataset and uses them as geometric priors to guide SAR feature learning. SAR features are projected onto these orthogonal subspaces via principal angle constraints, effectively transferring discriminative structure from the optical to the SAR domain. Specifically, our projection loss and the classifier loss optimized with a frozen simplex-ETF geometry jointly induce neural collapse by concentrating features around class means while maintaining large inter-class angles. We evaluate the approach on a benchmark comprising an optical ATR dataset and a SAR ATR dataset with 24 target classes, organized into a base training session and seven incremental sessions. Compared with recent FSCIL methods including NCFSCIL and so on, our method achieves the highest final accuracy and a favorable trade-off between final performance and performance degradation. Moreover, neural collapse metrics show improved intra-class compactness and inter-class separability, indicating that the learned features more closely approximate the ideal simplex-ETF geometry.

We present Echo Infinity, an autoregressive (AR) framework towards real-time infinite video generation that employs a learnable evolving memory to dynamically filter, abstract, and compress any-length history at constant cost. Existing methods mainly curate memory with predefined KV-cache schedules, fixed-ratio heuristic compression, or inference-time RoPE adaptation. These designs inevitably lose historical information and amplify compounding errors due to their limited cache window and ignorance of autoregressive generation noise. Inspired by human memory consolidation, Echo-Infinity replaces handcrafted memory curation with learnable Memory Query, which are updated by attention and a gating mechanism when past frames are evicted from the local window. The queries are optimized end-to-end with the video diffusion transformers (DiTs), forming an evolving memory that supports arbitrary compression ratios with constant computation independent of video length. They also act as a generalizable generation prior, improving quality even when only the optimized initial state is used. We further introduce Unified Relative RoPE Recipe, which anchors the sink frames to start from id 0 and lets the newest frame id grow at most to the DiTs' pretrained maximum temporal RoPE id throughout training and inference, freeing the model from the finite RoPE constraint and closing the train-test RoPE extrapolation gap. In long and short video generation, Echo-Infinity achieves state-of-the-art performance, and, to our knowledge, demonstrates promising 24-hour (>1.3 M frames) real-time rollouts for the first time, suggesting a practical path toward infinite video generation.

Correspondence pruning aims to identify inliers from an initial set of correspondences. Most existing Graph Neural Network (GNN)-based methods rely on geometric features mapped from coarse Euclidean coordinates, which struggle to capture the subtle geometric consistencies presented by inliers. While Mamba-based methods possess global receptive fields and long sequence modeling capabilities, they tend to accumulate substantial inconsistent features within the hidden state space, making it difficult to distinguish inliers from outliers. In this paper, we integrate frequency domain perception into this task for the first time and propose SFMambaNet, a novel Spectral-Frequency enhanced Mamba-based two-view correspondence pruning network. Our method is collaboratively composed of two components: First, we design a Local Spectral-Geometric Attention (LSGA) block. LSGA incorporates spectral positional encoding into local graph interactions and introduces multi-scale Mamba processing to enhance the capture of subtle geometric consistencies and improve local feature discriminability. Building upon this, we design a Spectral-Integrated Global Mamba (SIGM) block. SIGM embeds a frequency gating mechanism within the state space, utilizing the frequency information provided by LSGA to explicitly suppress high-frequency noise accumulation within hidden states and mitigate the propagation of inconsistent features. This enhances inlier-outlier separability and achieves robust global context modeling capabilities with nearly linear complexity. Extensive experiments demonstrate that SFMambaNet outperforms current state-of-the-art methods on several challenging tasks. The code is available at https://github.com/Kirito14IT/SFMambaNet.

High-quality dynamic human pose annotation equips AI with precise motion kinematics to enable human behavior mastery, yet remains labor-intensive and time-consuming. Current annotation tools either lack temporal correction propagation or fail in multi-person scenarios, necessitating excessive manual intervention. In this paper, we introduce IMPose, an interactive tool for multi-person dynamic pose annotation. It features a dual-level tracking mechanism that propagates one-frame multi-person pose corrections from annotators across entire videos. The keypoint-level ensures corrections temporal propagation via sequential modeling, while the instance-level employs keypoint-aware embedding with relative positional encoding to maintain multi-person cross-frame consistency. To further improve robustness, IMPose maintains historical pose and instance cues in a trajectory bank, which enhances long-range temporal association and stabilizes annotation in challenging cases such as occlusion and motion blur. By converting sparse human corrections into dense and coherent pose trajectories, our framework significantly reduces repeated manual refinement across frames. Extensive experiments show that IMPose consistently achieves a strong accuracy efficiency trade off under different interaction budgets, demonstrating particular advantages in low click annotation settings. IMPose achieves high precision annotation with high efficiency, requiring only 27 clicks per 1,050 frame video on 3DPW and 3 clicks per tracklet per 84-frame on PoseTrack21. We further expand PoseTrack21 with 188K pose instances (3.55M keypoints) at a minimal cost of 10 annotators in 10 hours. The annotation tool, codes, and extended dataset will be open-sourced.

Recent text-to-image (T2I) models can render highly legible and well-structured text within images, enabling applications including document generation and slide generation. However, it remains unclear whether such systems faithfully preserve reasoning ability when complex solutions must be expressed directly through rendered text, or whether they merely imitate surface-level patterns. We investigate this question by evaluating reasoning fidelity in visual text generation, where models must express complete reasoning processes as images. Our evaluation includes long text rendering, factual knowledge probing, context understanding, and multi-step reasoning. Across these settings, we find that current T2I models frequently produce semantic errors, logical inconsistencies, and incorrect intermediate steps, even when the rendered text appears visually clear. These failures contrast with the strong reasoning performance of text-only models on the same tasks. Our findings reveal a substantial gap between visual text generation and procedural reasoning, motivating more reliable visual text reasoning.

We introduce Adaptive Calibration (AC), a novel calibration strategy for facial recognition that maps cosine similarity between normalized embeddings to well-calibrated probabilities. By incorporating local context into calibration, Adaptive Calibration corrects for a fundamental mismatch in cosine similarity, whereby the same distance can correspond to different match probabilities in different embedding regions. Our approach improves both overall performance and results in a fairer calibration without requiring demographic metadata. Our approach consistently dominates existing methods both on accuracy and fairness metrics across a variety of pretrained models and standard benchmarks. AC provides a practical solution for equitable facial recognition, without requiring demographic group annotations, and while improving overall performance. Unlike existing approaches, our method provides continuous, region-specific calibration that avoids "leveling down" where fairness comes at the cost of degraded performance for some groups.

Leading flexible vision tokenizers achieve SOTA quality at an extreme cost, relying on parameter-heavy backbones and slow, multi-step generative decoders. We depart from this complex, spatial-token paradigm and introduce a simple, lightweight, and fast channel-wise flexible-length tokenizer. Our method treats each latent channel as a visual token, enabling a parameter-efficient CNN-Transformer hybrid backbone. Furthermore, employing a stochastic tail-dropping paradigm during training naturally forces channels to organize by semantic importance. This allows for flexible compression at inference by simply retaining the first $k$ channels, and naturally enables variable-length autoregressive image generation. We validate our approach through extensive experiments on ImageNet, demonstrating consistent quality across diverse token budgets. The results establish a new quality-efficiency frontier: our model achieves state-of-the-art perceptual quality (rFID 2.92) while being $8.6\times$ faster in decoding and $2.1\times$ smaller (159M params) than the next-best alternative. Our work establishes channel-wise tokenization as a powerful and practical paradigm for efficient visual representation. Project page: https://channeltok.github.io

Incorporating visual semantic representations as an intermediate step before image generation can reduce the modeling difficulty between text and images, thereby improving generation quality. Recent works such as X-Omni and BLIP3o-Next have explored this direction, but they typically use a two-stage external pipeline: a separate autoregressive model first generates semantic tokens, which are then fed as conditioning to an independent diffusion decoder. Since the decoder cannot jointly access the original input and the semantic plan, this design introduces an information bottleneck that limits detail preservation in downstream tasks such as editing. Internal architectures such as Transfusion, BAGEL, and Show-o2 avoid this bottleneck by enabling cross-modal interaction within a single model, but they still face the difficult text-to-pixel modeling gap without intermediate semantic guidance. We propose Visual Prompt Engineering (VPE), which can be seamlessly integrated into such internal frameworks. Specifically, the model first autoregressively generates visual semantic tokens (e.g., SigLIP 2) as "visual prompts" that capture the semantic layout, then generates the full image tokens conditioned on this plan. We validate VPE across class-conditional generation, text-to-image generation, and image editing, covering various token types and model architectures. Results show that VPE can accelerate convergence, raise quality ceilings, and through internal integration, achieve substantially better editing preservation (PSNR: 26.76 vs. 19.92) than external alternatives of the same parameter scale, while maintaining competitive editing responsiveness.

Radiomics enables extraction of quantitative imaging biomarkers from medical images and has become an important tool for computer-aided cancer diagnosis. However, radiomics datasets are typically high-dimensional with limited samples, making feature selection a critical step for building reliable predictive models. This study proposes a Gradient-Loss Recursive Feature Elimination (GL-RFE) framework that integrates gradient sensitivity analysis from a deep neural network to identify the most influential radiomic features for lung cancer stage detection. A total of 106 radiomic features were extracted from chest Computed Tomography (CT) scans using the PyRadiomics extension of the 3D Slicer platform. The proposed method evaluates feature importance by computing gradients of the network loss with respect to input features and recursively eliminates features with minimal contribution. The resulting top-15 radiomic features are used to train a deep neural network classifier for distinguishing early-stage and advanced-stage lung cancer. The proposed framework achieves strong classification performance, with accuracy of 90.22%, precision of 90.10%, recall of 90.24%, and F1-score of 90.16% on the test dataset. Visualization analyses, including correlation heat maps and distribution plots, further confirm reduced feature redundancy and improved class separability. Compared to conventional feature selection techniques, GL-RFE effectively captures nonlinear feature interactions and enhances model generalization. The presented protocol provides a reproducible and interpretable methodology for radiomics-based cancer stage detection and is particularly suitable for high-dimensional, small-sample biomedical datasets, with potential applications in other domains such as genomics and multimodal clinical analysis.

Collaborative perception extends the perceptual range of autonomous vehicles by sharing information across agents, but heterogeneous sensors and perception models make intermediate feature fusion difficult to deploy at scale. Existing heterogeneous collaboration methods typically follow a translation-first paradigm: collaborator features must be aligned, adapted, or projected into an ego-compatible space before fusion. Such feature-compatibility contracts improve fixed-system performance, but they couple deployment to collaborator-specific adaptation and make newly joined heterogeneous agents costly to integrate. To address this gap, we propose INTACT, an ego-guided typed sparse evidence retrieval framework for heterogeneous collaborative perception. Instead of translating an entire collaborator feature map, INTACT lets the ego vehicle issue typed evidence queries that express suspected objects and evidence-deficient regions. Collaborators respond only with local evidence at queried locations, and the ego selects useful responses through sparse per-query routing and injects them through gated residual write-back. This changes the compatibility requirement from global feature-map interpretability to local, typed response comparability under ego-issued queries, enabling a zero-training heterogeneous insertion protocol in which the ego interface is trained once and new collaborators join through checkpoint merging. Extensive experiments on simulated and real-world heterogeneous collaborative perception benchmarks validate the effectiveness and deployability of INTACT. On OPV2V-H, INTACT achieves 80.1 AP70 with only 0.52M additional parameters and 18.0 $\log_2$ communication volume, corresponding to about 16$\times$ compression over dense feature transmission. On DAIR-V2X, INTACT achieves 43.8 AP50 under challenging real-world conditions.

We propose a 3D-thinking-guided co-training framework that enables vision-language-action (VLA) models to perform 3D spatial reasoning implicitly during action prediction. Our core insight is that 3D geometry perception and 3D spatial reasoning are distinct capabilities that can be disentangled and injected at different feature hierarchies. During training, three tightly coupled components work in concert primarily within the latent space: (1) To gain geometric priors, a latent 3D geometry perception module aligns intermediate visual features with a 3D foundation model, acquiring low-level geometric cues without architectural modifications to the VLM backbone. (2) Complementing this, an online 3D reasoning distillation module mitigates the prompt-induced reasoning gap via a shared reasoning anchor token. During 3D VLM co-training, this anchor is emitted as the first output token to robustly encode spatial priors. During VLA training, it serves as an input token inserted between the task and action instructions, transferring high-level spatial thinking from explicit teacher reasoning prompts to student action prompts without chain-of-thought text generation. (3) These disentangled geometric and reasoning features are then united by a spatially augmented action integration, which jointly injects them into the action-query tokens as hierarchical spatial conditions to prevent action shortcuts. At deployment, our method retains only its lightweight adapters to perform implicit 3D reasoning, discarding the 3D foundation model and the teacher branch used for supervision. Consequently, it operates purely on 2D images without 3D sensors, external models, or explicit text generation while preventing catastrophic forgetting of the pretrained VLM, achieving state-of-the-art performance on LIBERO, LIBERO-PLUS, SimplerEnv, and real-world manipulation tasks.

Multimodal In-Context Learning (ICL) has emerged as a practical inference paradigm for Multimodal Large Language Models, where a small set of interleaved image-text In-Context Demonstrations (ICDs) conditions the model to solve new tasks. Despite its flexibility, multimodal ICL incurs high inference latency and suffers from instability due to sensitivity to demonstration formatting, ordering, and content. To address these limitations, we propose Hyper-ICL, a lightweight, training-based framework for demonstration-free multimodal ICL that reconstructs demonstration effects directly without requiring ICDs at inference time. Hyper-ICL learns a parameter-efficient low-rank logit-level adapter that calibrates attention distributions to better match demonstration-induced attention redistribution. To capture how demonstration influence varies across queries, we introduce a query-adaptive modulation mechanism that adaptively controls intervention strength at token level across layers and heads based on the current query. Finally, we propose a layer-wise hyperbolic anchor distillation loss that aligns intermediate student features to a demonstration-conditioned teacher via Lorentz geodesic distance. This loss encourages the student to reconstruct the demonstration-query relationships induced by ICDs. Extensive experiments across six different multimodal benchmarks (including VQAv2, OK-VQA, and COCO Caption) demonstrate that Hyper-ICL consistently improves accuracy and stability over vanilla ICL and existing state-of-the-art methods.

Vision-language models (VLMs) are increasingly used in multi-image, multi-turn agentic settings where decisions depend on visual changes. However, in existing open-weight VLMs, visual comparisons happen only inside the language model, while the visual encoder itself remains stateless: each image is encoded independently, without access to the prior visual context. As a result, small but task-critical changes may be attenuated before the language model has a chance to compare them, especially when those changes do not affect the high-level semantics of the scene. We introduce a Stateful Visual Encoder, which conditions each visual representation on prior visual features. Under supervised finetuning, VLMs equipped with stateful encoders achieve consistent improvements on controlled tasks involving cross-image spatial aggregation, multi-object visual differencing, and visual trajectory behavior cloning. These improvements are consistent across input resolutions, language model sizes, and VLM backbones. Finally, we validate our model on real-world tasks, including longitudinal radiology, fine-grained image comparison, and remote sensing, where stateful encoders consistently improve generalist VLM baselines and can match or surpass specialized models in selected domains. Project page: https://statefulvisualencoders.github.io/

Video diffusion transformers have achieved state-of-the-art visual quality, but their high inference cost remains a major bottleneck for real-time applications. Recent distillation frameworks produce autoregressive video diffusion models with reduced latency, yet these models still use a fixed number of denoising steps per frame, wasting computation on predictable frames and under-refining challenging ones. We present DSA, a confidence-guided adaptive computation framework for AR video diffusion. DSA introduces a lightweight confidence head, trained jointly with the generator under a distribution-matching distillation objective, to estimate per-frame denoising reliability. At inference, this confidence signal dynamically adjusts the number of diffusion steps: simple frames terminate early for speed, while complex frames receive additional refinement. Our method requires no extra video data, no heuristics, and little architectural modification. Experiments show that DSA achieves real-time autoregressive video generation, reaching 22.63 FPS with sub-second latency on H100 GPUs, while maintaining competitive or superior VBench quality compared to recent autoregressive and bidirectional video diffusion models. Our results demonstrate that confidence-guided adaptive sampling provides an effective and practical path toward interactive video generation.

