Scalable data attribution methods typically assign isolated utility scores to individual training examples. This prevalent additive assumption fundamentally fails to capture critical subset dynamics, including data redundancy and complementary coverage. In this work, we reframe attribution as subset-level counterfactual utility prediction and introduce GRASP, an interaction-aware surrogate. Grounded in a theoretical smoothness lower bound, GRASP explicitly models subset interactions through a quadratic geometric penalty. To achieve pretraining-scale efficiency without relying on hidden oracle tuning, we couple low-dimensional feature sketches with a strictly finite lower-confidence bound selection protocol. Extensive subset-retraining evaluations demonstrate that GRASP decisively outperforms existing scalable baselines. It more than doubles the task-level rank correlation for counterfactual subset fidelity while reducing upfront artifact construction costs by nearly an order of magnitude. Downstream diagnostics further show that this scoring mechanism transfers to language model curation and cross-domain vision selection, establishing a robust foundation for optimizing massive pretraining corpora.

Despite advances in 3D scene understanding, existing 3D Large Multimodal Models operate in offline settings, requiring complete scene observations or predefined video clips. In this paper, we present an online 3D vision-language model that enables real-time spatial understanding from streaming video. Our approach adopts an autoregressive streaming control modeling based on the LLM's next-token prediction objective to learn when to respond, and employs a lightweight Visual-Spatial Feature Integration (VSFI) module to incrementally inject temporally aligned geometry priors into the visual stream. To alleviate long-context decoding overhead, we propose a plug-and-play Geometry-Adaptive Voxel Compression (GAVC) module for efficient visual token compression. To address the scarcity of streaming 3D-language data, we further develop a scalable data generation pipeline that curates over 1M online spatio-temporal 3D QA pairs and establishes a comprehensive benchmark spanning 29 tasks. Extensive experiments show that our approach significantly outperforms both proprietary and open-source models across online and offline 3D spatial understanding, reasoning, and grounding tasks. The project page is available at https://stream3d-vlm.github.io/

Vision-Language Models (VLMs) frequently rely on language priors, producing confident answers that are weakly grounded in visual evidence. While this behavior is widely observed, its internal mechanisms and its impact on benchmark evaluation remain insufficiently understood. In this work, we study language-prior reliance from both mechanistic and behavioral perspectives. Internally, we combine counterfactual layer replacement with supervised layer-wise MLP probing to trace how ground-truth visual semantics and language-prior semantics compete across the language decoder. Our analysis reveals a multi-stage bottleneck: intermediate layers often fail to effectively retrieve visual information, while later layers can further suppress surviving visual signals in favor of text-space biases. Externally, we introduce a progressive visual decay metric based on multi-step Gaussian blurring, which identifies instances whose answers remain invariant even as visual content is increasingly destroyed. Across twelve visual question-answering benchmarks and three representative VLMs, we find that a substantial fraction of examples remain answerable under severe or total visual obfuscation, indicating that current benchmarks can inadvertently reward visual ignorance. These findings demonstrate that language-prior reliance is a systematic routing failure affecting both model internals and benchmark validity. Finally, we outline critical pathways for future research, highlighting the necessity of designing training distributions and evaluation protocols built on structurally isolated or counterfactual data to enforce genuine cross-modal grounding.

This paper introduces ARAPDiffusion, a latent diffusion model to learn the underlying continuous shape space of a deformation shape collection. The key innovation is in injecting the as-rigid-as-possible (ARAP) deformation model as regularization losses into latent diffusion (LD), releasing the requirement of having abundant 3D training data for learning generative models. In contrast to the standard LD, we show how the ARAP model can be used to improve both the encoder/decoder and the LD model. The training procedure alternates between using the synthetic distribution defined by the LD model to develop a regularization loss that enhances the shape encoder/decoder and using the shape decoder to develop a regularization loss to improve the LD model. We also show the benefit of the LD paradigm in combining a representation-free LD process and an implicit shape decoder that is applicable to unorganized point clouds. The experimental results of unconditional and conditional shape generation demonstrate the advantages of ARAPDiffusion over baseline approaches.

