Spatial Attention

Reinforcement learning with verifiable rewards (RLVR) improves vision-language models (VLMs) by optimizing outcome rewards derived from final answers. However, such outcome-only rewards do not tell the model which image regions justify an answer. For questions that require visual grounding, these rewards cannot distinguish responses supported by relevant visual evidence from those produced by language-prior shortcuts or lucky guesses. We introduce EASE (Evidence-Anchored Spatial Attention), which augments multimodal RLVR with visual-evidence process supervision. EASE converts annotated evidence regions into a smoothed visual-token target and uses it to guide response-to-image attention during RL training, but only on high-reward trajectories. The annotations are used solely as privileged training labels, while inference requires only the original image and question. Across Qwen2.5-VL-7B, Qwen3-VL-4B, and Qwen3-VL-8B, EASE raises average scores over DAPO by 2.5 to 3.1 points on perception, hallucination, visual math, and multimodal reasoning benchmarks. Diagnostics and ablations show that EASE better aligns visual attention with annotated evidence regions.

Key-Value (KV) cache remains a major bottleneck for deploying Large Language Models (LLMs) in long-generation tasks. Prior work often applies uniform compression across both prefill and decoding caches, but compressing the prefill cache degrades performance by corrupting critical context. While preserving the prefill cache is essential, decoding-phase compression remains underexplored, with existing methods relying on rigid recency windows or instantaneous attention. Our analysis of attention dynamics reveals strong temporal patterns: critical tokens receive sustained attention over long horizons, while local reasoning involves short-lived bursts. Static heuristics fail to capture this behavior, leading to premature eviction of important tokens or retention of stale ones. We propose Moment-KV, a decoding-time KV cache compression method based on momentum-driven temporal attention aggregation. Our method models token importance as a continuously evolving state, where attention is aggregated with decay, capturing both long-term influence and recent relevance. Experiments show that Moment-KV significantly improves generation fidelity in long-generation tasks (2.3-3.2 %) while maintaining decoding latency.

The digital media landscape has seen a pervasive shift toward short-form video advertising on TV, social media and e-commerce platforms. The present study focuses on deep saliency prediction for short-form video advertising. Deep saliency models have been used to generate predictions of human eye fixation patterns with the purpose of enhancing user interaction with digital technology and optimizing its design. For video ads, dynamic saliency maps capture where and when viewers are looking, revealing why video ads are effective, and how their content should be optimized. We develop and test a new deep dynamic saliency prediction model called ViASNet (Video Ad Saliency Network), which has an architecture founded on the 3D U-Net, and accommodates the influence of audio and the semantic meaning of scenes. We assess the model's performance on 151 video ads, each seen by about 20 viewers wile their eye movements were tracked, and explore the critical factors influencing model performance through ablation experiments. We calculate the entropy of the predicted saliency maps frame-by-frame as a diagnostic tool to identify ads and scenes that fail to engage viewers, and illustrate its use on test data of 15 unseen ads. Our study reveals that ad design and testing can be sped up considerably through automated systems built on deep saliency models such as ViASNet.

Predicting conversion from Mild Cognitive Impairment (MCI) to Alzheimer's Disease (AD) is critical for early intervention. Current deep learning paradigms predominantly rely on cross-sectional structural MRI, neglecting prognostic value in patient-specific anatomical trajectories. We introduce the Temporal Adaptive Fusion Network (TAF-Net), a hybrid CNN-Transformer architecture that models paired longitudinal 3D MRI scans. Central to TAF-Net is a Temporal Fusion Module governed by an Adaptive Temporal Gate, which learns patient-specific weightings to synthesize three spatiotemporal representations: explicit structural change, region-to-region temporal cross-attention, and bilateral feature concatenation. Evaluated on the Alzheimer's Disease Neuroimaging Initiative cohort for three-year MCI-to-AD conversion prediction, TAF-Net achieved the highest discriminative performance among all evaluated methods using only structural MRI, significantly outperforming the strongest baseline and approaching multimodal methods requiring PET, CSF, or genetic data. The architecture exhibited exceptional data efficiency, matching baseline performance with a fraction of training data. Ablation studies demonstrate that longitudinal fusion improves discrimination while reducing predictive variance by 48% compared to single-timepoint evaluation. Interpretability analyses reveal spatial attention aligned with established AD pathology in the medial temporal lobe and ventricles, while the gating mechanism prioritizes explicit volumetric change with strong positive correlation to conversion risk.