Image segmentation remains fundamentally limited by boundary ambiguity arising from sampling-induced information loss and inherent uncertainty in pixel-wise labeling. Although encoder-decoder architectures such as U-Net achieve strong performance, they often produce overconfident predictions that fail to capture transition-region ambiguity. To address this issue, we propose \textbf{NoiseUNet}, a simple yet effective framework that injects bounded perturbations into skip connections to regularize cross-scale feature fusion. This mechanism enforces robustness to local feature variations and promotes boundary-aware representations. Theoretically, the perturbation induces an implicit fuzzification effect, yielding soft, data-driven memberships without requiring explicit fuzzy modeling. We further introduce \textbf{ThyR}, a real-world thyroid ultrasound dataset with inherently ambiguous boundaries. Experiments demonstrate that NoiseUNet consistently improves both segmentation accuracy and boundary fidelity.

MRI provides excellent soft-tissue contrast without ionizing radiation, but long acquisition times increase patient discomfort while also raising exam costs and limiting scanner throughput. A common approach to reduce scan time is to acquire fewer measurements, which yields an ill-posed linear inverse problem; recovering diagnostic-quality images therefore requires incorporating prior knowledge beyond the measured data. In follow-up exams, the most recent prior scan of a patient can provide a highly informative subject-specific context, but practical use is complicated by temporal changes (including pathology progression), misalignment between scans, and protocol drift across acquisitions. In this work, we introduce L-TGVN, a Longitudinal Trust-Guided Variational Network that leverages prior scans as side information to reconstruct the current scan from heavily undersampled measurements. Crucially, L-TGVN constrains the influence of prior scans to be consistent with the acquired measurements. Unlike many existing longitudinal reconstruction methods, it does not require explicit pre-registration between prior and current scans. It further accommodates differences in acquisition protocols across visits (e.g., changes in sequence parameters). We evaluate L-TGVN against matched-capacity baselines, including prior-guided methods and methods that do not use longitudinal priors, and observe consistent improvements in standard quantitative metrics together with better preservation of fine structures at challenging accelerations. Source code is available at github.com/sodicksonlab/L-TGVN.

Multi-view cardiac magnetic resonance (CMR) imaging provides complementary anatomical information and is widely used for noninvasive disease assessment. Recent transformer-based models have demonstrated strong representation learning capabilities for CMR analysis; however, they typically learn unified latent embeddings that entangle view-specific anatomical variations with disease-related features. Such entanglement biases classifiers toward structural attributes rather than view-invariant pathological patterns. This issue is exacerbated in low-data regimes, particularly for underrepresented cardiac conditions, where limited samples increase the susceptibility to shortcut learning and view-dependent decision boundaries. To address this, we propose a Motion-Guided View--Disease Disentanglement framework MoViD built upon a ViT-MAE backbone. The model explicitly factorizes latent representations into view-specific and disease-discriminative components using dual-branch supervised contrastive objectives and a gradient-reversal adversarial constraint that minimizes disease leakage into the view embedding. Additionally, an annotation-free temporal motion feature, derived from inter-frame difference maps, is introduced to localize the beating heart region and suppress background artifacts. A focal reweighting mechanism is incorporated into the contrastive loss to mitigate class imbalance. We evaluate the framework on a private clinical venous thrombosis dataset and two public benchmarks (M&Ms, M&Ms2). Across disease classification and cardiac segmentation tasks, our approach consistently outperforms standard transformer baselines and demonstrates competitive performance against large-scale pretrained foundation models, validating the efficacy of structural disentanglement in medical image analysis.

While neural video codecs (NVCs) have demonstrated superior compression ratio, their prohibitive computational complexity remains a critical barrier to real-world deployment. This paper introduces a chunk-based coding framework designed to significantly improve the rate-distortion-complexity trade-off. Instead of processing frames sequentially, our approach encodes a chunk of multiple frames into a single compact latent representation and decodes them simultaneously. This is enabled by cross-frame interaction modules for joint spatial-temporal modeling and frame-specific decoders for parallel reconstruction. This paradigm not only dramatically enhances coding throughput but also facilitates more effective modeling of long-term temporal correlations. To further boost speed, we propose a streamlined entropy coding mechanism that consolidates bit-stream interactions into a single step, substantially reducing decoding overhead. Building on these innovations, we present DCVC-UF (Ultra-Fast), a new NVC that sets a new SOTA in performance. Our experiments show that DCVC-UF can achieve ultra-fast encoding and decoding speeds, significantly outperforming previous leading codecs. DCVC-UF serves as a notable landmark in the journey of NVC evolution. The code is at https://github.com/microsoft/DCVC.

Foundation models have driven rapid progress in computer vision, yet the two dominant paradigms, vision-language foundation models (VLMs) and vision-only foundation models (VFMs), remain only partially compatible. VLMs offer language-grounded semantic alignment but are often visually coarse, while VFMs learn discriminative perceptual geometry but lack semantic grounding. We propose GPUA (Geometry-Preserving Unsupervised Alignment), a framework that integrates the complementary strengths of VFMs and VLMs. Inspired by cross-lingual alignment, GPUA treats VFM features as a visual language and learns an orthogonal mapping that translates the VFM space into the VLM semantic space, preserving geometry and narrowing the modality gap without labels or model parameter updates. GPUA is task-agnostic and requires only feature-level access to pretrained models. Experiments across diverse benchmarks demonstrate improved cross-model compatibility and strong gains in downstream zero-shot recognition and segmentation with negligible overhead. Code is available at https://github.com/Yuteam14/GPUA

Few-shot cross-category 3D anomaly detection aims to determine whether an unknown point cloud belongs to a target normal category using only a few normal references. Existing training-based methods usually require category-wise optimization, while recent training-free methods based on multi-view CLIP visual features mainly rely on visual similarity and may be confused by geometrically similar categories. In this paper, we propose VT-3DAD, a training-free framework for cross-category 3D anomaly detection via Visual-Text Normal Space Alignment. Given few-shot normal references and a test point cloud, VT-3DAD first generates realistic multi-view depth maps and extracts view-wise features using a frozen CLIP visual encoder. The visual branch measures reference-test deviation in the multi-view feature space. In parallel, depth-aware and 3D-aware prompts are encoded by the frozen CLIP text encoder to construct textual normal anchors, which provide semantic normality constraints for the target category. The final anomaly score is obtained by fusing visual deviation from normal references and semantic deviation from the textual normal space. Experiments on the ShapeNetPart dataset demonstrate that VT-3DAD achieves state-of-the-art performance. In particular, VT-3DAD improves the one-shot average AUC-ROC from 92.49% to 94.80% compared with the visual-only baseline, while also reducing the average standard deviation from 5.64 to 3.41.

Radiology reports describe kidney lesions by type, size, enhancement, and attenuation, yet existing 3D methods predict only at the patient or organ level. We reformulate kidney CT characterization as a per-lesion set-prediction task: one model emits a variable number of lesions per kidney, each with four clinical attributes. We curated 2,619 CT volumes from 788 patients at one academic medical center, with multi-granularity side- and per-lesion labels, and used KiTS23 (489 cases) for zero-shot external validation. We propose \textbf{LesionDETR}, a DETR-style architecture with size-distance Hungarian matching and a hierarchical loss that aggregates per-slot outputs to side-level objectives. Across four input representations and six encoder initializations, two design choices dominate: a segmentation mask as an input channel, and same-domain abdominal pretraining (SuPreM); generic large-corpus pretraining is no better than random initialization. LesionDETR reaches bilateral side-level abnormality AUC $0.799 \pm 0.009$ on UF-Health and $0.817 \pm 0.072$ on KiTS23. A count-conditioned variant reaches per-lesion mAP $0.190 \pm 0.083$ on cystic lesions; rare solid-lesion AP stays at the noise floor, pointing to targeted data collection, not architecture, as the next bottleneck. The framework yields verified per-lesion predictions for downstream structured report generation.

This paper presents HYolo, an intelligent IoT-based object detection framework that integrates hypergraph learning into the YOLO architecture. Traditional YOLO-based object detection models primarily capture pairwise feature interactions and may fail to model complex high-order relationships among objects and contextual features. To address this limitation, HYolo incorporates hypergraph learning to capture richer contextual dependencies and improve object representation. Experimental evaluation on the COCO dataset demonstrates significant performance improvements over baseline YOLO models. The proposed approach achieves approximately 12% improvement in mAP@50 while enhancing overall detection accuracy and robustness. By modeling high-order feature relationships, HYolo provides improved contextual understanding and more reliable object detection performance in IoT-based environments. The results indicate that integrating hypergraph learning into object detection pipelines offers a promising direction for intelligent and context-aware IoT vision systems.

Real-world multi-view data always suffer from imperfect information problem, where the view-specific observations are absent (i.e., Incomplete Views, IV) and cross-view correspondences are mismatched (i.e., Noisy Correspondences, NC) for certain instances. As a remedy, numerous IV- and NC-oriented multi-view clustering (MvC) methods have been proposed, which however require either reliable correspondences or sufficiently complete instances, thus stopping short of addressing the imperfect information problem. In contrast, we observe that both IV and NC challenges originate from the same issue of imperfect cross-view counterpart information, where the counterpart of an anchor instance in another view might be either unavailable or unreliable. Based on the observation, we propose a novel robust MvC framework, termed Posterior-guided Latent Counterpart Inference (PLCI), which could handle both IV and NC in a unified manner. Specifically, PLCI formulates the desired cross-view counterpart of each anchor instance as a latent variable, and integrates both instance-level reliability and prototype-level semantic transport to infer the posterior distribution of the latent counterpart. Extensive experiments on six widely-used multi-view datasets against 10 state-of-the-art MvC methods demonstrate the effectiveness of PLCI for tackling the imperfect information problem. The code will be released upon acceptance.

Vision-language models (VLMs) have shown remarkable performance in various robotic tasks, as they can perceive visual information and understand natural language instructions. However, when applied to robotics, VLMs remain subject to a fundamental limitation inherent in large language models (LLMs): they struggle with numerical reasoning, particularly in object detection and object-state localization. To explore numerical reasoning as a regression task in VLMs, we propose a novel training strategy to adapt VLMs for object detection and object-state localization. This approach leverages box decoder outputs to compute an Auxiliary Regression Loss (ARL) during fine-tuning, while preserving standard sequence prediction at inference. We leverage this training strategy to develop StateVLM (State-aware Vision-Language Model), a novel model designed to perceive and learn fine-grained object representations, including precise localization of objects and their states, as well as graspable regions. Due to the lack of a benchmark for object-state affordance reasoning, we introduce an open-source benchmark, Object State Affordance Reasoning (OSAR), which contains 1172 scenes with 7746 individual objects and corresponding bounding boxes. Comparative experiments on adapted benchmarks (RefCOCO, RefCOCO+, and RefCOCOg) demonstrate that ARL improves model performance by an average of 1.6% compared to models without ARL. Experiments on the OSAR benchmark further support this finding, showing that StateVLM with ARL achieves an average of 5.2% higher performance than models without ARL. In particular, ARL is also important for the complex task of affordance reasoning in OSAR, where it enhances the consistency of model outputs.

In this report, we present our solution for Track 2 of the CVPR 2026 VidLLMs Challenge. This track evaluates visual relational reasoning in videos, where models must infer relations that are not always explicitly visible. We propose Answer Self-Consistency with Margin-Triggered Question Re-Arbitration (ASC-MQRA), a training-free test-time reasoning framework built on a multimodal reasoning model. The core ASC component performs multiple stochastic video question-answering runs and aggregates their answer choices through answer-level self-consistency. This substantially improves over single-pass inference and forms our final test submission. We further study MQRA, a conditional re-arbitration module for low-margin examples where the first-stage vote distribution indicates uncertainty. Our vote-margin analysis shows that low-margin examples often retain the ground-truth answer among the top candidates, motivating MQRA to narrow the candidate set and re-watch the video only over the retained candidates. On validation, MQRA further improves over ASC, indicating that low-margin vote distributions can provide a useful uncertainty signal. On test, however, MQRA slightly degrades performance relative to ASC, suggesting that re-arbitration is sensitive to the size and category distribution of the triggered subset. Our final test submission therefore uses ASC without re-arbitration, achieving 72.73 average accuracy and 78.34 category-wise macro average accuracy on validation, and 81.16 average accuracy and 80.91 category-wise macro average accuracy on test. This report details our prompting strategy, implementation setup, ablation studies, and diagnostic analyses. The code is available at https://github.com/data-analytics-labo/ASC-MQRA

We propose a neural formulation for estimating the appearance of complex luminaires. We focus on challenging luminaires with complex light transport (e.g., small emitters enclosed by multiple specular layers) that are difficult for (bidirectional) path tracing. To this end, we use light tracing to construct paths from emitters to the exit surfaces and formulate appearance estimation as a distribution learning problem. Specifically, we model the probability density function (pdf) of outgoing radiance on the exit surfaces using a large normalizing flow network, and recover the outgoing radiance as the product of the estimated pdf and flux. To enable efficient inference, we distill the learned appearance into a lightweight MLP that directly estimates radiance on the exit surfaces. We additionally train a sampling network for effective direct illumination computation from the luminaire, and a blending network to composite the luminaire into the scene. Our formulation makes it feasible to render challenging luminaires using low sample counts in arbitrary scenes.

Acquiring labeled medical image data is resource-intensive and a challenge further exacerbated in cross-domain scenarios where source and target datasets differ in imaging equipment, population, or clinical site. This study introduces XSSR (Cross-Domain Self-Supervised Representative Selection), a framework designed to minimize annotation effort in the target domain while maintaining robust segmentation performance. XSSR comprises three stages: first, a Masked Autoencoder (MAE) is trained on unlabeled source data to establish a shared embedding space without requiring target labels; second, a greedy selection algorithm scores unlabeled target samples based on a composite density, novelty, and diversity criterion; and third, a U-Net segmentation model is trained exclusively on the selected subset. The novelty-diversity trade-off parameter, alpha, is automatically calibrated by minimizing embedding-space coverage, eliminating manual tuning. We evaluate XSSR on three public benchmarks: Chest X-ray, RIGA+ retinal fundus imaging, and multi-site Prostate MRI, each under a fixed 5% annotation budget. XSSR achieves 99.3% of full-data performance on Chest X-ray using only 22 labeled samples, surpasses random selection by up to 2.5 Dice points on Prostate MRI, and consistently outperforms the CoreSet baseline by 0.4 to 1.2 Dice points across all datasets. Ablation studies indicate that diversity is the most influential scoring component, and per-site analysis shows that performance correlates with scanner similarity to the source domain.

We consider the problem of generating images whose internal structure -- defined by the distribution of patches across multiple scales -- matches that of a single reference image. Recent approaches address this problem by training a diffusion model on a single image. But even in this setting, training is computationally expensive and requires hours of optimization. Instead, we model the image using a dataset of its patches at different scales. As this dataset is finite and the dimensionality of its patches is small, the score function for a noisy patch can be computed tractably using an optimal, closed-form denoiser, eliminating the need for neural network training. We integrate this patch-based denoiser into an efficient, training-free image diffusion model, and we describe how our method connects to classical patch-based image restoration techniques. Our approach achieves state-of-the-art generation quality and diversity compared to trained single-image diffusion models, and we demonstrate applications, including unconditional image generation, text-guided stylization, image symmetrization, and retargeting. Further, we show that our approach is compatible with latent space diffusion, and we show multiple additional acceleration techniques to achieve megapixel single-image generation in one second, and gigapixel generation in minutes.