Human Image Animation has seen significant advancements, primarily driven by diffusion models. However, existing methods typically demand substantial training data and resources to achieve high-quality results, limiting generalization and accessibility. In this work, we introduce \emph{FreeAnimate}, a training-free framework that leverages the inherent capabilities of image diffusion models to enable temporal consistency, identity preservation, and background stability. Our approach incorporates a novel preview generation strategy that provides temporal and structural priors from generated preview frames, effectively guiding pose alignment and background consistency without training. Additionally, FreeAnimate introduces Inversion-Boosted Attention and Reference-Anchored Self-Attention modules to guarantee temporal consistency and identity preservation. Experimental results demonstrate that FreeAnimate outperforms existing training-free competitors and training-based baseline methods, achieving generation quality comparable to state-of-the-art methods and offering robust generalization across diverse datasets. Our project page is at https://freeani.github.io/.

Blood glucose forecasting models are foundational for modern diabetes management systems, as reliable short-term predictions can enable proactive interventions, support automated insulin delivery, and reduce the risk of hypo- and hyperglycemic events. From a modeling perspective, glucose forecasting poses unique challenges due to heterogeneous physiological dynamics across diabetes populations. Traditional machine learning and deep learning models have been extensively evaluated for glucose prediction, yet recent time-series foundation models (TSFMs) remain much less studied in this setting. To bridge this gap, we present GlucoFM-Bench, a comprehensive benchmark evaluating state-of-the-art TSFMs alongside supervised deep learning models for blood glucose forecasting. We assess eight representative architectures, including pre-trained TSFMs, time-series large language models, and task-specific deep learning models, across 15 publicly available diabetes-relevant datasets comprising 1,117 individuals with type 1 diabetes, type 2 diabetes, prediabetes, and no diabetes. Models are evaluated under zero-shot, few-shot, and full-shot protocols, with systematic variation in context length and prediction horizon. Across datasets, pre-trained TSFMs, especially Chronos-2 and TimesFM, show strong zero-shot and few-shot transfer, with the best zero-shot model performing within 5% of the best full-shot supervised model. Yet, when task-specific data are abundant, a lightweight LSTM remains strongest, outperforming TSFMs by 4--21% under full-shot training. Stratified analyses reveal persistent challenges in T1D cohorts and hypo-/hyperglycemic ranges, highlighting the need for evaluation beyond aggregate error metrics. Together, GlucoFM-Bench provides a standardized and reproducible foundation for evaluating, comparing, and improving foundation models for blood glucose forecasting.

Our prior work introduced COVA, a synthetically generated multi-turn conversational smishing dataset of 3,201 labeled conversations, establishing baseline detection benchmarks across eight models. While XGBoost with TF-IDF features achieved the best performance, with 72.5\% accuracy and 0.691 macro F1, transformer models underperformed, which was attributed to input truncation and insufficient training data. We present COVA-X, an expanded dataset of 10,985 conversations spanning eight elder-targeted scam categories, produced by an improved generation pipeline addressing contamination, label mismatch, stage-direction bleed, and prompt-design failures from the first iteration. Retraining all classifiers on the expanded dataset yields the central finding of this work: Longformer now surpasses XGBoost on all evaluation metrics, achieving 79.71\% accuracy and 0.7786 macro F1 compared with 78.43\% and 0.7563 for XGBoost. This directly confirms that transformer models require larger conversational corpora to realize their contextual advantages. We additionally document a quality life-cycle including a 12.7$\times$ improvement in label correction rate, from 49.8\% to 3.9\%, an architectural intervention reducing virtual-kidnapping artifact rates from 67.1\% to 46.5\%, and a per-scam-type outcome analysis showing that scam categories modulate results in mechanism-consistent ways. A pre/post-cleanup sensitivity analysis confirms that dataset refinement recovers genuine label-relevant signal across all three classifier architectures.

In this paper, we propose a cross-view fusion framework that enhances the robustness of 6-DoF grasp pose estimation in corner views. Our framework alleviates occlusion by incorporating an auxiliary view and avoids the time-consuming, task-agnostic multi-view reconstruction through a post-fusion strategy. To enhance cross-view fusion, we propose a self-supervised contrastive learning strategy that leverages cross-view associations to regularize point cloud features. In brief, a cross-view point pair is considered a match if the two points correspond to the same 3D location, and a non-match if they represent distinct grasp directions. The learning strategy significantly enhances the spatial consistency and direction distinctiveness of point features, thereby facilitating cross-view fusion and improving estimation robustness. Furthermore, we propose a cross-view-aligned cylinder integration module to fuse grasp-relevant geometry into a comprehensive representation. Specifically, the module first aligns the cross-view points and features according to their similarity to enhance the robustness against noise. Subsequently, these points are registered into the cylindrical coordinate frame, emphasizing the rotation-symmetric geometry which is important for grasping. Finally, local self-attention and seed cross-attention layers are alternately employed, respectively enabling interactions within single views and across views, which supports fine-grained representation of grasp-relevant geometry. Our framework achieves strong performance on the GraspNet-1Billion benchmark and in real-world applications. Code is available at https://github.com/KJZhuAutomatic/Cross-view-Grasp.