Multi-Modal Diffusion Transformers (MM-DiTs) encode rich representations for training-free concept grounding, but existing attention-based methods often produce overlapping activations on visually confusable concepts, a failure mode we call concept leakage, where target responses spill over to non-target objects. To address this issue, we propose AnchorDiff, a training-free grounding method that decouples semantic localization from structural refinement. AnchorDiff selects a high-confidence anchor from concept-to-image attention map and propagates it as a one-hot seed over a hybrid graph derived from image-to-image self-attention. The graph uses output-space similarity for dense within-object propagation and a row-wise attention gate to suppress cross-object connections. Additionally, we introduce the Multi-Concept Confusion Dataset, which contains images with multiple visually similar concepts and separate masks, enabling explicit evaluation of concept leakage. Experiments show that AnchorDiff achieves strong grounding performance on ImageNet-Segmentation and PascalVOC, while substantially reducing concept leakage on our Multi-Concept Confusion Dataset.

Accurate traffic forecasting is essential for intelligent transportation systems, supporting a wide range of real-world applications. However, it remains challenging due to two key factors:(1) Traffic series contain heterogeneous temporal patterns, where stable periodic regularities coexist with event-driven fluctuations. Existing methods often treat them within a unified representation, limiting their ability to capture fine-grained temporal dynamics.(2)Spatial dependencies among nodes are inherently dynamic and sparse, while dense all-pairs attention often introduces redundant interactions and amplifies noise. To address these issues, we propose ADMFormer, an Adaptive-Decomposition Transformer with Time-Varying Masked Spatial Attention. Specifically, ADMFormer first employs a time-node adaptive gating mechanism to decouple traffic signals into dominant regularities and residual fluctuations that vary across time and nodes. A dual-branch temporal module is then designed to separately capture global periodic dependencies and high-frequency irregular variations from these two decomposed components. Furthermore, ADMFormer introduces a time-varying masked spatial attention that sparsifies spatial interactions based on real-time traffic states, thereby effectively preserving dynamic and informative dependencies. Extensive experiments on four real-world datasets demonstrate that ADMFormer achieves state-of-the-art performance.

Recently, world models have made significant progress in enhancing end-to-end driving systems through both future situation forecasting and improved scene understanding. However, existing driving world models are typically built upon dense scene representations, causing high computational costs and redundant information. In this paper, we present SparseWorld, a lightweight world model that focuses on predicting only the critical layout of the scene, enabling efficient future forecasting for end-to-end driving systems. SparseWorld first performs autoregressive rollout to forecast future map elements and surrounding agents, enabling the model to learn how driving scenarios evolve over time. It then leverages these predicted futures to refine downstream motion prediction and trajectory planning. Specifically, we propose a Sparse Dreamer that anticipates future instances in the latent space through joint temporal and spatial attention. By interacting with predicted future instances, the motion planner captures more accurate motion patterns and generates more informed and safety-aware trajectories. Extensive experiments demonstrate that SparseWorld significantly reduces collision risk and achieves state-of-the-art performance on the open-loop planning metrics of the nuScenes dataset with a collision rate of 0.05%. Moreover, it substantially outperforms the baseline method in closed-loop planning metrics on the Bench2Drive benchmark. Supplementary material is available at the project page: https://wryzju.github.io/SparseWorld/.