3D vision has rapidly evolved, driven by increasingly diverse data representations, learning paradigms, and modeling strategies. Yet the field remains fragmented across representations and benchmarks, making it difficult to develop unified perspectives on efficiency, fidelity, and scalability. This work provides a data-centric taxonomy of 3D vision that connects geometric representations, datasets, learning frameworks, and applications within a single conceptual map. We begin by analysing the principal structural representations of 3D data--point clouds, meshes, voxels, and 3D Gaussians--along with their acquisition pipelines. We then examine how dataset design, benchmark construction, and supervision regimes shape recent advances, spanning 2D-supervised 3D learning, implicit neural representations, and 4D world modeling. Through this integrative lens, we clarify the relationships among representations, learning paradigms, and downstream tasks in reconstruction, generation, and video modeling, offering a consolidated view of emerging trends toward balancing efficiency and fidelity and toward multimodal geometric grounding.

Multimodal large language models (MLLMs) are predominantly evaluated on free-form vision-language tasks such as visual question answering, captioning, and summarization. However, their practical use is rapidly expanding to more structured computer vision settings, where users prompt models to perform localization-centric tasks such as object detection, often within larger agentic or decision-making systems. Despite this shift, there is currently no standardized benchmark that systematically evaluates these capabilities at scale. In this work, we introduce the first comprehensive benchmark specifically designed to assess the promptable localization abilities of generalist MLLMs. Our benchmark spans four core task categories: object detection, referring expression detection, instance-level detection, and video-based detection. To enable consistent and fair evaluation, we develop a unified framework that standardizes inputs, enforces parsable bounding box outputs, and defines transparent evaluation protocols across tasks. Using this suite, we evaluate a diverse set of open-source and proprietary MLLMs, providing an in-depth analysis of their performance and limitations. Beyond accuracy, we examine models' ability to adhere to output format specifications, showing that current systems are highly sensitive to formatting constraints and often fail to generalize even to minor variations. Our results highlight both the strengths and shortcomings of state-of-the-art MLLMs in localization settings, and point toward important directions for improving multimodal model design and evaluation.

Autonomous driving has shifted from modular perception-prediction-planning stacks toward end-to-end (E2E) models that map sensor inputs directly to vehicle control, often regularized by auxiliary tasks such as 3D detection, motion forecasting, and HD-map perception. Progress is driven by a fast-growing ecosystem of sensor-rich driving datasets, yet each ships its own file formats, APIs, coordinate conventions, and modality coverage, leaving cross-dataset experimentation and even basic per-dataset preprocessing to be re-implemented per project. We present StandardE2E, a framework that provides a single unified interface over E2E driving datasets. StandardE2E (i) standardizes per-dataset preprocessing under one shared data schema; (ii) combines multiple datasets in a single PyTorch DataLoader for cross-dataset pretraining, auxiliary-task supervision, and scenario-level filtering; and (iii) reduces adding a new dataset to a single per-dataset mapping from raw frames to the canonical schema, leaving the entire downstream pipeline unchanged. The framework supports six datasets out of the box: Waymo End-to-End, Waymo Perception, Argoverse 2 Sensor, Argoverse 2 LiDAR, NAVSIM (OpenScene-v1.1), and WayveScenes101, and is released as the open-source standard-e2e Python package, available at https://github.com/stepankonev/StandardE2E.

Deformable object manipulation (DOM) is challenging due to high-dimensional, partially observable states that evolve through long-horizon, topology-changing interactions with multiple valid manipulation modes. We introduce Instant-Fold, an in-context imitation learning framework for DOM. Given a single human demonstration, our policy infers and executes diverse manipulation modes directly from the demonstration, including variations in spatial execution and ordering, without requiring gradient updates. Our approach first learns deformation-aware visual representations via temporal contrastive pretraining, after which a flow-matching transformer policy conditioned on the demonstration predicts actions to execute the intended manipulation mode. Trained entirely in simulation, Instant-Fold generalizes across diverse folding modes and transfers zero-shot to real-world settings without additional data collection or finetuning. Videos are available at https://instant-fold.github.io.

Recent years have seen remarkable progress in unified vision-language models handling both multimodal understanding and generation within a single architecture. While autoregressive VLMs can reason across modalities, they fail to generate high-quality images. In contrast, diffusion models produce photorealistic visuals yet struggle to generate coherent text, making it challenging to develop a single unified model that can seamlessly handle both visual and text generation. Recent advances suggest that language can be effectively embedded within visual representations, allowing models to reason about textual semantics directly from images. To this end, we propose UniCanvas, a first attempt that unifies diffusion models to generate interleaved multimodal contents through text-in-image generation. Diffusion models naturally capture transformations on a shared pixel canvas, which can be viewed as world models of visual change. Instead of producing discrete text tokens, the model learns to represent language as visual patterns inside images, leveraging its inherent multimodal embedding space. This design allows the model to "draw" text naturally within a single pixel canvas during image synthesis, achieving seamless multimodal generation. Experiments demonstrate that UniCanvas improves performance over previous unified models, positioning text-in-image generation with diffusion models as a promising unified multimodal generation paradigm.

Curating training data is among the most consequential yet labor-intensive parts of modern AI development: practitioners iteratively propose, implement, evaluate, and revise data policies against noisy benchmark feedback. We ask whether generalist coding agents can automate this data-curation loop. We introduce *Curation-Bench*, an agent-centric benchmark that fixes the model, training recipe, and evaluation suite while giving agents command-line access to inspect data, implement policies, submit them to a fixed training/evaluation pipeline, and revise. In a vision-language instruction-tuning instantiation, out-of-the-box agents reach strong published data-selection baselines within ten iterations. However, trajectory analysis reveals a persistent *execution-research gap*: agents mainly tune local policy variants rather than explore new policy families, even when given strategy guides and paper references. Scaffolds requiring each iteration to cite, instantiate, and adapt a prior method shift agents toward method-guided exploration. The scaffolded agent autonomously composes -- without human design input -- a data-selection policy that outperforms strong published baselines at one-tenth their data budget. Overall, current agents can run the curation loop, but reliable data research requires scaffolded method adaptation, not open-ended prompting alone. Code and benchmark are open-sourced.

Reconstructing thin 3D structures is challenging due to their sparsity, scale variation, and complex geometry. Such structures arise in a wide range of domains, including medical imaging of vascular systems and industrial pipe systems. While recent neural methods perform well on dense surfaces, they often fail to recover fine thin geometries. We propose a reconstruction approach based on local depth projections, which provide an efficient and informative 2D representation of thin structures. Specifically, we traverse the 3D model with a sliding box to generate local orthographic depth projections, which are processed by a neural network to reconstruct missing thin structures in 2D. The local reconstructions are subsequently fused back into the 3D model to produce a coherent and detailed shape. Experiments on pulmonary artery reconstruction from CT volumes and industrial pipeline recovery from synthetic and real scans demonstrate improved preservation of fine structural details over existing methods.

Prospective reconstruction is crucial in many clinical applications such as MRI-guided radiotherapy, which demands accurate image reconstruction and fast motion estimation from currently acquired measurements. However, prospective reconstruction remains challenging due to ultra-sparse sampling and stringent latency requirements. In this work, we propose PDMR, a Prospective Dynamic 3D MRI Reconstruction framework with latent-space motion tracking. Our core idea is to learn an efficient and generalizable latent manifold of motion fields offline, enabling rapid online adaptation for prospective reconstruction. Specifically, we parameterize the deformation vector fields (DVFs) on a low-dimensional manifold, effectively reducing the search space for fast online adaptation, and employ a tri-plane representation to achieve geometry-aware and memory-efficient encoding of 3D motion. Experiments on both XCAT digital phantoms and in-house abdominal MRI datasets demonstrate that PDMR achieves high-fidelity and temporally consistent reconstruction across multiple prospective scenarios (Immediate and After-2min), outperforming state-of-the-art retrospective and online methods. Our results suggest a promising pathway toward ultra-fast, motion-aware prospective MRI reconstruction in clinical practice.

Multimodal large language models are increasingly capable of complex reasoning, yet their performance often degrades when they must externalize a problem through a tool and then reason over the tool's output, specifically when they rely on visual aids. This gap is especially important because real engineering and scientific workflows often rely on visualization tools for analysis, validation, and decision-making. To study this discrepancy, we introduce VAMPS (Visual-Assisted Mathematical Problem Solving), a benchmark for graph-assisted mathematics. VAMPS contains 1,168 multimodal, bilingual multiple-choice question-answer pairs drawn from Iranian University Entrance Exam algebra and calculus problems and expanded with human-reviewed LLM-generated synthetic variants, all selected so that plotting provides a natural solution strategy by revealing intersections, extrema, asymptotes, etc. Designed for both benchmarking and diagnosis, VAMPS goes beyond prior multimodal benchmarks that primarily evaluate reasoning over fixed visual inputs by testing whether a model can benefit from constructing a useful graph and grounding its answer in the resulting visualization. Overall, we found that across a diverse set of models, direct analytical solving surprisingly outperforms tool-enabled visual solving, even on problems where plotting is a natural strategy.

Retrieval over visually-rich documents, pages that interleave text with figures, tables, and charts, is essential for multimodal retrieval-augmented generation, yet most retrievers still discard the visual channel. The \emph{Multimodal Document Retrieval Challenge}, Track~1 of the MIR Challenge at the first EReL@MIR workshop, co-located with The Web Conference 2025, asks participants to build a \emph{single} retrieval system that handles two complementary regimes: closed-set document page retrieval within long documents from a text query (MMDocIR), and open-domain retrieval of Wikipedia-style passages from an image or image-plus-text query (M2KR). Systems are ranked by the macro-average of mean Recall@$\{1,3,5\}$ over the two tasks. The challenge drew 455 entrants and 586 submissions across 22 teams. This report describes the challenge design, datasets, and evaluation protocol; reports the final standings; and analyses the three winning teams' systems. All three build on decoder-based Multimodal-LLM embedders from the Qwen2-VL family rather than on CLIP-style encoders, and differ chiefly in whether they reach the top through fine-tuned ensembles, training-free multi-route fusion with a strong vision-language re-ranker, or zero-shot late interaction. The training-free system finished within $0.1$ point of the fine-tuned winner.

The growing popularity and capacity of generative models have eroded the distinction between human and machine-generated content, motivating a growing body of work on detection across text, images, and audio. Most available detectors are either commercial software or, if open-source, come with incompatible codebases with bespoke preprocessing, evaluation protocols, and evaluation metrics, which make their adoption, fair comparison, and reproduction quite difficult. To address this critical gap, we introduce DetectZoo, a first-of-its-kind, extensible toolkit designed to provide a unified interface for AI-generated content detection across text, audio, and image modalities. DetectZoo standardizes the complete empirical pipeline, from data ingestion and preprocessing to model assessment, offering researchers a cohesive framework to benchmark state-of-the-art detectors systematically. By integrating diverse public datasets and baseline detection algorithms under a single, unified API, our toolkit facilitates rigorous and reproducible evaluation. DetectZoo provides reference implementations of 61 detectors, native loaders for 22 benchmark datasets, and a standardized evaluation pipeline that reports multiple metrics through a common interface. Each detector is self-contained yet accessible through the same interface, automatically caches pretrained weights, and reproduces the original published results. DetectZoo lowers the barrier to entry for multi-modal AI forensics, enabling researchers to identify performance gaps across domains and accelerating the development of robust, generalizable detection techniques. The open-source repository and comprehensive documentation are publicly available at https://github.com/sadjadeb/DetectZoo, and the package can be installed via pip install detectzoo.

Remote photoplethysmography (rPPG) achieves low heart-rate error on uncompressed benchmarks yet is deployed over compressed video channels in telehealth, neonatal ICU, and driver fatigue applications. No prior work identifies the physical quantity determining when spatial decomposition outperforms global-projection methods under codec compression. We propose Spatial Artifact Coherence (SAC), defined as the ratio of off-diagonal to diagonal energy in the 4x4 inter-patch Green-channel covariance matrix (bandpass 0.75-2.5 Hz), and the PatchPCA algorithm family (four codec-aware rPPG algorithms). We evaluate 280 subjects across three public datasets, 11 codec degradation variants (MPEG-4, H.265, H.264, JPEG, chroma subsampling), and 13 algorithms via Wilcoxon tests (BH-FDR, q < 0.05, 904 tests). SAC explains 93.8% of between-variant variance in PCA advantage (r = +0.969), with zero overlap between codec families: non-MPEG-4 variants cluster at SAC 0.10-0.18 with 84-90% PCA win rates, while MPEG-4 variants cluster at SAC 0.48-0.59 with 61% win rate and a 5.8x reduction in mean improvement. Within subjects, 78% confirm the expected pattern (p < 10^-22, dz = 0.73). Within-variant subject-level SAC correlation is r = +0.099, confirming SAC classifies codec families rather than predicting individual outcomes. MPEG-4's effect is structural (macroblock DCT geometry, not noise amplitude), governed by source codec state, not resolution. P-Hybrid is identified as the most deployment-robust algorithm. Two necessary operating conditions for PatchPCA advantage are established: SAC < 0.30 and low-to-moderate motion, directly ruling out raw-to-MPEG-4 transcoding pipelines. SAC provides a physically grounded metric for codec-aware rPPG algorithm selection in clinical remote monitoring systems.

Practical text-recognition pipelines for historical documents typically decompose layout analysis into line detection followed by a separate reading-order step, with the latter most often handled by a hand-coded geometric heuristic that struggles with marginalia, multiple columns, tables, and source-specific editorial conventions. This article introduces Orli (Ordered Regression of Lines), an end-to-end model that casts both sub-tasks as a single image-to-sequence problem: from a page image, Orli autoregressively generates text-line baselines directly in reading order. Baselines are represented in a chord-frame parameterization that anchors a line's position, orientation, and extent while encoding local geometry through perpendicular offsets; an iterative refinement head and a local visual refiner produce the final curve. Trained on a heterogeneous corpus of 196,691 pages spanning ten writing systems, Orli marginally exceeds the previously reported state of the art for cBAD line detection without dataset-specific training, reaches near perfect coverage and ordering on multiple reading-order benchmarks zero-shot, and adapts to more specialized out-of-domain layouts with limited fine-tuning. The method's source code and model weights are available under an open license at https://github.com/mittagessen/orli.

Image geolocation aims to estimate where a photograph was taken from its visual content. At worldwide scale, this remains challenging because visual evidence is often ambiguous, diverse, and unevenly distributed. Prior work has typically treated geolocation of ordinary internet photos and street-view imagery as separate tasks, despite their complementary strengths: internet photos better match the appearance distribution of user-captured queries, while street-view imagery provides denser, geographically grounded coverage. We present Pinpoint, a retrieve-and-rerank architecture that combines both sources in a coarse-to-fine pipeline. A contrastive image-GPS embedder is trained on both user-uploaded Flickr photos and street-view imagery, learning a shared image-GPS embedding space that is used to retrieve candidate locations. An attention-based reranker then rescores retrieved candidates by combining candidate-level visual and GPS features with cross-source evidence from nearby locations to ground the prediction. Unlike recent prior work, Pinpoint does not rely on multimodal large-language models, making inference faster and more reproducible. Pinpoint achieves state-of-the-art results across all metrics on standard benchmarks for internet photos (IM2GPS3k and YFCC4k) and street-view imagery (OSV-5M).