Task planning often suffers from severe efficiency bottlenecks when robots must reason over long-horizon action sequences under complex logical constraints, including object affordances, spatial relationships, and sequential action dependencies. Recent neuro-symbolic methods improve planning efficiency by learning object-importance scores to prune task-irrelevant objects, but they typically rely on fixed offline supervision generated from full search spaces. This creates a train-test mismatch: at deployment, the planner operates in pruned search spaces induced by the model's own imperfect predictions, leading to exposure bias and degraded planning performance. To address this challenge, we formulate object-importance learning for task planning as an imperative learning-based bilevel optimization problem. The upper level optimizes a neural scorer, while the lower level solves a symbolic planning problem in the score-pruned search space. To stabilize this learning process, we introduce a 3R strategy into the lower-level planning, using parallel Repair, Restart, and Rollback recovery to provide reliable and adaptive feedback for upper-level learning. Experiments on three challenging benchmarks demonstrate state-of-the-art performance, including an 80.04% reduction in failure rate and a 57.14% reduction in planning time. We further validate the framework on a quadruped-based mobile manipulator in simulation and the real world, demonstrating its potential for efficient and deployable neuro-symbolic task planning.

Diffusion transformers (DiTs) equipped with multimodal attention (MM-Attn) have become a dominant paradigm for image generation. However, preventing the generation of harmful content remains a critical challenge, particularly in image-to-image (I2I) editing tasks. Existing safety mechanisms are primarily designed for text-to-image (T2I) synthesis or U-Net-based architectures, which limits their effectiveness for unified safety mitigation in DiT-based frameworks. To bridge this gap, we propose Unified Visual Safety Regulator (UVR), a training-free safe generation framework that regulates unsafe semantics in generated images. UVR is grounded in an analysis of attention dynamics from the perspective of information flow in MM-Attn. We identify a task-independent start-up stage, during which unsafe semantics in output patches rapidly emerge and can be accurately localized, followed by task-specific semantic amplification and interference stages, where harmful signals are further propagated and entangled with benign content. Based on these observations, UVR mitigates unsafe generation through unified, targeted attention modulation and explicit restriction of harmful information flow over the identified unsafe output patches. Experiments across various concepts show that UVR achieves state-of-the-art safety performance by achieving 91% and 77% erase rate in image synthesis and editing tasks, while preserving visual quality and fidelity with minimal degradation. Code is available at https://github.com/deng12yx/UVR.

Estimating hand-surface contact pressure from an egocentric view is crucial for AR/VR devices, robotic imitation, and ergonomic analysis. Existing methods often discretize pressure signal and process frames independently, leading to quantization errors and temporal inconsistencies. We present \emph{EgoPressDiff}, a conditional video diffusion framework that generates UV-pressure maps from visual input. The core of our approach is a multi-modal conditioning strategy, introducing a PoseNet and a Vertex Encoder to efficiently extract features from hand pose and 3D mesh vertices. These signals, along with depth information, guide the generative process to ensure the pressure fields are physically grounded. To effectively fuse these heterogeneous features, we further propose a Distribution-Calibrated Spatial Layer, which aligns their statistical properties before combination. Evaluated on the EgoPressure ego-view setting, EgoPressDiff achieves state-of-the-art results, improving Volumetric IoU by over 34\% relative to prior baseline, while reducing MAE and maintaining high temporal accuracy. Our project page is at https://egopressdiff.github.io/.