Low-light images suffer from severe noise, contrast loss, and semantic ambiguity, making enhancement a joint problem of denoising and detail recovery. We propose PixIE, a feed-forward pixel-space LLIE framework semantically prompted by a vision foundation model. PixIE first performs cross-scale denoising to suppress noise and preserve structure, then refines details using DINO-Prompted Pixel Blocks (DPPBs), which inject intermediate DINOv3 features through patch-conditioned, spatially continuous per-pixel modulation. To make pixel-space attention efficient across scales, we introduce Spatial-Channel Compaction (SCC), which jointly reduces the spatial token grid and channel dimension. We further propose Multi-Receptive-Field Pixel Embedding (MRPE) to provide neighborhood-aware pixel representations before semantic prompting, improving robustness to signal-dependent noise beyond point-wise embeddings. Experiments on LLIE benchmarks show that PixIE improves average PSNR by 1.9-15.0% over recent state-of-the-art methods and reduces LPIPS by 8.5-44.4%. Qualitative comparisons further show sharper details and more stable textures, improving both reconstruction fidelity and perceptual quality.

Diffusion Transformer (DiT) has emerged as a powerful model architecture for generating high-quality images and videos. In the case of video DiT, 3D Spatio-Temporal Attention increases token length in proportion to the number of frames, sharply increasing computational cost. Token reduction methods mitigate this cost by exploiting spatial redundancy, but existing approaches rely on inaccurate similarity estimates and lightweight matching algorithms, resulting in poor matching quality and only marginal acceleration. To overcome these limitations, we propose ORBIS, an SW-HW co-designed accelerator for video DiT. ORBIS leverages the output activation from the previous timestep to obtain more accurate inter-token similarity, substantially improving matching quality and enabling a higher token reduction ratio. We further introduce a Distribution-Aware Token Matching (DATM) algorithm that captures global token distribution and explicitly minimizes token-pair loss for additional gains. To fully hide DATM latency, we design specialized, deeply pipelined hardware and minimize its hardware cost through quantization, occupying only 2.4% of total area with negligible accuracy loss. Extensive experiments show that ORBIS achieves about 2x higher token reduction ratio than the state-of-the-art approach, AsymRnR, while delivering up to 4.5x speedup and 79.3% energy reduction compared to an NVIDIA A100 GPU.

Video temporal grounding (VTG), which localizes the start and end times of a queried event in an untrimmed video, is a key test of whether multimodal large language models (MLLMs) understand not only what happens but also when it happens. Although modern MLLMs describe video content fluently, their timestamp predictions remain unreliable, while existing remedies either require costly post-training on temporal annotations or rely on coarse training-free heuristics. In this work, we probe the cross-modal attention of MLLMs and uncover a perception-generation gap. Our key finding is that MLLMs often know the target interval during prefill, but lose this signal when generating the final answer. In the prefill stage, a sparse set of attention heads, which we call \emph{Temporal Grounding Heads} (TG-Heads), concentrates query-to-video attention on the ground-truth interval. During autoregressive decoding, however, the answer tokens shift attention away from this interval toward visually salient but query-irrelevant segments. This observation motivates an inference-time read-then-regenerate framework. We first convert TG-Head prefill attention into a debiased frame-level relevance signal and extract the high-attention interval it highlights. We then re-invoke the MLLM with visual context restricted to this interval, using video cropping or attention masking to suppress distractors. Without parameter updates and architectural changes, our framework consistently improves MiMo-VL-7B, Qwen3-VL-8B, and TimeLens-8B on three VTG benchmarks, with gains of up to +3.5 mIoU. The project website can be found at https://ddz16.github.io/mllmsknowwhen.github.io/.