Single-view 3D generative models have achieved impressive visual quality, yet they are not designed to satisfy structural or functional requirements, and in practice, often fall short. Symmetry is one such requirement: violations, even subtle ones, on symmetry can render a model physically unusable. We present SymTRELLIS, a method that enforces arbitrary finite point group symmetries (rotational, reflectional, and polyhedral) during the flow-based 3D generation of TRELLIS.2, without retraining the underlying VAE or flow model. Our key idea is to approximate the latent-space action of spatial transformations as a learned linear operator on voxel latents, implemented as a lightweight spatial-transform latent mapper trained on generic, non-symmetric 3D data. At generation time, we enforce symmetry by averaging predicted flow velocities across all symmetry-equivalent transformations at each ODE step, a process we call velocity symmetrization. The symmetry specification can be estimated automatically from an initial TRELLIS.2 generation or supplied by the user, enabling deliberate fold manipulation beyond what the input image suggests. On a curated benchmark of 266 strictly symmetric objects spanning 2- to 20-fold rotations and polyhedral symmetry groups, SymTRELLIS substantially reduces all symmetry error metrics compared to TRELLIS.2, Hunyuan3D-2.1, and TripoSG, while maintaining reconstruction accuracy comparable to the base model.

Single-image reflection separation is highly challenging under extreme conditions like glare or weak reflections. Existing methods often struggle to recover both layers in glare or weak-reflection scenarios because of insufficient information. This paper presents a diffusion model explicitly fine-tuned for this task, leveraging generative diffusion priors for robust separation. Our method simultaneously generates transmission and reflection layers through a unified diffusion model, incorporating a novel cross-layer self-attention mechanism for better feature disentanglement. We further introduce a disjoint sampling strategy to iteratively reduce interference between the layers during diffusion and a latent optimization step with a learned composition function for improved results in complex real-world scenarios. Extensive experiments demonstrate that our approach surpasses state-of-the-art methods on multiple real-world benchmarks. Project page: https://brian90709.github.io/diff-reflection-separation/

Video misinformation increasingly operates at the semantic and evidential level: authentic footage may be selectively edited, temporally reordered, spliced across sources, or augmented with AI-generated content to construct false narratives. Such evidence-dependent manipulations cannot be reliably verified from the input video alone, because the missing, reordered, replaced, or recontextualized evidence lies outside the video itself. We introduce \textbf{EVID-Bench}, a benchmark for search-grounded video misinformation detection, where a system must search the open web for related videos and identify what information is false through cross-video comparison. EVID-Bench comprises 222 videos spanning 9 manipulation types across 3 categories: AI generation, single-source editing, and multi-source editing. All samples are verified to be undetectable by frontier models through visual inspection alone. We evaluate nine frontier multimodal models using a retrieval-augmented verification baseline. The best system achieves only 61.43\% point-level accuracy and 43.24\% video-level accuracy, while AI-generated manipulations remain especially challenging. Error analysis reveals recurring challenges: models fixate on irrelevant anchors, misattribute synthetic content to editorial splicing, and terminate search prematurely before fully explaining the manipulation.

Flow matching models learn to transport samples from a simple prior distribution to a complex data distribution. When prior-data pairs are coupled via optimal transport (OT), the learned trajectories are straight and non-crossing, enabling fast, even single-step, generation. However, computing the OT coupling in high dimensions is intractable, and existing methods attempt to solve the OT problem, at the cost of persistent bias or significant overhead. Rather than solving for the OT coupling, we reformulate the problem. Once the prior is treated as a design choice rather than a fixed input, the OT coupling between prior and data is no longer unique. Many priors admit an OT-optimal identity coupling to the data, leaving us free to choose one that is also tractable to sample. We identify low-frequency projection of natural images as such a choice. The identity coupling between data and its low-frequency representation is empirically OT-optimal, the prior is structured enough to be sampled by a lightweight model at inference, and the remaining flow-matching task reduces to synthesizing high-frequency detail. Interpolating the prior with Gaussian noise further improves generation quality while preserving the OT coupling. The approach requires no modifications to the flow model itself, and integrates naturally with latent-space models, classifier-free guidance, and one-step generation frameworks. Across all benchmarks, our method reduces trajectory curvature by more than $2\times$ compared to existing flow matching methods, yielding better generation quality in the few-step regime.

Large-scale web-harvested datasets have fueled the progress of cross-modal retrieval but inevitably suffer from noisy correspondence, which severely degrades model generalization. Existing methods primarily address this by filtering out noise or seeking a substitute label, yet they predominantly remain bound by a "Discrete Selection" paradigm. We argue that relying on a single discrete proxy induces Single-Point Fragility and Discretization Error. To overcome these limitations, we propose a novel framework, Intra-modal Neighbor-aware Noise Rectification (IN2R), which shifts the paradigm from searching for a substitute to synthesizing a reliable supervision target. Leveraging the intrinsic geometric stability of intra-modal data, IN2R employs a Graph Refiner to perform relational reasoning over neighbors retrieved from a dynamic Cross-Model Memory. Instead of propagating discrete labels, our method synthesizes a continuous, soft prototype that reflects the consensus of the local semantic neighborhood, effectively rectifying inter-modal misalignment. Extensive experiments on Flickr30K, MS-COCO, and CC152K demonstrate that IN2R significantly outperforms state-of-the-art methods. Our code and pre-trained models are publicly available at https://github.com/liuyyy111/IN2R.

Weakly Incremental Learning for Semantic Segmentation (WILSS) suffers from the continuous introduction of noisy supervision, which progressively corrupts class-level representations, leading to severe feature drift and semantic corruption, thereby causing newly learned classes to overwrite old ones. To address these issues, we propose a drift-resilient WILSS approach, named SASA, designed to stabilize semantic learning via Semantic Anchors and Spatial Arbitration. Specifically, at the representation level, we introduce semantic anchors of learnable tokens as rigid class-level references to preserve long-term semantic identity. Complementary to this, an elastic residual adaptation facilitates controlled, instance-specific refinement, ensuring a stable yet flexible learning trajectory. At the supervision level, we develop a Spatial Label Arbitration mechanism that performs geometry-aware decisions to directly filter unreliable signals and enforce a strict "one object, one class" constraint. By synergistically stabilizing representations and improving supervision reliability, SASA effectively mitigates feature drift under weak supervision. Extensive experiments on standard benchmarks demonstrate that our approach consistently outperforms existing state-of-the-art methods, particularly in challenging multi-step incremental settings. The code is available at https://github.com/ZhonggaiWang/SASA.

In embodied vision-language decision making tasks such as robotic manipulation and navigation, Vision-Language and Vision-Language-Action Models (VLMs & VLAs) are powerful tools with different benefits: VLMs are better at long-term planning, while VLAs are better at reactive control. However, their performance is limited by the same perceptual bottleneck: visual hallucinations arise due to the models' inability to distinguish task-relevant objects from distractors. In principle, accurate identification and focus on critical objects while filtering out irrelevant ones is the key to break this limitation. A straightforward solution is one-step focus: directly attending to essential objects. However, this approach proves ineffective because effective focus inherently requires deep scene understanding. To this end, we propose SceneDiver, a coarse-to-fine focus plan generation method for VLMs leveraging their long-term planning abilities, that first constructs a holistic scene graph to establish initial comprehension, then progressively decomposes the task into simpler sub-problems through an iterative cycle of recognition, understanding, and analysis. To enable reactive control, we also design a lightweight adapter for distilling the deliberate focus ability into VLAs. Evaluations on standard embodied AI benchmarks confirm that our method substantially reduces visual hallucinations for both VLMs and VLAs, while preserving computational efficiency in tasks requiring fast execution. Our code and data are released at: https://future-item.github.io/SceneDiver.

We present AAD-1, an Asymmetric Adversarial Distillation framework for One-step autoregressive image-to-video generation. State-of-the-art methods adopt adversarial distillation but suffer from motion collapse and training instability, resulting in static videos. AAD-1 addresses these challenges through two key designs in architecture and training strategy. Our key architectural insight is to break the symmetry between generator and discriminator. While the generator remains causal to preserve autoregressive sampling capability, the discriminator attends bidirectionally over the full spatiotemporal context and produces a single holistic realism score for the entire video sequence. This asymmetric design enables the discriminator to effectively detect global temporal failures and long-range drift that cause motion collapse in autoregressive generation. To stabilize training, we introduce a phased strategy that first uses distribution matching to bootstrap a stable one-step generator, providing a warm-up phase that brings the student distribution closer to the teacher before adversarial distillation begins. Extensive experiments on VBench demonstrate that AAD-1 achieves state-of-the-art performance in one-step autoregressive video generation.

Video-Action Models (VAMs) leverage the broad visual dynamics captured by pre-trained video diffusion models, offering a promising path toward generalizable robot manipulation. However, RGB-only video rollouts are not directly actionable: they leave metric 3D motion, contact geometry, and fine-grained spatial constraints under-specified, making action grounding ambiguous. Meanwhile, scaling action supervision across diverse tasks and embodiments remains costly. We present PointAction, a framework that bridges video predictions to robot actions through explicit point-based 4D modeling. PointAction fine-tunes a foundation video generation model to jointly predict future RGB frames and dynamic 3D pointmaps, producing temporally consistent 3D motion of task-relevant scene geometry. These point dynamics serve as a structured, embodiment-agnostic action interface, which a diffusion-based action decoder maps to executable robot actions. By using metric 3D point dynamics as the interface between video prediction and control, PointAction reduces the ambiguity of RGB-only action grounding and supports transfer across tasks and embodiments with limited action supervision. Experiments show that PointAction achieves state-of-the-art 4D generation quality on robot scenes, outperforms existing baselines in simulation, and generalizes to two real robot arms unseen during pretraining.

Few-step distillation has become an effective strategy for accelerating advanced visual generative models, yet prior work has largely focused on distillation objectives. In this work, we revisit few-step distillation from a complementary perspective, focusing on the training recipe that critically shapes student performance. Using Qwen-Image-2.0 as a representative case, we systematically investigate three factors in unified text-to-image generation and instruction-guided image editing distillation: data composition, teacher guidance, and task mixture. Our empirical analysis reveals several non-obvious behaviors, which motivate the development of Qwen-Image-Flash. Overall, our results suggest that effective few-step distillation requires not only carefully designed objectives, but also principled organization of the broader training pipeline.

Vision-Language-Action (VLA) models have achieved remarkable success in language-conditioned robotic manipulation. However, deploying these models in open-ended environments requires continuously acquiring novel skills, a process that inevitably triggers severe catastrophic forgetting of previously learned behaviors. While experience replay (ER) serves as a standard mitigating strategy, naive uniform sampling fundamentally misaligns with the temporal characteristics of manipulation trajectories. It systematically under-samples brief but causally critical sub-skills, leading to phase starvation, and completely overlooks the varying degrees of forgetting across historical tasks. To overcome these limitations, we introduce PHASER, an architecture-agnostic continual learning framework. PHASER employs a phase-centric capacity allocation to guarantee equal memory support for all sub-skills, coupled with a multi-modal interference routing strategy that dynamically prioritizes historical phases at high risk of forgetting. Furthermore, to enable fully autonomous lifelong adaptation, we integrate Auto-PC, a lightweight pipeline combining unsupervised action-signal change-point detection with VLM-based semantic verification to extract temporal boundaries without intensive manual supervision. Evaluated across three VLA backbones on LIBERO continual learning suites, PHASER yields substantial empirical improvements, increasing Average Success Rate (ASR) by up to 31% over matched-budget ER and achieving an 87.8% final ASR on the LIBERO-Goal CL setting.

Reasoning segmentation aims to segment target objects described by complex language through joint visual-textual reasoning. Existing methods typically rely on either learned semantic tokens to bridge Multimodal Large Language Models (MLLMs) and segmentation models, suffering from difficult cross-modal alignment, or explicit spatial prompts such as bounding boxes, which may lose holistic response semantics. To address these limitations, we propose Attention-Guided and CoT-Enhanced Coarse-to-Refined Reasoning Segmentation, termed CR-Seg, a two-stage framework for coarse-to-refined reasoning segmentation. Specifically, we design an Extract Attention Maps and Points (EAP) module to extract attention maps for coarse target localization and select informative points, both of which are fed into SAM for mask refinement. To alleviate reasoning--answer inconsistency, we further introduce Global-to-Local Chain-of-Thought (GLCoT), which guides the model to reason progressively from global scene context to local target details. Extensive experiments on reasoning segmentation benchmarks demonstrate the effectiveness of CR-Seg.

Audio-driven human motion video generation aims to synthesize realistic and temporally coherent human animations from a single static image, with applications in talking-head synthesis, co-speech gesture generation, and dynamic presentations. Moving beyond conventional keypoint-based methods that often struggle to capture subtle motion dynamics, We propose a novel implicit-motion framework for generating realistic and temporally coherent human motion videos from a single static image and audio. Our approach uses a two-stage pipeline that decouples motion prediction from rendering. The first stage integrates appearance priors and hierarchical depth cues into a region-aware attention mechanism to model latent motion features. The second stage employs a Mamba-enhanced diffusion model to directly predict these features from audio and the source image, enabling unsupervised learning of fine-grained motion patterns. This decoupled architecture enhances flexibility and efficiency. Trained on a new 380-hour high-quality dataset, our method outperforms prior work across multiple public benchmarks and our collected data in accuracy, naturalness, and temporal coherence, setting a new state-of-the-art.

Hallucination has recently garnered significant research attention in Large Vision-Language Models (LVLMs). Direct Preference Optimization (DPO) aims to learn directly from the corrected preferences provided by humans, thereby addressing the hallucination issue. Despite its success, this paradigm has yet to specifically target the perceptual bottleneck in attended regions or address insufficient Visual Robustness against image degradation. Furthermore, existing preference pairs are often vision-agnostic and their inherently off-policy nature limits their effectiveness in guiding model learning. To address these challenges, we propose Perceptual Processing Direct Preference Optimization (P$^2$-DPO), a novel training paradigm in which the model generates and learns from its own preference pairs, thereby directly addressing the identified visual bottlenecks while inherently avoiding the issues of vision-agnostic and off-policy data. It introduces: (1) an on-policy preference pairs construction method targeting Focus-and-Enhance perception and Visual Robustness, and (2) a well-designed Calibration Loss to precisely align visual signals with the causal generation of text. Experimental results demonstrate that with a comparable amount of training data and cost, P$^2$-DPO outperforms strong baselines that rely on costly human feedback on benchmarks. Furthermore, evaluations on Attention Region Fidelity (ARF) and image degradation scenarios validate the effectiveness of P$^2$-DPO in addressing perceptual bottleneck in attended regions and improving Visual Robustness against degraded inputs.