Diagnosing 802.11 packet captures requires expert protocol knowledge, is slow, inconsistent across engineers, and unscalable. LLM-based approaches sound plausible but fabricate protocol events absent from captures (especially truncated traces), produce uncalibrated confidence scores, and suffer evaluation bias when golden references are co-produced by the model under test. We introduce PROBE (Protocol Reasoning Over evidence-Based Ensembles), a multi-stage pipeline addressing all three failures. It integrates (i) deterministic PCAP-to-text normalization with frame-level verifiability, (ii) multi-run, multi-candidate ensembles with optional cross-model second opinion and progressive obfuscation, (iii) a verdict-aware evidence framework treating absence of failure evidence as contributing evidence, and (iv) a fully deterministic composite reliability score from evidence validity, run-to-run stability, and cross-model agreement without LLM self-assessment. On 87 enterprise Wi-Fi captures (104 capture-reviewer pairs), single-pass LLM analysis raises weighted evidence F1 from 0.871 (expert baseline) to 0.912 but misses critical frames in 35% of cases. Naive ensemble voting drops below baseline (0.842) as majority voting amplifies conservative verdicts: 50% of confirmed failures are misclassified as 'no issue' or 'insufficient evidence.' Adding evidence-grounded reconciliation achieves 0.957 F1, a 96% auto-accept rate, and a worst-case floor above 0.70. LLM self-reported confidence clusters at 0.95 regardless of difficulty (71% report exactly 0.95), confirming it is uninformative. We also introduce a model-agnostic evaluation framework using per-field assertion matching, eliminating circular bias from model-co-produced golden references.

Assistive robots operating under shared autonomy must balance user control with autonomous assistance. Because robot actions depend on internal intent inference that is not directly observable, mismatches between inferred and intended goals can undermine coordination and trust. We investigate how interface-level transparency, including feedback modality (visual vs. auditory) and information richness (sparse vs. rich), shapes interaction in a vision-based shared autonomy system. In a user study with N=25 participants across two assistive manipulation tasks, we evaluate how these designs influence coordination and trust. Providing feedback significantly improves intent alignment and reduces corrective intervention, indicating that making the inferred goal legible accelerates convergence in shared control. Participants preferred visual over auditory feedback, while preferences for sparse versus rich information depended on task complexity. We also found that revealing the full belief distribution did not consistently improve alignment or trust. Together, these findings indicate that effective transparency enhances coordination primarily through goal legibility, while trust depends on task-appropriate information exposure rather than maximal disclosure. Based on these results, we outline guidelines for designing transparent shared autonomy systems.

Aim: Existing AI-assisted traditional Chinese medicine diagnostic tools suffer from opaque reasoning processes, passive interaction, and limited treatment plan presentation. This study proposes a knowledge-enhanced visual diagnostic system to improve the transparency and interpretability of syndrome differentiation and treatment. Methods: The system is built upon a Neo4j knowledge graph comprising 241 syndromes, 1,263 symptoms, and 2,485 relations. It incorporates a four-stage symptom matching pipeline (exact, semantic, fuzzy, and large language model verification), an information gain-driven proactive questioning strategy optimized with genetic algorithms, and a multimodal treatment presentation integrating artificial intelligence-generated illustrations, three-dimensional meridian-acupoint models, and evidence-based literature. Results: Knowledge graph constraints reduced non-standard outputs by 32%. Case studies validated the effectiveness of the interactive workflow across patient self-assessment, clinician-assisted diagnosis, and traditional Chinese medicine education. Automated paired-comparison evaluation across 30 cases further demonstrated significant improvements in diagnostic trust (Cohen's d = 1.82, p < 0.001), reduced cognitive load (improvements in four of five dimensions), and higher credibility of evidence-based references (4.21 vs. 2.95). Conclusions: The proposed system enhances the transparency of traditional Chinese medicine diagnostic reasoning and the interpretability of treatment plans through knowledge graph-driven visualization and multimodal interaction, offering a practical solution for trustworthy artificial intelligence-assisted traditional Chinese medicine applications.