Diffusion Language Models (DLMs) enable globally coherent, bidirectional, and controllable text generation, offering advantages over traditional autoregressive LLMs, while scaling to ultra-long sequences remains costly. Many existing block-sparse attention methods select blocks by fixed sampling patterns over the high-resolution attention space, such as tail regions or anti-diagonal stripes. Such prior-driven sampling can miss salient tokens and introduce instability under distribution shifts. In this paper, we propose the Block Approximate Sparse Attention framework (BA-Att) with block-wise pre-downsampled operation, which identifies informative regions within a compact downsampled space, avoiding reliance on brittle positional priors. To analyze its theoretical behavior, we define an oracle post-downsample attention map and formalize the approximation error between pre- and post-downsample schemes. Based on this insight, we introduce a lightweight norm-sorting module and a covariance-compensated correction that approximates full covariance using diagonal QK variances, reducing computational complexity. Extensive experiments show that our operator achieves up to 6.95x acceleration over FlashAttention in attention computation, and maintains near full-attention performance at 50% sparsity across language models, multimodal language models, and video generation models, demonstrating strong efficiency and generalization.

First-person dynamic spatial reasoning requires models to track continuous motion and precise geometric structure, but the quadratic attention cost of Transformer-based Video-LLMs makes dense visual tokens computationally expensive. Existing token pruning paradigms predominantly rely on discrete static snapshots, failing to preserve the motion and geometric cues essential for reasoning. We propose Event Cascade Pruning (ECP), to our knowledge the first training-free framework that leverages the high-frequency motion cues from event cameras as a continuous event-guided motion prior to guide token selection. ECP combines three stages: Event-Triggered Causal Sampling to anchor motion-informative keyframes, Event-guided Motion Saliency Filtering to suppress event-inactive visual tokens, and Event-Attention Ranking Fusion to calibrate spatial attention with motion-salient dynamics. With 80% visual token reduction, ECP outperforms the full-token baseline (37.62% vs. 36.31%) while achieving 1.89x inference speedup and 52% GFLOPs reduction. We further introduce ESR-Real, the first real-world RGB-event benchmark for first-person spatial reasoning, where ECP improves accuracy by 2.68 percentage points over full-token baselines.

Driver gaze estimation serves as a fundamental metric for evaluating driver attentiveness in modern monitoring systems. Beyond being vulnerable to sudden lighting changes and sensor noise, spatial-domain models struggle to disentangle authentic gaze cues from irrelevant visual attributes. In this paper, we propose LISA, a \textbf{L}anguage-guided \textbf{I}nterference-aware \textbf{S}patial-Frequency \textbf{A}ttention framework that combines frequency-domain priors with vision-language knowledge. Observing that the amplitude spectrum remains relatively stable even under spatial perturbations, we design a dual-domain fusion mechanism. It integrates stable low-frequency semantics into high-frequency details, employing spatial attention to precisely target ocular regions. To reduce semantic ambiguity, we also introduce a training-time disentanglement strategy. Using a frozen CLIP encoder and orthogonal regularization, we explicitly separate gaze features from appearance interference. Experiments on two benchmarks show that LISA achieves state-of-the-art performance, with significantly improved robustness against occlusions and lighting variations. The code repository is available at https://github.com/Mason-bupt/LISA.

Video reasoning segmentation requires localizing objects across video frames from natural language expressions, often involving spatial reasoning and implicit references. Recent approaches leverage frozen large vision-language models (LVLMs) by extracting attention maps and using them as spatial priors for segmentation, enabling training-free grounding. However, these attention maps are optimized for text generation rather than spatial localization, often resulting in diffuse and ambiguous grounding signals. In this work, we introduce SteerSeg, a lightweight framework that identifies attention misalignment as the key bottleneck in attention-based grounding and proposes to steer attention at its source through input-level conditioning. SteerSeg combines learnable soft prompts with reasoning-guided Chain-of-Thought (CoT) prompting. The soft prompts reshape the attention distribution to produce more spatially concentrated maps, while CoT-derived attributes resolve ambiguity among similar objects by guiding attention toward the correct instance. The resulting attention maps are converted into point prompts across keyframes to guide a segmentation model, while candidate tracklets are ranked and selected using correlation-based scoring. Our approach freezes the LVLM and segmentation model parameters and learns only a small set of soft prompts, preserving the model's pretrained reasoning capabilities while significantly improving grounding. Despite being trained only on Ref-YouTube-VOS, SteerSeg generalizes well across diverse benchmarks, significantly improving the spatial grounding capability of LVLMs. Project page: https://steerseg.github.io