Reinforcement learning from expert videos across visually distinct domains is challenging due to the absence of reward signals and the presence of domain gaps. We introduce XIPER (Cross-domain Video Prediction Reward), a reward model for learning from expert videos collected in a visually different domain, where the agent's appearance differs due to factors such as color, morphology, or the sim-to-real gap. More specifically, XIPER trains a cross-domain video prediction model that maps agent observations into the expert domain and uses the prediction likelihood as a reward signal. Experiments on the DMC Color Suite (8 tasks) and DMC Body Suite (3 tasks) show that XIPER consistently outperforms baselines despite domain gaps such as differences in agent color and morphology. We further analyze XIPER on a sim-to-real transfer dataset, demonstrating that it produces meaningful reward signals for real-robot observations given only simulated expert videos. Code, pretrained models, datasets and video demonstrations can be found on our project webpage: https://sites.google.com/view/xiper

Instance Goal Navigation (IGN) requires an embodied agent to find a specific object instance among distractors from an under-specified natural-language description. Such ambiguity often cannot be resolved from perception and language alone, making interaction with an oracle a natural mechanism for disambiguation. Prior interactive methods allow oracle queries but treat lightweight clarification and route-level guidance alike, letting agents boost success rate through repeated high-information questions rather than by resolving the underlying ambiguity efficiently. We recast interactive IGN as a cost-sensitive uncertainty-reduction problem, where the agent should ask the question whose answer provides the largest reduction in navigation uncertainty relative to its penalty. To this end, we apply an information-gain analysis on existing navigation corpora to identify which cues reduce navigation uncertainty, yielding a compact set of question types and data-derived weights. However, existing interactive navigation benchmarks do not model the cost of different question types or evaluate how efficiently agents use interaction, making them unsuitable for studying cost-sensitive interaction. Based on this taxonomy, we construct a benchmark for diagnosing interaction behavior and efficiency, together with a Weighted Success Rate metric that penalizes each query by its derived cost. We further propose a zero-shot MLLM navigator that selectively queries at each decision step only when the expected uncertainty reduction justifies the interaction cost.

Edge AI nodes for search and rescue are increasingly expected to run computer vision locally, yet ultra-low-end hardware imposes hard constraints on memory, compute, and inter-device communication. This work addresses occlusion-robust object detection on devices with less than 1 MB SRAM by combining an MCUNet backbone, a YOLOv2 detection head, and Lite quantisation. Two collaborative inference strategies are evaluated: feature-level fusion, concatenating intermediate feature maps, and decision-level fusion via Weighted Boxes Fusion (WBF). WBF outperforms feature-level fusion under all tested occlusion conditions, yielding gains of up to +0.2736 mAP in asymmetric scenarios. Extending fusion to three views improves accuracy further (up to +0.3827 mAP) at modest communication overhead (~1.3 KB per exchange). Hardware experiments progress from a host-assisted USB-relay baseline to a Wi-Fi peer-to-peer deployment on two Coral Dev Board Micro units, where WBF executes on-device with negligible communication energy relative to inference. In a 301.9 s autonomous session of 108 frames, fused output is produced on 61 frames versus 47 for a single board - a coverage gain of +29.8%. A decentralised federated learning feasibility note is included but not treated as a primary result, as performance remains limited under non-iid data. The results support decision-level fusion as a viable option for improving occlusion robustness in small-scale edge object detection, including host-free multi-board operation on ultra-low-end hardware.

Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, but real-world deployment requires them to continually acquire new vision-language capabilities, making Multimodal Continual Instruction Tuning (MCIT) essential. To reduce inter-task interference and promote collaboration, recent methods often employ sparse architectures like Mixture of LoRA Experts with image-text similarity routing. However, tasks with distinct response structures could share highly similar visual-linguistic semantics and thus be wrongly routed to the same expert; image-text similarity alone is insufficient for reliable task assignment. For example, an expert in a grounding task requiring coordinate prediction may be biased toward producing short textual answers after learning semantically similar VQA tasks. This format-blind task assignment integrates heterogeneous response types into shared parameters, inducing gradient interference and ineffective expert collaboration. To address this problem, we propose ProtoAda, a prototype-guided adaptive tuning framework. ProtoAda introduces format-aware task prototypes to align task assignment and routing with both task semantics and output structure, and further consolidates format-compatible updates in a geometry-aware manner to effectively reuse and progressively refine existing parameters. Extensive experiments on multiple benchmarks demonstrate that ProtoAda achieves superior performance, especially on tasks whose answer structures are easily corrupted by sequential tuning.

One-step text-to-image generators are attractive for deployment because they generate an image with a single forward pass, but preference finetuning them remains difficult: standard alignment methods often rely on policy likelihoods, denoising trajectories, differentiable reward gradients, or test-time optimization. We propose Drifting Preference Optimization (DrPO), an online preference-finetuning method for deterministic one-step generators. For each prompt, DrPO samples candidates from the current generator, ranks them with a target reward, and uses high- and low-scoring samples to synthesize a feature-space update direction. The update is a non-parametric dipole preference field plus a reference drift estimated from the frozen base generator, and is optimized through a detached feature-space regression target. The target reward is used only for ranking, so DrPO can train with large, black-box, or non-differentiable rewards while inference remains a single generator call. We evaluate DrPO on SD-Turbo and SDXL-Turbo with multiple target rewards and benchmarks, including HPSv3 and GenEval. DrPO improves alignment over reward-gradient-free one-step preference baselines and reduces HPSv3 training computation by $3.51\times$ under the matched effective-batch setting by removing reward-model backpropagation. Initial offline experiments suggest that sample-based gradient synthesis can also be used beyond online reward ranking.

Generating physically consistent 3D tabletop scenes is a fundamental yet underexplored problem for interactive and generalist robotic learning. The challenge stems from dense object hierarchies and irregular affordances. Here, an interactive scene denotes a physically valid, collision-free environment directly loadable into physics simulators. Existing methods, ranging from decoupled symbolic solvers to end-to-end regression models, often suffer from error propagation or overfitting to noisy supervision containing widespread physical violations. To address these limitations, we introduce PhyScene3D, a framework that reformulates generation as a Human-Mimetic Constructive Process. The proposed Cognitive Topological Reasoning Chain (CTRC) factorizes scene synthesis into a sequential, anchor-conditioned process. It employs a 3D AABB-based placement scheme that imposes a strong structural inductive bias. To address imperfect supervision and physical infeasibility, we introduce Physics-Aware Denoising Alignment (PADA). It integrates a differentiable Signed Distance Field (SDF) with Test-Time Optimization (TTO) to project generated scenes onto a physics-feasible manifold while preserving semantic intent. Experiments demonstrate that PhyScene3D outperforms state-of-the-art approaches in both semantic accuracy and physical validity, achieving a 40% reduction in scene-wise collision rate relative to the human-annotated training data.

Gaussian splatting has shown strong potential for 3D reconstruction and novel view synthesis. However, most existing methods require accurate camera parameters and per-scene optimization, while feed-forward methods with pixel-aligned Gaussian primitives often suffer from artifacts and non-uniform primitives. In this paper, we propose $\text{VG}^2$GT, a Voxel-Gaussian Splatting Visual Geometry-Grounded Transformer. $\text{VG}^2$GT leverages a frozen pretrained visual foundation model (VFM), incorporates a multi-scale differentiable voxel module to enhance geometric understanding, and directly splits and regresses Gaussian primitive parameters from voxel features. During training, depth maps are supervised through stochastic solid volume rendering, enabling geometrically accurate Gaussian scene reconstruction while keeping the visual foundation model fully frozen. This design enables $\text{VG}^2$GT to be seamlessly plugged into any patch-feature-based VFM, while substantially reducing the required training cost. $\text{VG}^2$GT outperforms current state-of-the-art methods on widely used DTU, Replica, TAT, and ScanNet datasets.

Clinical diagnosis often requires combining imaging with physiological measurements, yet deployed models typically operate on unimodal data. We present PaCX-MAE, a cross-modal distillation framework that injects physiological priors into chest X-ray (CXR) encoders while remaining strictly unimodal at inference. PaCX-MAE augments in-domain masked autoencoding with a dual contrastive-predictive objective, aligning CXR representations with paired ECG and laboratory embeddings. Extensive evaluation across nine benchmarks demonstrates consistent improvements over domain-specific MAE, particularly on physiology-dependent tasks (e.g., +2.7 AUROC on MedMod; +6.5 F1 on VinDr). The method proves highly label-efficient in the 1% regime and preserves anatomical fidelity, achieving parity with MAE on segmentation tasks. Zero-shot and attention analyses confirm that PaCX-MAE successfully learns to attend to physiological indicators, such as the cardiac silhouette, absent in standard visual pretraining.

Visual inspection remains the dominant quality-control practice in woven and tufted carpet production, yet it is slow, subjective, and inconsistent at the line speeds and widths of modern looms. We present a design proposal for an in-line machine-vision system whose primary purpose is twofold: to inspect the carpet web in real time and, equally importantly, to systematically collect and label images of defect patterns so that increasingly capable quality-control models can be trained over the life of the installation. The proposal is grounded in a concrete industrial setting: a Six Sigma (DMAIC) project at a woven-carpet production facility that anticipated a production bottleneck following the installation of additional weaving machines, with a substantial baseline defect rate and significant financial exposure associated with quality failures. We describe an imaging subsystem based on synchronized line-scan cameras with combined bright-field and grazing illumination, derive the resolution and throughput requirements needed to resolve fine structural defects across a multi-metre web, and define a carpet-specific defect taxonomy. We then lay out a staged modelling strategy that begins with unsupervised anomaly detection trained on defect-free material, following the paradigm exemplified by the carpet category of the MVTec Anomaly Detection benchmark, and matures through a human-in-the-loop annotation flywheel into supervised detection and segmentation models. Finally, we connect detection performance to the DMAIC objectives, showing how reductions in escaped defects translate into improved process quality and process sigma levels. The contribution is an end-to-end, deployable blueprint that treats data collection as a first-class engineering objective rather than an afterthought.

For low-altitude Unmanned Aerial Vehicle (UAV) autonomy, 3D spatial understanding is not merely a perception objective, but the safety interface between human instructions and physical flight. In human-scale urban airspace below 20 meters, thin geometry, occlusions, vegetation, and urban clutter define whether an aerial agent can safely enter the space ahead. However, existing UAV datasets mainly provide 2D annotations or 3D boxes, while driving-oriented occupancy benchmarks assume stable ground-level sensor rigs. Both miss the defining regime of low-altitude flight: a front-facing monocular camera observing occupied and free space from a moving aerial body with frame-wise changing 6-DoF pose and camera extrinsics. To bridge this gap, we introduce SkyShield, to the best of our knowledge the first front-view monocular semantic occupancy benchmark for urban UAV flight below 20 meters. Built on CARLA, SkyShield contains 36K front-view UAV samples across diverse urban scenes and weather conditions, pairing each image with frame-wise 6-DoF UAV pose, frame-wise dynamic camera geometry, UAV states, and front-frustum semantic occupancy labels. We further propose KAR-mIoU, a UAV-centric and dynamics-aware metric that re-weights voxel-level evaluation by kinematic reachability and time-to-collision, revealing safety-critical risks hidden by conventional mIoU. To tackle this challenging new setting, we provide SkyOcc, a geometry-first monocular baseline that integrates frame-wise UAV attitude into projection, fuses temporal occupancy features, and applies safety-prior optimization to preserve sparse collision-critical structures. Together, SkyShield, KAR-mIoU, and SkyOcc establish occupancy as a safety interface for low-altitude aerial autonomy. Code and dataset will be released publicly.

Human Activity Recognition (HAR) from ambient sensors enables smart-home applications such as health monitoring and assisted living. In realistic deployments, however, sensor events arrive as a continuous stream and activity boundaries are unknown. Sliding-window inference therefore produces many windows that straddle transitions and contain mixed activities, creating boundary contamination that violates the pre-segmented instance assumption used by most benchmarks and models. Moreover, many pipelines under-use spatial context by treating sensor IDs as independent tokens. We present LastAct, a trajectory-centric framework for streaming smart-home HAR that targets the most recent activity under mixed windows while explicitly modeling spatial structure. LastAct projects sensor events onto the home floorplan to form a layout-aligned trajectory image sequence that preserves spatial continuity. A lightweight gate identifies contaminated windows, and a boundary localizer estimates the last transition to enable boundary-guided masking that emphasizes post-boundary evidence and suppresses stale context. For efficiency, we reuse a precomputed layout-aligned template cache to avoid repeated rendering. Empirically, across four public smart-home datasets under near-realistic mixed-activity protocols, LastAct achieves competitive or superior performance on pure windows and yields substantial Macro-F1 gains on cross/mixed windows, demonstrating improved robustness under near-realistic sliding-window regimes.

Real-world image restoration (IR) is bottlenecked by the scarcity of high-quality paired training data. Synthetic datasets are abundant but often fail to model real-world degradations, while real-world paired datasets are expensive and difficult to capture. As a result, IR models trained on these datasets show limited generalization in real-world scenarios. In this work, we propose Generative Ground Truth (GGT) by using generative multimodal foundation models (MFMs) to produce high-quality (HQ) targets from real-world low-quality (LQ) images. We first conduct a systematic evaluation of nine state-of-the-art MFMs, including Nano-Banana-2 and GPT-Image-2, on images of various scenes and degradation types. The results demonstrate that Nano-Banana-2 with VLM-based adaptive prompting shows the highest capability to synthesize perceptually realistic and content-faithful HQ targets, which can serve as the GGT for the LQ input. We then employ Nano-Banana-2 to build a GGT synthesis pipeline, which involves multi-stage quality control to ensure data reliability, and construct GGT-100K, an LQ-HQ paired dataset comprising 103,707 training pairs and covering diverse scenes and complex real-world degradations. A test set of 500 image pairs is also established. Extensive experiments show that GGT-100K consistently improves the real-world generalization of a wide range of IR models, with particularly strong benefits for finetuning generative models for IR tasks. Our results suggest that MFMs can serve as practical tools for restoration-oriented data generation, and GGT-100K is a useful resource to expand the generalization boundaries of real-world IR models.

Geometry-aware generative models and novel view synthesis approaches have shown strong potential in visual fidelity and consistency. In parallel, equivariant representation learning has emerged as a powerful framework for constructing latent spaces where analytically known group transformations could act directly, capturing geometric structure in data and enhancing both interpretability and generalization in novel view synthesis. However, we identify that existing approaches often suffer from latent misalignment, a discrepancy between the intended group action and the actually required transformations in the latent space. Consequently, the learned latents often fail to consistently preserve the equivariant relations imposed by the underlying group symmetry. To address this, we propose Residual Latent Flow, a flow-based framework that corrects the misaligned latents, thereby improving compliance with the underlying equivariance relation. Our comprehensive experiments show that our method significantly reduces latent misalignment and improves novel view synthesis quality, under rotation groups SO(n).

Self-supervised pre-training paradigm has gained increasing prominence for learning transferable representations in medical imaging, yet existing methods for ultrasound (US) images operate at the image or frame level, overlooking the anatomical context for clinical-aligned representation learning. In this work, we propose an anatomy-anchored ultrasound self-supervision framework ANAUS that shifts representation learning from generic visual regions to clinically meaningful anatomical structures. Utilizing a learnable latent prompt engine alongside a one-time domain adaptation on existing public image-mask pairs, we empower the LP-SAM module to achieve annotation-free anatomy delineation at scale. Building upon this anatomical grounding, we propose a dual-policy self-supervised learning paradigm consisting of inter-view semantics-aware anatomy-separating alignment and contextual core-region prediction to enhance representation learning. Specifically, the former enforces feature invariance within identical anatomical regions while promoting discriminability across distinct structures; the latter compels the model to reconstruct corrupted regions, thereby capturing fine-grained structural details. Extensive evaluations on six public datasets demonstrate that ANAUS consistently outstrips current state-of-the-art methods while maintaining the computational efficiency essential for clinical deployment. Code is available at https://github.com/zhcz328/ANAUS.

Multimodal large language models (MLLMs) frequently suffer from object hallucinations, yet the visual perceptual mechanism underlying this failure remains poorly understood. In this work, we reveal that hallucinations are strongly associated with a human-like attention distraction phenomenon, where humans under divided focus experience degraded visual clarity and produce inaccurate descriptions, while in models the same mechanism manifests as spatial inconsistency in multi-head attention and temporal fading of attention to image tokens during decoding. We further provide theoretical insights that attention dispersion increases model complexity and degrades classification generalization. Motivated by these findings, we propose an Attention-Focused Approach for Improved Image Perception (AFIP), which corrects attention distraction via cross-head attention enrichment and reinforces visual grounding through dynamic historical attention enhancement. Extensive experiments on multiple benchmarks and models validate the effectiveness of AFIP without additional training.