Modern medicine relies on heterogeneous data sources spanning radiology, pathology, text reports, and structured clinical information. However, real-world patient data are frequently incomplete, with missing or sparsely acquired modalities, limiting the effectiveness of standard multimodal fusion approaches. To this end, we propose the Multimodal Flexible Redundancy-aware decomposed GAted Learning (Multi-FRuGaL) framework, a decomposition-aware, adaptive gated intermediate-fusion framework that performs modality-level representation learning under missing data. Multi-FRuGaL integrates per-modality encoders with a signal decomposition layer, an input-conditioned gating network, and an information-aware fusion objective to separate redundant from modality-specific complementary signals, selectively upweighting informative modalities and suppressing redundant or noisy inputs, and remaining well-defined even when multiple modalities are absent. We evaluate Multi-FRuGaL on two multimodal head and neck cancer cohorts: the HANCOCK challenge dataset (N = 763) comprising five modalities and two prognostic endpoints (5-year survival and 2-year recurrence), and the HECKTOR challenge dataset (N = 588) comprising three modalities for human papillomavirus (HPV) status classification. Multi-FRuGaL consistently achieves higher mean performance than the evaluated baselines across multiple tasks, improving AUC from 0.601 to 0.8496 for survival, from 0.672 to 0.8102 for recurrence, and achieving 0.975 AUC for HPV prediction on HECKTOR. For survival analysis, it further achieves a concordance index of 0.6814 for overall survival, 0.7421 for recurrence-free survival, and 0.7143 for progression-free survival on HANCOCK, and 0.7203 for recurrence-free survival on HECKTOR. Qualitative analyses further show that Multi-FRuGaL learns discriminative and robust multimodal representations, even under severe missing-modality conditions.

The prediction of masses of atomic nuclei using machine learning can complement theoretical models and advance the exploration of poorly known domains of the nuclear chart. We propose a machine learning technique based on gated recurrent units (GRU), which have demonstrated competitive performance in nuclear-mass prediction by exploiting long-term dependencies. By integrating multiplicative interactions and product-unit transformations within recurrent units, we report significant improvements in nuclear-mass prediction. Computations are performed in the complex domain to jointly capture amplitude and phase dynamics. For interpolation and temporal-extrapolation tasks based on the atomic mass evaluation (AME2016 and AME2020), the complex additive-multiplicative product-unit gated recurrent unit (AM-PU-GRU) model consistently achieves the lowest prediction errors, with an interpolation RMSE of 0.227 $\pm$ 0.004 MeV and an extrapolation RMSE of 0.179 $\pm$ 0.015 MeV. These results surpass other state-of-the-art machine learning models and also outperform the real-valued GRU baseline and product-unit ablation variants, while remaining robust to different theoretical priors, including WS4 and SEMF. Our findings establish complex-valued product-unit recurrent networks as a new benchmark for sequence-based nuclear-mass prediction.

Large language models (LLMs) have been increasingly explored for graph computation, where tasks require reasoning over structured relationships and algorithmic operations. Yet, it remains unclear when LLMs can reliably support such computation and how they should be incorporated into graph-solving pipelines. Existing surveys at the intersection of LLMs and graphs primarily focus on graph learning, text-attributed graphs, or graph-language modeling. To bridge this gap, we provide a comprehensive review of LLMs for graph computation through a role-based taxonomy. Specifically, we identify two major paradigms: i) LLMs as executors, where models directly solve graph tasks from graph descriptions and instructions; and ii) LLMs as planners, where models formulate problems, decompose reasoning steps, and invoke external tools or agents for execution. Based on this taxonomy, we analyze the strengths and limitations of current methods. Our review indicates that LLMs are promising for simple, small-scale tasks, but remain unreliable for large-scale and exactness-demanding tasks. Finally, we summarize available datasets and suggest four future directions.

Multiple instance learning (MIL) has become a standard paradigm for whole slide image (WSI) analysis in digital pathology, as it enables slide-level prediction without dense annotations. Existing MIL methods typically rely on exhaustive extraction and encoding of high-resolution patches. However, this practice suffers from two critical limitations in real-world clinical settings: it struggles to capture global visual cues at lower magnifications, and incurs substantial computational overhead due to the massive number of high-resolution patches per slide. To address these limitations, we propose an efficient low-resolution multiple instance learning (LRMIL) framework that transfers high-resolution knowledge to low-resolution representations. LRMIL adopts a two-stage distillation strategy. First, patch-level cross-resolution distillation aligns low-resolution patch embeddings with high-resolution representations. Second, slide-level knowledge distillation trains a low-resolution student MIL model under both slide-level supervision and teacher guidance. At inference time, LRMIL operates exclusively on low-resolution patches, substantially reducing data preprocessing and computational cost. Extensive experiments on multiple WSI benchmarks demonstrate that LRMIL consistently outperforms state-of-the-art MIL methods while achieving more efficient inference. These results highlight LRMIL as a practical and scalable solution for WSI analysis in clinical pathology.