Federated learning relies on effective client selection to alleviate the performance degradation caused by data heterogeneity. Most existing methods assume full visibility of all clients at each communication round. However, in large-scale or edge-based deployments, the server can only access a subset of clients due to communication, mobility, or availability constraints, resulting in partial visibility where only a subset of clients is observable for aggregation in each communication round. In this paper, we formulate federated client selection under partial visibility as a Partially Observable Markov Decision Process (POMDP) and propose a Spatial-Temporal attention-based reinforcement learning framework. By integrating historical global models and client identity embeddings, the proposed method captures both the temporal contexts of training and the persistent characteristics of clients. Experimental results across multiple datasets demonstrate that our approach achieves superior performance compared to existing baselines in heterogeneous and partially visible settings, validating its effectiveness in addressing the challenges of incomplete observations in practical federated learning systems.

State Space Models (SSMs) have emerged as a compelling alternative to attention models for long-range vision tasks, offering input-dependent recurrence with linear complexity. However, most efficient SSM variants reduce computation cost by modifying scan routes, resolutions, or traversal patterns, while largely leaving the recurrent dynamics implicit. Consequently, the model's state-dependent memory behavior is difficult to control, particularly in compact backbones where long scan paths can exceed the effective memory horizon. We propose Token-Conditioned Poles SSM (TCP-SSM), a structured selective SSM framework that improves efficiency while making recurrence dynamics explicit and interpretable through stable poles. TCP-SSM builds each scan operator with 1) real poles that model monotone or sign-alternating decay, and 2) complex-conjugate poles that capture damped oscillatory responses. Using bounded radius and angle modulation, TCP-SSM converts shared base poles into token-dependent poles, allowing each scan step to adapt its memory behavior to the current visual token while preserving pole stability. For practical scalability, we integrate grouped pole sharing with a lightweight low-rank input pathway, yielding an efficient scan operator that preserves linear-time scan complexity. Across image classification, semantic segmentation, and object detection, TCP-SSM reduces SSM computation complexity up to 44% in Vision Mamba-style models while maintaining or surpassing baseline accuracy.

Vision state space models inherit the efficiency and long-range modeling ability of Mamba-style selective scans. However, their performance depends critically on the representation of two-dimensional visual features as one-dimensional token sequences. Existing scan operators range from predefined geometric traversals to dynamic coordinate-based samplers that reroute tokens through predicted offsets and interpolation. While effective, these mechanisms primarily adapt paths or sampling locations, rather than explicitly modeling which local patches should exchange information before global state-space mixing. This motivates a simple question: \emph{can graphs help vision state space models see better?} We introduce \textbf{GraphScan}, a graph-induced dynamic scanning operator for Vision SSMs. For each token, GraphScan constructs a spatially bounded local graph, learns feature-conditioned affinities with relative positional bias, and produces the output token by one-step message passing over its semantic neighborhood. The resulting tokens are locally grounded before being processed by the selective SSM for global aggregation. GraphScan preserves token count and linear scaling in image size, while replacing coordinate-conditioned interpolation with feature-conditioned semantic routing. Integrated into a hierarchical backbone, \textbf{GraphScan-Mamba} achieves state-of-the-art performance among Vision SSMs across image classification, object detection, instance segmentation, and semantic segmentation, with modest computational overhead. Our analysis further shows that GraphScan induces interpretable displacement fields over the token lattice, providing a semantic and spatially grounded view of dynamic scanning. These results suggest that future Vision SSMs should treat scanning not merely as geometric serialization, but as learned local semantic routing before global state-space modeling.