Monocular video human mesh recovery is essential for digital humans, avatar animation, and embodied simulation, where both temporal stability and expressive whole-body motion are required. Existing video HMR methods produce coherent body motion but often overlook detailed hand articulation, while image-based whole-body methods recover SMPL-X meshes independently per frame, often leading to jittery and inaccurate hand motion. We present a temporally coherent whole-body HMR framework for challenging in-the-wild monocular videos. Our model unifies body context and part-specific hand observations through residual body-hand fusion, enabling stable body motion and detailed hand recovery within a single temporal architecture. We further introduce close-up-aware augmentation to improve robustness under upper-body framing. Experiments on whole-body and body-only benchmarks demonstrate improved hand reconstruction and competitive body accuracy. Our method also produces temporally stable and 2D-consistent SMPL-X motion in challenging real-world videos.

Land Use Scene Classification (LUSC) from remote sensing imagery plays a critical role in environmental monitoring, urban planning, and sustainable resource management. In recent years, deep learning methods have significantly advanced the state of the art, with Convolutional Neural Networks (CNNs) dominating the field because of their strong ability to capture local spatial features. However, the emergence of Vision Transformers (ViTs) has introduced a new paradigm that models long-range dependencies through self-attention mechanisms, potentially enabling improved global context understanding. This paper presents a comparative assessment of Vision Transformers and CNN-based architecture for remote sensing land use scene classification. Representative CNN models, such as AlexNet, is evaluated alongside the Vision Transformer (ViT) using benchmark remote sensing datasets, including the UC Merced Land Use and EuroSAT Land Use datasets. The study examines classification accuracy, precision, recall, F1-score, and computational complexity to provide a comprehensive performance comparison. Experimental results demonstrate that CNNs perform robustly on datasets with limited training samples and strong local texture characteristics, whereas Vision Transformers exhibit superior performance in capturing global spatial relationships in complex scenes when sufficient training data are available. However, ViTs typically require greater computational resources and larger training datasets to achieve optimal performance. The findings of this study provide insights into the strengths and limitations of both architectures and offer guidance for selecting appropriate models for remote sensing land use scene classification applications.

Image-to-video models often generate videos that remain overly static, compared to text-to-video models. While prior approaches mitigate this issue by weakening or modifying the image-conditioning signal, they often require additional training or sacrifice fidelity to the reference image. In this work, we identify reference-frame dominance as a key mechanism behind motion suppression. We observe that non-reference frames in I2V models allocate excessive self-attention to reference-frame key tokens, causing reference information to be over-propagated across time and suppressing inter-frame dynamics. Based on this finding, we propose DyMoS (Dynamic Motion Slider), a training-free and model-agnostic method that rebalances the attention pathway from generated frames to the reference frame during initial denoising steps. DyMoS leaves both the input image and model weights unchanged and introduces a single scalar parameter for continuous control over motion strength. Experiments across multiple state-of-the-art I2V backbones demonstrate that DyMoS consistently improves motion dynamics while maintaining visual quality and fidelity to the reference image.

Pixel-space diffusion models bypass the reconstruction bottleneck of Variational Autoencoders (VAEs) but face a fundamental "granularity dilemma": capturing global semantics favors large patch scales, while generating high-fidelity details demands fine-grained inputs. To address this issue, we propose HyperDiT, a unified framework establishing Hyper-Connected Cross-Scale Interactions to bridge the semantic and pixel manifold. Diverging from injecting semantics by AdaLN, HyperDiT utilizes Cross-Attention mechanisms, enabling fine-grained tokens to query multi-level semantic anchors globally. To resolve the spatial mismatch during multi-scale interactions, we introduce Scale-Aware Rotary Position Embedding (SA-RoPE) to ensure precise geometric alignment among tokens of varying patch sizes. Furthermore, we incorporate Registers to learn the dense semantics from a pretrained Visual Foundation Model (VFM), effectively reducing generation hallucination and artifacts. Extensive experiments demonstrate that HyperDiT achieves state-of-the-art (SoTA) FID of $\mathbf{1.56}$ on ImageNet $256\times256$ directly within the pixel space. By combining the fine-grained stream with semantic guidance, HyperDiT offers a superior paradigm for high-fidelity pixel generation.

In recent years, the rapid evolution of generative AI has fundamentally reshaped the paradigm of image forgery, breaking the traditional boundaries between document editing, natural image manipulation, DeepFake generation, and full-image AIGC synthesis. Despite this shift toward unified forgery generation, existing research in Fake Image Detection and Localization (FIDL) remains fragmented. This creates a mismatch between increasingly unified forgery generation mechanisms and the domain-specific detection paradigm. Bridging this mismatch poses two key challenges for FIDL: understanding cross-domain artifacts transfer and interference, and building a high-capacity unified foundation model for joint detection and localization. To address these challenges, we propose DeFakerOne, a data-centric, unified FIDL foundation model integrating InternVL2 and SAM2. DeFakerOne enables simultaneous image-level detection and pixel-level forgery localization across diverse scenarios. Extensive experiments demonstrate that DeFakerOne achieves state-of-the-art performance, outperforming baselines on 39 forgery detection benchmarks and 9 localization benchmarks. Furthermore, the model exhibits superior robustness against real-world perturbations and state-of-the-art generators such as GPT-Image-2. Finally, we provide a systematic analysis of data scaling laws, cross-domain artifacts transfer-interference patterns, the necessity of fine-grained supervision, and the original resolution artifacts preservation, highlighting the design principles for scalable, robust, and unified FIDL.

Achieving robust perception-reasoning synergy is a central goal for advanced Vision-Language Models (VLMs). Recent advancements have pursued this goal via architectural designs or agentic workflows. However, these approaches are often limited by static textual reasoning or complicated by the significant compute and engineering burden of external agentic complexity. Worse, this heavy investment does not yield proportional gains, often witnessing a "seesaw effect" on perception and reasoning. This motivates a fundamental rethinking of the true bottleneck. In this paper, we argue that the root cause of this trade-off is an ambiguity in modality credit assignment: when a VLM fails, is it due to flawed perception ("bad seeing") or flawed logic ("bad thinking")? To resolve this, we introduce a reinforcement learning framework that improves perception-reasoning synergy by reliably rewarding the perception fidelity. We explicitly decompose the generation process into interleaved perception and reasoning steps. This decoupling enables targeted supervision on perception. Crucially, we introduce Perception Verification (PV), leveraging a "blindfolded reasoning" proxy to reward perceptual fidelity independently of reasoning outcomes. Furthermore, to scale training across free-form VL tasks, we propose Structured Verbal Verification, which replaces high-variance LLM judging with structured algorithmic execution. These techniques are integrated into a Modality-Aware Credit Assignment (MoCA) mechanism, which routes rewards to the specific source of error -- either bad seeing or bad thinking -- enabling a single VLM to achieve simultaneous performance gains across a wide task spectrum.

Few-shot classification (FSC) is widely used for learning from limited labeled data, yet most evaluations implicitly assume that target concepts are independent of contextual cues. In real-world settings, however, examples often appear within rich contexts, allowing models to exploit spurious correlations between foreground content and background signals. While such effects have been studied in few-shot image classification, their role in few-shot audio classification remains largely unexplored, and existing audio benchmarks offer limited control over contextual structure. We introduce SpurAudio, a benchmark that leverages the natural separability of foreground events and background environments in audio to enable controlled, multi-level evaluation of contextual shifts across support and query sets. Using this benchmark, we show that many state-of-the-art few-shot methods suffer severe performance degradation when background correlations are disrupted, despite achieving similar accuracy under standard evaluation protocols. Crucially, this vulnerability persists even in large pretrained audio foundation models, ruling out limited backbone capacity as an explanation. Moreover, methods that appear comparable under conventional benchmarks can exhibit markedly different sensitivity to spurious correlations, revealing systematic algorithmic strengths and vulnerabilities tied to how feature representations interact with classifier heads at inference time. These findings provide new insight into the behavior of few-shot methods in audio and highlight the need for benchmarks that explicitly probe context dependence when evaluating FSC models.

Transformer-based models are becoming a central paradigm in autonomous driving because they can capture long-range spatial dependencies, multi-agent interactions, and multimodal context across perception, prediction, and planning. At the same time, their deployment in real vehicles remains difficult because high-capacity attention-based architectures impose substantial latency, memory, and energy overhead. This survey reviews representative Transformer-based autonomous driving models and organizes them by task role, sensing configuration, and architectural design. More importantly, it examines these models from a deployment-oriented perspective and analyzes how efficiency constraints reshape model design choices in practice. We further review compression and acceleration strategies relevant to Transformer-based driving systems, including quantization, pruning, knowledge distillation, low-rank approximation, and efficient attention, and discuss their benefits, limitations, and task-dependent applicability. Rather than treating compression as an isolated post-processing step, we highlight it as a system-level design consideration that directly affects deployability, robustness, and safety. Finally, we identify open challenges and future research directions toward standardized, safety-aware, and hardware-conscious evaluation of efficient autonomous driving systems.

Tokenization in video models, typically through patchification, generates an excessive and redundant number of tokens. This severely limits video efficiency and scalability. While recent trajectory-based tokenizers offer a promising solution by decoupling video duration from token count, they rely on complex external segmentation and tracking pipelines that are slow and task-agnostic. We propose TrajTok, an end-to-end video tokenizer module that is fully integrated and co-trained with video models for a downstream objective, dynamically adapting its token granularity to semantic complexity, independent of video duration. TrajTok contains a unified segmenter that performs implicit clustering over pixels in both space and time to directly produce object trajectories in a single forward pass. By prioritizing downstream adaptability over pixel-perfect segmentation fidelity, TrajTok is lightweight and efficient, yet empirically improves video understanding performance. With TrajTok, we implement a video CLIP model trained from scratch (TrajViT2). It achieves the best accuracy at scale across both classification and retrieval benchmarks, while maintaining efficiency comparable to the best token-merging methods. TrajTok also proves to be a versatile component beyond its role as a tokenizer. We show that it can be seamlessly integrated as either a probing head for pretrained visual features (TrajAdapter) or an alignment connector in vision-language models (TrajVLM) with especially strong performance in long-video reasoning.

Although person re-identification has made impressive progress, occlusion caused by obstacles remains an unsettled issue in real applications. The difficulty lies in the mismatch between incomplete occluded samples and holistic identity representations. Severe occlusion removes discriminative body cues and introduces interference from background clutter and occluders, making global metric learning unreliable. Existing methods mainly rely on extra pre-trained models to estimate visible parts for alignment or construct occluded samples via data augmentation, but still lack a unified framework that learns robust visibility-consistent matching under realistic occlusion patterns. In this paper, we propose DPM++, a Dynamic Masked Metric Learning framework for occluded person re-identification. DPM++ learns an input-adaptive masked metric that dynamically selects reliable identity subspaces for each occluded instance, enabling matching to emphasize visibility-consistent evidence while suppressing unreliable components. Built upon the classifier-prototype space, DPM++ introduces a CLIP-based two-stage supervision scheme, where ID-level semantic priors are learned from the text branch and transferred into the classifier-prototype space for dynamic masked matching. To strengthen the masked metric, we introduce a saliency-guided patch transfer strategy to synthesize controllable and photo-realistic occluded samples during training. Exploiting real scene priors, this strategy exposes the model to realistic partial observations and provides richer supervision than random erasing. In addition, occlusion-aware sample pairing and mask-guided optimization improve the stability and effectiveness of the framework. Experiments on occluded and holistic person re-identification benchmarks show that DPM++ consistently outperforms previous state-of-the-art methods in both holistic and occlusion scenarios.

Millimetre-wave (mmWave) radar offers a more privacy-preserving alternative to RGB-based human pose estimation. However, existing methods typically rely on pre-extracted intermediate representations such as sparse point clouds or spectrogram images, where the rich spatiotemporal information naturally present in radar video streams is discarded for model learning, while such signal processing adds system complexity. In addition, existing solutions are mainly conducted in an end-to-end supervised manner without leveraging unlabelled raw video streams to learn generalized representations. In this study, we present MAEPose, a masked autoencoding-based human pose estimation approach that operates directly on mmWave spectrogram videos. MAEPose learns spatiotemporal motion-aware generalized representations from unlabelled radar video, and leverages its heatmap decoder for multi-frame pose estimation predictions. We evaluate it across three datasets based on leave-one-person-out cross-validation with rigorous statistical testing. MAEPose consistently outperforms state-of-the-art baselines by up to 22.1% in MPJPE p<0.05, and maintains robust accuracy under zero-shot bystander interference with only a 6.5% error increase. Ablation studies confirm that both the pre-training and the heatmap decoder contribute substantially, while modality analysis indicates that leveraging Range-Doppler video as input achieves better pose estimation performance than Range-Azimuth or their fusion, with lower computational cost.

Effective human behavior modeling requires a representation of the human body movement that capitalizes on its compositionality. We propose a hierarchical representation consisting of Action Atoms that capture the atomic joint movements and Action Motifs that are formed by their temporal compositions and encode similar body movements found across different overall human actions. We derive A4Mer, a nested latent Transformer to learn this hierarchical representation from human pose data in a fully self-supervised manner. A4Mer splits a 3D pose sequence into variable-length segments and represents each segment as a single latent token (Action Atoms). Through bottom-up representation learning, temporal patterns composed of these Action Atoms, which capture meaningful temporal spans of reusable, semantic segments of body movements, naturally emerge (Action Motifs). A4Mer achieves this with a unified pretext task of masked token prediction in their respective latent spaces. We also introduce Action Motif Dataset (AMD), a large-scale dataset of multi-view human behavior videos with full SMPL annotations. We introduce a novel use of cameras by mounting them on the feet to achieve their frame-wise annotations despite frequent and heavy body occlusions. Experimental results demonstrate the effectiveness of A4Mer for extracting meaningful Action Motifs, which significantly benefit human behavior modeling tasks including action recognition, motion prediction, and motion interpolation.

Traditional neural network models for intent inference rely heavily on observable states and struggle to generalize across diverse tasks and dynamic environments. Recent advances in Vision Language Models (VLMs) and Vision Language Action (VLA) models introduce common-sense reasoning through large-scale multimodal pretraining, enabling zero-shot performance across tasks. However, these models still lack explicit mechanisms to represent and update belief, limiting their ability to reason like humans or capture the evolving human intent over long-horizon. To address this, we propose a belief-aware VLM framework that integrates retrieval-based memory and reinforcement learning. Instead of learning an explicit belief model, we approximate belief using a vector-based memory that retrieves relevant multimodal context, which is incorporated into the VLM for reasoning. We further refine decision-making using a reinforcement learning policy over the VLM latent space. We evaluate our approach on publicly available VQA datasets such as HD-EPIC and demonstrate consistent improvements over zero-shot baselines, highlighting the importance of belief-aware reasoning.

Vision-centric retrieval for VQA requires retrieving images to supply missing visual cues and integrating them into the reasoning process. However, selecting the right images and integrating them effectively into the model's reasoning remains challenging.To address this challenge, we propose R3G, a modular Reasoning-Retrieval-Reranking framework.It first produces a brief reasoning plan that specifies the required visual cues, then adopts a two-stage strategy, with coarse retrieval followed by fine-grained reranking, to select evidence images.On MRAG-Bench, R3G improves accuracy across six MLLM backbones and nine sub-scenarios, achieving state-of-the-art overall performance. Ablations show that sufficiency-aware reranking and reasoning steps are complementary, helping the model both choose the right images and use them well. We release code and data at https://github.com/czh24/R3G.