Understanding nonlinear feature interactions is crucial in science and engineering, yet standard multilayer perceptrons (MLPs) often capture such interactions only implicitly, leading to entangled representations that can impair robustness and interpretability. We investigate product-unit residual networks (PURe) that integrate multiplicative product units with residual connections to explicitly model cross-feature couplings while stabilizing optimization. We conduct a systematic evaluation on an interaction-driven synthetic benchmark and two real-world datasets, assessing predictive accuracy, robustness to Gaussian feature noise, and performance under limited training data, and we compare real- and complex-valued variants under a matched parameter budget. Beyond accuracy, SHapley Additive exPlanations (SHAP)-based interaction analyses show that PURe learns more concentrated and structurally coherent interaction patterns than MLP baselines. Overall, PURe achieves competitive or improved performance, better robustness and sample efficiency in low-data regimes, and enhanced interaction-level interpretability.

A central goal of cognitive neuroscience is to characterize the features that are represented by human language cortex. Artificial language models (LMs) have emerged as a powerful tool to address this challenge, but studies relating biological and artificial representations are often criticized as relating one black box to another. The present work introduces Augmented Sparse Encoding Models, an encoding framework that replaces dense LM hidden states with hierarchically-organized sparse autoencoder (SAE) features, while explicitly including surprisal as a predictor. Using this approach, we (i) produce interpretations of neural responses and (ii) test whether model-brain alignment reflects primary or idiosyncratic variation in LM representations. Using a high-field 7T fMRI dataset of eight participants listening to 200 linguistically diverse sentences, we first validate our modeling framework by recovering previous interpretations of voxel populations tuned to processing difficulty and meaning abstractness. We then interpret a previously-uncharacterized (but reliable) voxel population and find that it is tuned to people-related content. Next, we show that the fronto-temporal human language network is predicted by a common set of features across its constituent regions, but find that frontal regions are relatively well-explained by surprisal alone, even in the absence of LM-based features. Finally, we show that brain responses during language processing are not merely predictable from an arbitrary set of LM features. Rather, brain responses are best explained by the features that tend to capture the most general information encoded in LM representations, suggesting a nontrivial correspondence between brain and LM language representation.

Dynamic vision sensors (DVS) offer exceptional temporal resolution and dynamic range by asynchronously reporting pixel-level intensity changes. However, conventional DVS rely on a per-pixel independent triggering mechanism, ignoring the spatial integration performed by biological retinal ganglion cells (RGCs). Consequently, they lack the contrast sensitivity function (CSF) and its inherent sensitivity to mid-spatial frequencies, which inevitably leads to information incompleteness due to sub-threshold signal loss. To bridge this gap, we propose FS-DVS (Frequency-Selective Dynamic Vision Sensor), a novel paradigm that integrates a learnable spatial filter strictly preceding the event triggering process to mimic the RGC aggregation mechanism. By developing a differentiable event simulation framework, the spatial filter can be optimized end-to-end with downstream tasks. Our study reveals that starting from a delta function, the learned spatial filters spontaneously evolve into center-surround patterns that emphasize mid-frequency components, consistently aligning with human CSF. Beyond achieving substantial performance gains in object detection and action recognition, the consistent convergence to human-like CSF characteristics across different tasks underscores the universality of this mid-frequency selective mechanism. Compared to naively increasing sensor sensitivity or relying on post-processing, our paradigm achieves selective information enhancement with high noise resilience, providing a robust, biologically plausible blueprint for next-generation neuromorphic sensors.

This paper uses geometry to explain how a machine learning model can be stolen using an already existing well-known method. The author has shown the exact conditions required to perfectly copy the final layer of a transformer network. When looking deeper into the hidden layers the author has explained clear limits. The author has also demonstrated that a hidden network cannot be fully reverse engineered just by looking at the final results. The research clearly maps out what can and cannot be stolen from a model.