A persistent paradox in time-series forecasting is that structurally simple MLP and linear models often outperform high-capacity Transformers. We argue that this gap arises from a mismatch in the sequence-modeling primitive: while many time-series dynamics are governed by global temporal operators (e.g., filtering and harmonic structure), standard attention forms each output as a convex combination of inputs. This restricts its ability to represent signed and oscillatory transformations that are fundamental to temporal signal processing. We formalize this limitation as a simplex-constrained mixing bottleneck in softmax attention, which becomes especially restrictive for operator-driven time-series tasks. To address this, we propose $\textbf{Temporal Operator Attention (TOA)}$, a framework that augments attention with explicit, learnable sequence-space operators, enabling direct signed mixing across time while preserving input-dependent adaptivity. To make dense $N \times N$ operators practical, we introduce Stochastic Operator Regularization, a high-variance dropout mechanism that stabilizes training and prevents trivial memorization. Across forecasting, anomaly detection, and classification benchmarks, TOA consistently improves performance when integrated into standard backbones such as PatchTST and iTransformer, with particularly strong gains in reconstruction-heavy tasks. These results suggest that explicit operator learning is a key ingredient for effective time-series modeling.

We introduce HYPERPOSE, a novel 3D human pose estimation framework that performs spatio-temporal reasoning entirely within the Lorentz model of hyperbolic space $\mathbb{H}^d$ to natively preserve the hierarchical tree topology of the human skeleton. Current state-of-the-art pose estimators aim to capture complex joint dynamics by relying on transformers and graph convolutional networks. Since these architectures operate exclusively in Euclidean space which fundamentally mismatches the inherent tree structure of the human body, these methods inevitably suffer from exponential volume distortion and struggle to maintain structural coherence. To this end, we depart from flat spaces and aim to improve geometric fidelity with Hyperbolic Kinematic Phase-Space Attention (HKPSA), natively embedding complex joint relationships without distortion, alongside a multi-scale windowed hyperbolic attention mechanism that efficiently models temporal dynamics in $O(TW)$ complexity. Furthermore, to overcome the well-known instability of training non-Euclidean manifolds, HYPERPOSE introduces a novel Riemannian loss suite and an uncertainty-weighted curriculum, enforcing physical geodesic constraints like bone length and velocity consistency. Extensive evaluations on the Human3.6M and MPI-INF-3DHP datasets demonstrate that HYPERPOSE achieves state-of-the-art structural and temporal coherence, significantly reducing both volume distortion and velocity error, while establishing new state-of-the-art benchmarks in overall positional accuracy.

Vision-language models (VLMs) have recently shown strong potential in soccer video understanding. However, given the high complexity of soccer videos due to large viewpoint variations, rapid shot transitions, and cluttered scenes, it remains unclear on whether VLMs rely on meaningful visual evidence or exploit spurious correlations and shortcut learning. Existing evaluation protocols focus primarily on classification accuracy and do not assess visual grounding. To address this limitation, we introduce SoccerLens, a benchmark for grounded soccer video understanding. The benchmark contains annotated video segments spanning $13$ common soccer events, with structured visual cues organized into three levels of semantic relevance. We further extend the attribution method of Chefer [arXiv:2103.15679] to jointly model spatial and temporal attention, and introduce evaluation metrics that measure whether model attention aligns with annotated cues or drifts toward spurious regions. Our evaluation of state-of-the-art soccer VLMs shows that, despite strong classification accuracy, current models fail to exceed $50\%$ grounding performance even under the loosest cue definitions and consistently underutilize temporal information. These results reveal a substantial gap between predictive performance and true visual grounding, highlighting the need for grounded evaluation in complex spatio-temporal domains such as soccer.