Modern Text-to-Image (T2I) diffusion models have achieved remarkable semantic alignment, yet they often suffer from a significant lack of variety, converging on a narrow set of visual solutions for any given prompt. This typicality bias presents a challenge for creative applications that require a wide range of generative outcomes. We identify a fundamental trade-off in current approaches to diversity: modifying model inputs requires costly optimization to incorporate feedback from the generative path. In contrast, acting on spatially-committed intermediate latents tends to disrupt the forming visual structure, leading to artifacts. In this work, we propose to apply repulsion in the Contextual Space as a novel framework for achieving rich diversity in Diffusion Transformers. By intervening in the multimodal attention channels, we apply on-the-fly repulsion during the transformer's forward pass, injecting the intervention between blocks where text conditioning is enriched with emergent image structure. This allows for redirecting the guidance trajectory after it is structurally informed but before the composition is fixed. Our results demonstrate that repulsion in the Contextual Space produces significantly richer diversity without sacrificing visual fidelity or semantic adherence. Furthermore, our method is uniquely efficient, imposing a small computational overhead while remaining effective even in modern "Turbo" and distilled models where traditional trajectory-based interventions typically fail.

Large Vision-Language Models (LVLMs) often produce plausible but unreliable outputs, making robust uncertainty estimation essential. Recent work on semantic uncertainty estimates relies on external models to cluster multiple sampled responses and measure their semantic consistency. However, these clustering methods are often fragile, highly sensitive to minor phrasing variations, and can incorrectly group or separate semantically similar answers, leading to unreliable uncertainty estimates. We propose Semantic Gaussian Process Uncertainty (SGPU), a Bayesian framework that quantifies semantic uncertainty by analyzing the geometric structure of answer embeddings, avoiding brittle clustering. SGPU maps generated answers into a dense semantic space, computes the Gram matrix of their embeddings, and summarizes their semantic configuration via the eigenspectrum. This spectral representation is then fed into a Gaussian Process Classifier that learns to map patterns of semantic consistency to predictive uncertainty, and that can be applied in both black-box and white-box settings. Across six LLMs and LVLMs on eight datasets spanning VQA, image classification, and textual QA, SGPU consistently achieves state-of-the-art calibration (ECE) and discriminative (AUROC, AUARC) performance. We further show that SGPU transfers across models and modalities, indicating that its spectral representation captures general patterns of semantic uncertainty.

Video Corpus Moment Retrieval (VCMR) aims to retrieve both the correct video and its temporal segment corresponding to a natural-language query, a task that is especially challenging for multi-verb queries where temporal action ordering is critical. Existing approaches often rely solely on text or static images and struggle to capture implicit motion dynamics, leading to retrieval errors and temporal misalignment. We propose GenSpan, a generation-calibrated VCMR framework that constructs short auxiliary videos from LLM-selected subtitle cues and decomposed sub-events, using these as temporal priors rather than direct retrieval targets. A token selector filters candidate-video features aligned with generated motion, and a bidirectional state-space model efficiently predicts video-moment tuples. Experiments on TVR and ActivityNet-Captions demonstrate that GenSpan improves corpus-level retrieval and moment localization, particularly for complex multi-action queries, while reducing computational cost compared to state-of-the-art multimodal baselines.

Spatial Transcriptomics (ST) profiles thousands of gene expression values at discrete spots with precise coordinates on tissue sections, preserving spatial context essential for clinical and pathological studies. With rising sequencing throughput and advancing platforms, the expanding data volumes motivate large-scale ST pretraining. However, the fundamental unit for pretraining, i.e., what constitutes a single training sample, remains ill-posed. Existing choices fall into two camps: (1) treating each spot as an independent sample, which discards spatial dependencies and collapses ST into single-cell transcriptomics; and (2) treating an entire slide as a single sample, which produces prohibitively large inputs and drastically fewer training examples, undermining effective pretraining. To address this gap, we propose treating spatial transcriptomics as croppable images. Specifically, we define a multi-channel image representation with fixed spatial size by cropping patches from raw slides, thereby preserving spatial context while substantially increasing the number of training samples. Along the channel dimension, we define gene subset selection rules to control input dimensionality and improve pretraining stability. Extensive experiments show that the proposed image-like dataset construction for ST pretraining consistently improves downstream performance, outperforming conventional pretraining schemes. Ablation studies verify that both spatial patching and channel design are necessary, establishing a unified, practical paradigm for organizing ST data and enabling large-scale pretraining.

As generative AI advances, global governance frameworks increasingly mandate verifiable content provenance. However, existing watermarking techniques face a critical policy-to-technology disconnect: sampling-based methods require computationally prohibitive inversion, while fine-tuning approaches are tethered to specific model checkpoints, hindering standardized, cross-model oversight. To bridge this gap, we introduce DiffMark, a plug-and-play multi-bit watermarking framework. DiffMark embeds a persistent, learned perturbation into every denoising step of a frozen diffusion model, accumulating a recoverable signal in the final latent space. To enable efficient training through the frozen network, we utilize Latent Consistency Models (LCMs) as a differentiable training bridge. DiffMark achieves 64-bit extraction in a single 16.4 ms forward pass, which is a $45\times$ speed-up over inversion baselines. By enabling per-image key flexibility and cross-architecture transferability without retraining, DiffMark provides the practical, scalable technical tooling necessary to operationalize user accountability and enforce emerging AI governance mandates.

Generative image models produce striking visuals yet often misrepresent culture. Prior work has examined cultural bias mainly in text-to-image (T2I) systems, leaving image-to-image (I2I) editors underexplored. We bridge this gap with a unified evaluation across six countries, an 8-category/36-subcategory schema, and era-aware prompts, auditing both T2I generation and I2I editing under a standardized protocol that yields comparable diagnostics. Using open models with fixed settings, we derive cross-country, cross-era, and cross-category evaluations. Our framework combines standard automatic metrics, a culture-aware retrieval-augmented VQA, and expert human judgments collected from native reviewers. To enable reproducibility, we release the complete image corpus, prompts, and configurations. Our study reveals three findings: (1) under country-agnostic prompts, models default to Global-North, modern-leaning depictions that flatten cross-country distinctions; (2) iterative I2I editing erodes cultural fidelity even when conventional metrics remain flat or improve; and (3) I2I models apply superficial cues (palette shifts, generic props) rather than era-consistent, context-aware changes, often retaining source identity for Global-South targets. These results highlight that culture-sensitive edits remain unreliable in current systems. By releasing standardized data, prompts, and human evaluation protocols, we provide a reproducible, culture-centered benchmark for diagnosing and tracking cultural bias in generative image models. Project page: https://seochan99.github.io/ECB

Model stitching, connecting early layers of one model (source) to later layers of another (target) via a light stitch layer, has served as a probe of representational compatibility. Prior work finds that models trained on the same dataset remain stitchable (negligible accuracy drop) despite different initializations or objectives. We revisit stitching for Vision Foundation Models (VFMs) that vary in objectives, data, and modality mix (e.g., CLIP, DINOv2, SigLIP 2) and ask: Are heterogeneous VFMs stitchable? We introduce a systematic protocol spanning the stitch points, stitch layer families, training losses, and downstream tasks. Three findings emerge. (1) Stitch layer training matters: conventional approaches that match the intermediate features at the stitch point or optimize the task loss end-to-end struggle to retain accuracy, especially at shallow stitch points. (2) With a simple feature-matching loss at the target model's penultimate layer, heterogeneous VFMs become reliably stitchable across vision tasks. (3) For deep stitch points, the stitched model can surpass either constituent model at only a small inference overhead (for the stitch layer). Building on these findings, we further propose the VFM Stitch Tree (VST), which shares early layers across VFMs while retaining their later layers, yielding a controllable accuracy-latency trade-off for multimodal LLMs that often leverage multiple VFMs. Taken together, our study elevates stitching from a diagnostic probe to a practical recipe for integrating complementary VFM strengths and pinpointing where their representations align or diverge.

Motivated by discrete diffusion's success in language-vision modeling, we explore its potential for multi-view generation, a task dominated by continuous approaches. We introduce ViewMask-1-to-3, formulating multi-view generation as a discrete sequence modeling problem where each viewpoint is represented as visual tokens from MAGVIT-v2. Through discrete diffusion via masked token prediction, our approach enables progressive multi-view generation via iterative token unmasking, unifying language and vision in a shared token space. Importantly, simple random masking combined with self-attention naturally encourages cross-view consistency without specialized architectures or 3D geometric priors. Our method outperforms the baseline on the GSO and 3D-FUTURE benchmarks, ranking first on average across standard image metrics, and achieving a 10.6% higher IoU than continuous diffusion models on 3D-FUTURE. Furthermore, the proposed framework can be naturally extended to support text-to-image generation and multimodal understanding, highlighting its potential toward a more unified paradigm for multimodal understanding and generation.

The adaptation of large-scale vision-language models (VLMs) to downstream tasks with limited labeled data remains a significant challenge. While parameter-efficient prompt learning methods offer a promising path, they often suffer from catastrophic forgetting of pre-trained knowledge. Toward addressing this limitation, our work is grounded in the insight that governing the evolutionary path of prompts is essential for forgetting-free adaptation. To this end, we propose EvoPrompt, a novel framework designed to explicitly steer the prompt trajectory for knowledge-preserving fine-tuning. Specifically, our approach employs a Modality-Shared Prompt Projector (MPP) to generate hierarchical prompts from a unified embedding space. Critically, an evolutionary training strategy decouples low-rank updates into directional and magnitude components, preserving early-learned semantic directions while only adapting their magnitude, thus enabling prompts to evolve without discarding foundational knowledge. This process is further stabilized by Feature Geometric Regularization (FGR), which enforces feature decorrelation to prevent representation collapse. Extensive experiments demonstrate that EvoPrompt achieves state-of-the-art performance in few-shot learning while robustly preserving the original zero-shot capabilities of pre-trained VLMs.

The growing realism of generative models has blurred the boundary between real and synthetic content, posing significant challenges to reliable AI-generated image detection. Although large-scale pre-trained Vision Foundation Models have advanced detection capability, their generalization to images from unseen generation pipelines remains inadequate. In this paper, we identify, for the first time, a key failure mechanism, termed \emph{semantic fallback}, wherein forensic fine-tuning fails to fully reshape the representation space. Consequently, the resulting representations remain organized along high-level semantic structures rather than manipulation-specific forensic cues. Building on this insight, we propose a \textbf{Geometric Semantic Decoupling (GSD)} framework, which explicitly suppresses semantically dominant directions, thereby promoting invariant forensic representations. Specifically, GSD leverages a frozen CLIP encoder to estimate the dominant semantic subspace via Singular Value Decomposition (SVD). It then suppresses the semantic components through a geometry-constrained formulation with the suppression strength adaptively modulated across samples and layers. We further introduce a mini-batch SVD approximation strategy that amortizes subspace estimation, achieving over a $15 \times$ reduction in computational overhead while preserving effectiveness. Finally, considering practical scenarios spanning both large-scale and online evaluation, we develop three inference protocols, batch, per-sample, and reference-based inference, and demonstrate that they induce consistent semantic decoupling, yielding a stable forgery-oriented feature manifold.

Interactive world models continually generate video by responding to a user's actions, enabling open-ended generation capabilities. However, existing models typically lack a 3D representation of the environment, meaning 3D consistency must be implicitly learned from data, and spatial memory is restricted to limited temporal context windows. This results in an unrealistic user experience and presents significant obstacles to downstream tasks such as training agents. To address this, we present PERSIST, a new paradigm of world model which simulates the evolution of a latent 3D scene: environment, camera, and renderer. This allows us to synthesise new frames with persistent spatial memory and consistent geometry. Both quantitative metrics and a qualitative user study show substantial improvements in spatial memory, 3D consistency, and long-horizon stability over existing methods, enabling coherent, evolving 3D worlds. We further demonstrate novel capabilities, including synthesising diverse 3D environments from a single image, as well as enabling fine-grained, geometry-aware control over generated experiences by supporting environment editing and specification directly in 3D space. Project page: https://francelico.github.io/persist.github.io

This paper presents ShareVerse, a video generation framework enabling multi-agent shared world modeling, addressing the gap in existing works that lack support for unified shared world construction with multi-agent interaction. ShareVerse leverages the generation capability of large video models and integrates three key innovations: 1) A dataset for large-scale multi-agent interactive world modeling is built on the CARLA simulation platform, featuring diverse scenes, weather conditions, and interactive trajectories with paired multi-view videos (front/ rear/ left/ right views per agent) and camera data. 2) We propose a spatial concatenation strategy for four-view videos of independent agents to model a broader environment and to ensure internal multi-view geometric consistency. 3) We integrate cross-agent attention blocks into the pretrained video model, which enable interactive transmission of spatial-temporal information across agents, guaranteeing shared world consistency in overlapping regions and reasonable generation in non-overlapping regions. ShareVerse, which supports 49-frame large-scale video generation, accurately perceives the position of dynamic agents and achieves consistent shared world modeling.

Plug-and-Play diffusion prior (PnPDP) frameworks have emerged as a powerful paradigm for solving imaging inverse problems by treating pretrained generative models as modular priors. However, we identify a critical flaw in prevailing PnP solvers (e.g., based on HQS or Proximal Gradient): they function as memoryless operators, updating estimates solely based on instantaneous gradients. This lack of historical tracking inevitably leads to non-vanishing steady-state bias, where the reconstruction fails to strictly satisfy physical measurements under heavy corruption. To resolve this, we propose Dual-Coupled PnP Diffusion (DC-PnPDP), which restores the classical dual variable to provide integral feedback, progressively enforce agreement between the data-consistency and prior. However, this rigorous geometric coupling introduces a secondary challenge: the accumulated dual residuals exhibit spectrally colored, structured artifacts that violate the Additive White Gaussian Noise (AWGN) assumption of diffusion priors, causing severe hallucinations. To bridge this gap, we introduce Spectral Homogenization (SH), a frequency-domain adaptation mechanism that modulates these structured residuals into statistically compliant pseudo-AWGN inputs. This effectively aligns the solver's rigorous optimization trajectory with the denoiser's valid statistical manifold. Extensive experiments on CT and MRI reconstruction demonstrate that our approach resolves the bias-hallucination trade-off, achieving state-of-the-art fidelity with significantly accelerated convergence. The code is available at https://github.com/duchenhe/DC-PnPDP

Can unified vision-language models (VLMs) perform forward dynamics prediction (FDP), i.e., predicting the future state (in image form) given the previous observation and an action (in language form)? We find that VLMs struggle to generate physically plausible transitions between frames from instructions. Nevertheless, we identify a crucial asymmetry in multimodal grounding: fine-tuning a VLM to learn inverse dynamics prediction (IDP)-effectively captioning the action between frames-is significantly easier than learning FDP. In turn, IDP can be used to bootstrap FDP through two main strategies: 1) weakly supervised learning from synthetic data and 2) inference time verification. Firstly, IDP can annotate actions for unlabelled pairs of video frame observations to expand the training data scale for FDP. Secondly, IDP can assign rewards to multiple samples of FDP to score them, effectively guiding search at inference time. We evaluate the FDP resulting from both strategies through the task of action-centric image editing on Aurora-Bench with two families of VLMs. Despite remaining general-purpose, our best model achieves a performance competitive with state-of-the-art image editing models, improving on them by a margin between 7% and 13% according to GPT4o-as-judge, and achieving the best average human evaluation across all subsets of Aurora-Bench.