The new era has witnessed a remarkable capability to extend Vision-Language Models (VLMs) for tackling tasks of video understanding. While current VLMs excel at event- or story-level understanding, their ability to capture fine-grained motion details remains limited, primarily due to their focus on high-level static semantic structures and macro-event logic. In contrast, Video Diffusion Models (VDMs) are adept at modeling dynamic motion patterns, benefiting from large-scale video data and the intrinsic requirement of temporal generation. In this paper, we introduce MotionEnhancer, a novel approach that leverages motion priors distilled from a powerful video diffusion model as auxiliary supervision to enhance the motion understanding capability of a VLM via attention alignment. MotionEnhancer comprises two simple parameter-free modules, Motion-sensitive Head Selection (MHS) and Motion-salient Text Token Identification (MTTI), to directly extract and optimize motion-related attentions from the VDM in a computation-only manner. MotionEnhancer provides a scalable solution for motion understanding without additional training parameters, modifications to existing architectures, or tool calling. Extensive experiments demonstrate that MotionEnhancer can achieve consistent improvements over state-of-the-art VLMs on two motion-level video understanding benchmarks, especially on motion-related metrics.

Blind face restoration on consumer devices has to balance image quality against speed and memory. Strong methods such as GFPGAN and CodeFormer give good perceptual quality, but they rely on large pretrained generative priors and on operators such as attention, codebook lookup, and style modulation that are hard to compile and quantize on the small neural processing units (NPUs) used in consumer hardware. Small convolutional restorers run fast enough, but they tend to over-smooth and to leave artifacts around the eyes, nose, and mouth. We present CFRNet, a 2.0,M-parameter ResNet-style restorer for on-device use at $256\times256$, the common face-crop size on consumer NPUs. The main idea is Cycle-Consistent Fixed-Point Training (CCFP). Instead of training the network for one pass and then running it several times by hand, we train it to act as a fixed-point operator, so that applying it again to a restored face does not change the face. CCFP uses three training losses, namely progressive multi-cycle supervision, an idempotence loss, and a re-degradation cycle loss, and it adds no cost at inference. To compare fairly under our deployment limits, we retrain all baselines from scratch at the same $256\times256$ resolution. On a 300-image test set, CFRNet reaches the best perceptual score (LPIPS 0.250 at three cycles, which is 31% lower than one cycle) and also the best PSNR and SSIM at two cycles. It runs in about 23,ms per cycle in INT8 on a HiSilicon Hi3402 NPU, while the same baselines cannot be compiled to that chip. The cycle count $k$ acts as a simple quality knob that needs no retraining: PSNR is best at $k\!=\!2$ and LPIPS keeps improving up to $k\!=\!3$. We further show that the same idea works with a plain CNN that is even easier to deploy, and we run the model in real time on an in-car driver-monitoring board.

Table reasoning remains challenging for large language models (LLMs), particularly in tasks that require multi-step inference over long and structured tables. Existing approaches predominantly rely on single-direction reasoning, which limits their ability to explore alternative hypotheses across tasks. In this work, we propose CRAFT, a unified Counterfactual Reasoning Framework that reformulates Tabular question answering and fact verification into a general bidirectional verification process. Our method explicitly constructs both declarative statements and their counterfactual variants. Evidence is then extracted from reasoning along both the original and counterfactual paths, and integrated via a weighted mechanism to arrive at the final answer. Experimental results show that our approach consistently surpasses representative baselines on table reasoning datasets such as WikiTQ and TabFact, achieving especially large improvements on complex question answering. Our framework also significantly mitigates performance gaps between different backbone LLMs. This indicates that counterfactual reasoning effectively overcomes the limitations of single-direction inference, guiding LLMs toward more discerning reasoning and establishing a more principled paradigm for structured reasoning tasks. Our code will be made publicly available upon acceptance.

Modern reasoning models offer surprisingly strong zero-shot performance on challenging multi-label tasks that require selecting a small set of relevant options from hundreds of thousands to millions of candidate labels. We investigate how they achieve this mechanistically. We characterize reasoning as a two-phase process: A broad "shortlisting" of candidates followed by fine-grained reasoning over the resulting set. We provide evidence across a range of datasets that these steps can be isolated and are complementary. Using this characterization, we develop a mechanistic distillation strategy that consistently outperforms standard distillation.

Language-guided UAV agents must execute long-horizon semantic instructions while producing smooth, physically feasible continuous flight commands, yet existing Vision-Language Navigation (VLN) benchmarks typically use discrete or coarse actions and existing UAV Vision-Language-Action (VLA) tasks focus on short, atomic maneuvers. To address this gap in UAV task settings, we introduce \textbf{FLIGHT}, a \textbf{F}ine-grained \textbf{L}ong-horizon \textbf{I}nstruction-\textbf{G}uided benchmark for \textbf{H}ybrid UAV navigation and reasoning \textbf{T}asks, which combines multi-stage instructions with dense 6-DoF trajectory annotations across two dataset splits: Fine-grained VLN and Long-horizon Flow. To endow the UAV agent with the capability of real-time in-flight reasoning over task execution status and mission planning, while simultaneously accommodating high-frequency, real-time precise control, we further propose \textbf{FLIGHT VLA}, an asynchronous architecture that decouples a low-frequency Streaming Pilot Vision-Language Model (VLM) for task-state reasoning from a high-frequency diffusion action model for continuous control, supervised by explicit \textbf{Pilot Reasoning} texts that summarize the current flight state and anticipate the next subgoal. In closed-loop evaluation, FLIGHT VLA consistently surpasses representative VLN and VLA baselines on our FLIGHT benchmarks, achieving stronger multi-stage completion, subgoal adherence, and terminal control. Its trained Streaming Pilot Reasoning VLM further improves UAV video reasoning, validating the effectiveness of our design.

The performance gap across languages in LLMs is well documented, and closing it natively requires pretraining or fine-tuning on corpora that, for most languages, do not exist. Translation offers an alternative: converting an input into the model's dominant language unlocks its full capabilities at once. Applying translation to every input, however, is wasteful for languages the model already handles, while leaving the choice to the model fails in the opposite way, as LLMs are overconfident and skip the tool even when they cannot understand the input. Prior work resolves this with language-specific rules, domain heuristics, language identifiers, or external routers, each requiring manual engineering. We instead learn a single policy that decides when to translate from reward alone, developing language- and domain-adaptive introspection that assesses its own comprehension and invokes translation only when it cannot solve a task natively. Using data built by our answer-preserving translation pipeline, we continue RL on the post-trained Qwen3-4B across 22 languages in 3 resource tiers (High, Low, XLow) and 5 domains, and introduce confidence-gated GSPO for cost-sensitive tool use. The gated policy lifts reward over the baseline by +4.6 on High, +23.5 on Low, and +17.5 on XLow. Against an unconstrained policy that almost always translates, it preserves full reward at 63% of the cost and is Pareto-optimal across 87% of the cost-sensitivity range. Additionally, to simulate behavior on a completely unseen language, we create 2 synthetic languages, where our gated policy improves +18.7 over the overconfident baseline that underutilizes the tool even on these incomprehensible inputs. The policy transfers zero-shot to 9 held-out languages, and we analyze how tool use emerges over training, per language and per domain.

Automatic Speech Recognition (ASR) systems operating in real-time settings must process acoustic input under strict temporal constraints, where transcription decisions are inherently made on incomplete information. This causal constraint serves as an information bottleneck on attackers, significantly limiting attack performance. Our new Semantic Gambit attack breaks this causal limitation by augmenting the adversary with predictive context derived from a Large Language Model in real-time. Our experiments show that this form of augmentation can elevate the corpus-level Word Error Rate to 35.6% -- a three-fold increase over the current state-of-the-art. Ultimately, this work reveals how common, low-latency LLM tooling can be exploited to systematically subvert real-time ASR pipelines.

Robots performing long-horizon visual manipulation observe high-dimensional images, but successful plans depend on action-relevant facts: what can be done now and what changes afterward. A useful planning representation should discard irrelevant visual details while preserving action applicability and effects. Classical task planners exploit this structure through symbolic operators with preconditions and effects, but obtaining such representations from raw visual experience remains challenging. We study a visual task-planning setting in which a robot receives only image transitions: the current image, executed high-level action, and the resulting image. At test time, given a start image and a goal image, the robot must produce a sequence of high-level actions that reaches the goal. To address this problem, we introduce STRIPS-WM, a framework for learning image-grounded STRIPS-style world models directly from visual transitions. STRIPS-WM first induces a finite abstract transition graph from images, then learns latent binary predicates and one grounded propositional operator per action label. The learned operators form a symbolic action model with sparse preconditions and add/delete effects. Finally, the learned predicates are distilled into a visual encoder, enabling classical planning directly from novel start and goal images. Experiments on visual rearrangement tasks show that STRIPS-WM improves image-to-plan success over the tested visual rollout, latent graph-search and latent-symbolic baselines.