The smoothness of the transformer architecture has been extensively studied in the context of generalization, training stability, and adversarial robustness. However, its role in transfer learning remains poorly understood. In this paper, we analyze the ability of vision transformer components to adapt their outputs to changes in inputs, or, in other words, their \emph{plasticity}. Defined as an average rate of change, it captures the sensitivity to input perturbation; in particular, a high plasticity implies a low smoothness. Our theoretical analysis and extensive experiments -- over $1,000$ finetuning runs on large-scale vision transformers -- showcase that this perspective provides principled guidance in choosing the components to prioritize during adaptation. A key takeaway for practitioners is that the high plasticity of the attention modules and feedforward layers consistently leads to better finetuning performance. Our findings depart from the prevailing assumption that smoothness is desirable, offering a novel perspective on transformers' functional properties. The code is available at https://github.com/ambroiseodt/vit-plasticity.

Content moderation remains a critical yet challenging task for large-scale user-generated video platforms, especially in livestreaming environments where moderation must be timely, multimodal, and robust to evolving forms of unwanted content. We present a hybrid moderation framework deployed at production scale that combines supervised classification for known violations with reference-based similarity matching for novel or subtle cases. This hybrid design enables robust detection of both explicit violations and novel edge cases that evade traditional classifiers. Multimodal inputs (text, audio, visual) are processed through both pipelines, with a multimodal large language model (MLLM) distilling knowledge into each to boost accuracy while keeping inference lightweight. In production, the classification pipeline achieves 67% recall at 80% precision, and the similarity pipeline achieves 76% recall at 80% precision. Large-scale A/B tests show a 6-8% reduction in user views of unwanted livestreams}. These results demonstrate a scalable and adaptable approach to multimodal content governance, capable of addressing both explicit violations and emerging adversarial behaviors.

Multi-layer perceptrons (MLPs) are a standard tool for learning and function approximation, but they inherently produce globally smooth outputs. Consequently, they struggle to represent functions that are continuous yet intentionally non-differentiable (i.e., functions with prescribed $C^0$ sharp features) without ad hoc post-processing. We present SharpNet, a modified MLP architecture that encodes user-specified sharp features by augmenting the network with an auxiliary feature function defined as the solution to Poisson's equation with jump Neumann boundary conditions. This feature function is evaluated via an efficient local integral and is fully differentiable with respect to the feature locations, allowing us to jointly optimize both the feature locations and the MLP parameters to recover the target function or geometry. This construction provides precise control over where non-differentiability occurs, enforcing the desired $C^0$ behavior at feature locations while preserving smoothness elsewhere. We validate SharpNet on 2D problems and 3D CAD reconstruction, and compare it with several state-of-the-art baselines. In both settings, SharpNet accurately recovers sharp edges and corners while remaining smooth away from them, whereas existing methods tend to blur gradient discontinuities. Qualitative and quantitative results demonstrate the effectiveness of our approach. Our project page, code and models are publicly available at https://sharpnettech.github.io.

Multi-object tracking aims to maintain object identities over time by associating detections across video frames. Two dominant paradigms exist in literature: tracking-by-detection methods, which are computationally efficient but rely on handcrafted association heuristics, and end-to-end approaches, which learn association from data at the cost of higher computational complexity. We propose Track-Detection Link Prediction (TDLP), a tracking-by-detection method that performs per-frame association via link prediction between tracks and detections, i.e., by predicting the correct continuation of each track at every frame. TDLP is architecturally designed primarily for geometric features such as bounding boxes, while optionally incorporating additional cues, including pose and appearance. Unlike heuristic-based methods, TDLP learns association directly from data without handcrafted rules, while remaining modular and computationally efficient compared to end-to-end trackers. Extensive experiments on multiple benchmarks demonstrate that TDLP consistently surpasses state-of-the-art performance across both tracking-by-detection and end-to-end methods. Finally, we provide a detailed analysis comparing link prediction with metric learning-based association and show that link prediction is more effective, particularly when handling heterogeneous features such as detection bounding boxes. Our code is available at \href{https://github.com/Robotmurlock/TDLP}{https://github.com/Robotmurlock/TDLP}.

Text-to-Audio-Video (T2AV) generation aims to synthesize temporally coherent video and semantically synchronized audio from natural language, yet its evaluation remains fragmented, often relying on unimodal metrics or narrowly scoped benchmarks that fail to capture cross-modal alignment, instruction following, and perceptual realism under complex prompts. To address this limitation, we present T2AV-Compass, a unified benchmark for comprehensive evaluation of T2AV systems, consisting of 500 diverse and complex prompts constructed via a taxonomy-driven pipeline to ensure semantic richness and physical plausibility. Besides, T2AV-Compass introduces a dual-level evaluation framework that integrates objective signal-level metrics for video quality, audio quality, and cross-modal alignment with a subjective MLLM-as-a-Judge protocol for instruction following and realism assessment. Extensive evaluation of 11 representative T2AVsystems reveals that even the strongest models fall substantially short of human-level realism and cross-modal consistency, with persistent failures in audio realism, fine-grained synchronization, instruction following, etc. These results indicate significant improvement room for future models and highlight the value of T2AV-Compass as a challenging and diagnostic testbed for advancing text-to-audio-video generation.

Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving. However, there still lacks a driving-targeted dense geometry perception model that can adapt to different scenarios and camera configurations. To bridge this gap, we propose a Driving Visual Geometry Transformer (DVGT), which reconstructs a global dense 3D point map from a sequence of unposed multi-view visual inputs. We first extract visual features for each image using a DINO backbone, and employ alternating intra-view local attention, cross-view spatial attention, and cross-frame temporal attention to infer geometric relations across images. We then use multiple heads to decode a global point map in the ego coordinate of the first frame and the ego poses for each frame. Unlike conventional methods that rely on precise camera parameters, DVGT is free of explicit 3D geometric priors, enabling flexible processing of arbitrary camera configurations. DVGT directly predicts metric-scaled geometry from image sequences, eliminating the need for post-alignment with external sensors. Trained on a large mixture of driving datasets including nuScenes, OpenScene, Waymo, KITTI, and DDAD, DVGT significantly outperforms existing models on various scenarios. Code is available at https://github.com/wzzheng/DVGT.

Vision-Language Models (VLMs) are increasingly deployed as the perception and reasoning backbone of autonomous agents acting in the wild, with autonomous driving (AD) being one of the most safety-critical instances. Reliable temporal understanding is essential for such agents to anticipate events, attribute causes, and act safely in dynamic environments, yet this remains a significant challenge even for state-of-the-art (SoTA) VLMs. Prior video benchmarks have emphasized other content (sports, cooking, etc.), yet no existing benchmark focuses exclusively on temporal understanding for both short- and long-form AD footage. To fill this gap, we present the Temporal Understanding in Autonomous Driving (TAD) benchmark, comprising nearly 6000 question-answer (QA) pairs across 7 tasks, and evaluate 9 closed- and open-source generalist as well as AD-specialist models. Current SoTA models perform substantially below human accuracy on TAD. To improve the temporal reasoning of VLM-based driving agents, we propose two novel training-free solutions: Scene-CoT, which uses Chain-of-Thought (CoT) reasoning, and TCogMap, which incorporates an ego-centric temporal cognitive map produced by a trajectory-analysis module that operates as an agentic tool around the VLM. Integrated with existing VLMs, our methods improve average accuracy on TAD by up to $17.72\%$ and by up to $10.35\%$ on STSBench. By introducing TAD, benchmarking SoTA models, and proposing effective enhancements, this work aims to catalyze further progress on temporal understanding for agentic AD systems operating in the wild. The benchmark and evaluation code are available at ${\href{https://huggingface.co/datasets/vbdai/TAD}{\text{Hugging Face}}}$ and ${\href{https://github.com/vbdi/tad_bench}{\text{GitHub}}}$, respectively.

Pansharpening aims to fuse a high-resolution panchromatic image with a low-resolution multispectral image. Existing deep learning methods, including recent adaptive convolutions, struggle with regional heterogeneity in remote sensing images and often incur prohibitive computational costs. To address these challenges, we propose Dual Mask-Adaptive Convolution (DMAConv), a novel operator that dynamically allocates computational resources based on feature characteristics. DMAConv first employs a lightweight module to generate soft and hard masks. The hard mask separates features into a compact branch for processing redundant information globally and a focused branch that models complex, heterogeneous regions with greater computational investment. The soft mask then preliminarily modulates the input features for both branches. This dual-branch, mask-adaptive design significantly enhances feature representation while minimizing computational overhead. Extensive experiments demonstrate that our method achieves SOTA on a broad array of quantitative benchmarks, with substantially lower parameter counts and the minimal computational cost among adaptive convolution models.

We present SAM 3D, a generative model for visually grounded 3D object reconstruction, predicting geometry, texture, and layout from a single image. SAM 3D excels in natural images, where occlusion and scene clutter are common and visual recognition cues from context play a larger role. We achieve this with a human- and model-in-the-loop pipeline for annotating object shape, texture, and pose, providing visually grounded 3D reconstruction data at unprecedented scale. We learn from this data in a modern, multi-stage training framework that combines synthetic pretraining with real-world alignment, breaking the 3D "data barrier". We obtain significant gains over recent work, with at least a 5:1 win rate in human preference tests on real-world objects and scenes. We will release our code and model weights, an online demo, and a new challenging benchmark for in-the-wild 3D object reconstruction.

Detailed structural and species information on individual tree level is increasingly important to support precision forestry, biodiversity conservation, and provide reference data for biomass and carbon mapping. Point clouds from airborne and ground-based laser scanning are currently the most suitable data source to rapidly derive such information at scale. Recent advancements in deep learning improved segmenting and classifying individual trees and identifying semantic tree components. However, deep learning models typically require large amounts of annotated training data which limits further improvement. Producing dense, high-quality annotations for 3D point clouds, especially in complex forests, is labor-intensive and challenging to scale. We explore strategies to reduce dependence on large annotated datasets using self-supervised and transfer learning. Our objective is to improve performance across three tasks: instance segmentation, semantic segmentation, and tree classification using realistic and operational training sets. We observe improvements across all tasks, compared to training from scratch, evaluated with their respective metrics. For instance segmentation, self-supervised learning combined with domain adaptation improves AP50 by 16.98%. For semantic segmentation, self-supervised learning alone improves mIoU by 1.79%. For tree classification, hierarchical transfer learning improves mean Jaccard by 6.07%. To simplify use and encourage uptake, we integrated the tasks into a unified framework, streamlining the process from raw point clouds to tree delineation, structural analysis, and species classification. Pretrained models reduce energy consumption and carbon emissions by ~21%. This open-source contribution aims to accelerate operational extraction of individual tree information from laser scanning point clouds to support forestry, biodiversity, and carbon mapping.

Text-guided medical image editing must satisfy the requested pathology while preserving anatomy, modality-specific appearance, and clinical plausibility. However, existing datasets largely supervise editors with final accepted edits and discard the failed attempts produced during generation. We argue that these failures provide essential supervision for quality control: they specify what should be rejected, why an edit is medically or visually invalid, and how the instruction should be revised. We present Med-Banana, a trajectory-supervised framework for quality-controlled medical image editing. We introduce Med-Banana-80K, a large-scale resource of success-and-failure editing trajectories with candidate images, verification outcomes, rejection reasons, and prompt refinements. Building on it, Med-Banana jointly trains an editor, verifier, and refiner, enabling edit--verify--refine inference from accepted and rejected attempts. Experiments across MLLM judges, blind expert assessment, source-preservation and real--synthetic separability probes demonstrate consistent improvements over open medical image editors. Code and data are publicly available.

Foundation Models (FMs) are large-scale, pre-trained artificial intelligence (AI) systems that have revolutionized natural language processing and computer vision, and are now advancing geospatial analysis and Earth Observation (EO). They promise improved generalization across tasks, scalability, and efficient adaptation with minimal labeled data. However, despite the rapid proliferation of geospatial FMs, their real-world utility and alignment with global sustainability goals remain underexplored. We introduce SustainFM, a comprehensive benchmarking framework grounded in the 17 Sustainable Development Goals with extremely diverse tasks ranging from asset wealth prediction to environmental hazard detection. This study provides a rigorous, interdisciplinary assessment of geospatial FMs and offers critical insights into their role in attaining sustainability goals. Our findings show: (1) While not universally superior, FMs often outperform traditional approaches across diverse tasks and datasets. (2) Evaluating FMs should go beyond accuracy to include transferability, generalization, and energy efficiency as key criteria for their responsible use. (3) FMs enable scalable, SDG-grounded solutions, offering broad utility for tackling complex sustainability challenges. Critically, we advocate for a paradigm shift from model-centric development to impact-driven deployment, and emphasize metrics such as energy efficiency, robustness to domain shifts, and ethical considerations.

The emergence of audio-visual foundation models underscores the importance of reliably assessing their multi-modal understanding. The VGGSound dataset is commonly used as a benchmark for evaluation audio-visual classification. However, our analysis identifies several limitations of VGGSound, including incomplete labelling, partially overlapping classes, and misaligned modalities. These lead to distorted evaluations of auditory and visual capabilities. To address these limitations, we introduce VGGSounder, a comprehensively re-annotated, multi-label test set that extends VGGSound and is specifically designed to evaluate audio-visual foundation models. VGGSounder features detailed modality annotations, enabling precise analyses of modality-specific performance. Furthermore, we reveal model limitations by analysing performance degradation when adding another input modality with our new modality confusion metric.

Symbol grounding (Harnad, 1990) describes how symbols such as words acquire their meanings by connecting to real-world sensorimotor experiences. Recent work has shown preliminary evidence that grounding may emerge in (vision-)language models trained at scale without using explicit grounding objectives. Yet, the specific loci of this emergence and the mechanisms that drive it remain largely unexplored. To address this problem, we introduce a controlled evaluation framework that systematically traces how symbol grounding arises within the internal computations through mechanistic and causal analysis. Our findings show that grounding concentrates in middle-layer computations and is implemented through the aggregate mechanism, where attention heads aggregate the environmental ground to support the prediction of linguistic forms. This phenomenon replicates in multimodal dialogue and across architectures (Transformers and state-space models), but not in unidirectional LSTMs. Our results provide behavioral and mechanistic evidence that symbol grounding can emerge in language models, with practical implications for predicting and potentially controlling the reliability of generation.

Manual medical image segmentation by clinicians, though accurate, is time-consuming and variable across experts, whereas AI-based models automate this process but often underperform with limited data and domain shifts. Inspired by how pathology trainees acquire disease recognition skills through guided comparison with expert-annotated slides and histopathology atlas reference images, we propose Joint Retrieval-Augmented Segmentation (J-RAS). This framework enables segmentation networks to learn with guidance. J-RAS jointly optimizes a segmentation model and a retrieval model through alternating contrastive and supervised learning, allowing the retrieval network to discover contextually relevant image-mask pairs that refine the segmentation model's anatomical reasoning. Unlike conventional retrieval-based augmentation that passively provides similar samples, J-RAS establishes a mutual adaptation and optimization loop where the retrieval model learns to emphasize segmentation-relevant cues, while the segmentation model leverages retrieved examples to improve boundary delineation, robustness to rare cases, and cross-dataset generalization. Evaluations on four public benchmarks spanning different imaging modalities, including ACDC and M&Ms (MRI), Breast Cancer Ultrasound, and lung and infection CT, across multiple backbones (U-Net, TransUNet, SAM, and SegFormer) demonstrate the generalizability and effectiveness of J-RAS. For instance, on ACDC, SegFormer improves from a mean Dice of 0.8708$\pm$0.042 and HD of 1.8130$\pm$2.49 to 0.9115$\pm$0.031 and 1.1489$\pm$0.30. These results highlight how retrieval-guided contrastive optimization bridges human-like guidance and machine-learned precision in medical image segmentation.