Adaptive control of Euler-Lagrange systems is challenging when friction is governed by a finite-horizon internal state that is not directly observable from joint measurements. In this setting, the measured closed-loop state is no longer Markovian, and standard certainty-equivalence adaptive laws may lose their convergence guarantees. The paper proposes a meta-control architecture in which the gains of a computed-torque controller are generated by a self-attention block processing a short window of recent motion history. The number of attention heads is selected before policy training through a surrogate analysis of the autocovariance of the memory-state gradient along the temporal window. This surrogate is based on a temporal adaptation of an incremental rank-tracking framework previously developed by the authors. The selected head count is then fixed and used as an architectural hyperparameter in a reinforcement-learning stage, where the policy is trained under a shielded admissibility constraint. The approach is tested on a 2-DOF manipulator with nonlinear friction and variable payload. In the short and matched memory regimes, the single-layer attention-only meta-controller outperforms a deeper Transformer baseline, with tracking-error reductions of 12 and 19 percentage points, respectively. The reported effect sizes are large, with d approximately -1.1 and -2.1, and Mann-Whitney p < 0.05 in both cases. In the long memory regime, however, the advantage disappears. Four out of ten training runs show either divergence or payload-invariant policy collapse, revealing a weakness in the static Phase-1 head-count prescription. This motivates moving rank-tracking inside the reinforcement-learning loop, allowing attention heads to be pruned or grown at runtime instead of fixed before training.

Video semantic search in densely crowded scenes remains a challenging task due to visual encoders tendency to prioritize salient foreground regions while neglecting contextually important, background areas. We propose an Inverse Attention Embedding mechanism that explicitly captures and highlights these overlooked regions. By combining inverse attention embeddings with traditional visual embeddings, our method significantly enhances semantic retrieval performance without additional training. Initial experiments and ablation studies demonstrate promising improvements over existing approaches in recall for video semantic search in crowded environments.

Although Large Vision-Language Models (LVLMs) have demonstrated remarkable performance on downstream tasks, they frequently produce contents that deviate from visual information, leading to object hallucination. To tackle this, recent works mostly depend on expensive manual annotations and training cost, or decoding strategies which significantly increase inference time. In this work, we observe that LVLMs' attention to visual information is significantly enhanced when answering caption queries compared to non-caption queries. Inspired by this phenomenon, we propose Caption-guided Visual Attention Steering (CAST), a training-free, plug-and-play hallucination mitigation method that leverages the attention activation pattern corresponding to caption queries to enhance LVLMs' visual perception capability. Specifically, we use probing techniques to identify attention heads that are highly sensitive to caption queries and estimate optimized steering directions for their outputs. This steering strengthens LVLM's fine-grained visual perception capabilities, thereby effectively mitigating object hallucination. CAST reduced object hallucination by an average of 6.03% across five widely used LVLMs and five benchmarks including both discriminative and generative tasks, demonstrating state-of-the-art performance while adding little inference cost and preserving other foundational capabilities.

Video editing has evolved toward In-Context Learning (ICL) paradigms, yet the resulting quadratic attention costs create a critical computational bottleneck. In this work, we propose In-context Sparse Attention (ISA), the first near-lossless empirical sparse framework tailored for ICL video editing. Our design is grounded in two key insights: first, context tokens exhibit significantly lower saliency than source tokens; second, we theoretically prove and empirically validate that Query sharpness correlates with approximation error. Motivated by these findings, ISA implements an efficient pre-selection strategy to prune redundant context, followed by a dynamic query grouping mechanism that routes high-error queries to full attention and low-error ones to a computationally efficient 0-th order Taylor sparse attention. Furthermore, we build \textbf{\texttt{LIVEditor-14B}} , a novel lightning video editing model via ISA and a proposed video-editing data pipeline that curated a 1.7M high-quality dataset. Extensive experiments demonstrate that LIVEditor-14B achieves a $\sim$60% reduction in attention-module latency while surpassing state-of-the-art methods across EditVerseBench, IVE-Bench, and VIE-Bench, delivering near-lossless acceleration without compromising visual fidelity.

Automated culprit identification in surveillance systems is a critical task that requires high accuracy along with computational efficiency for real-time deployment. In this paper, an optimized deep learning framework is proposed using a lightweight MobileNet architecture integrated with channel and spatial attention mechanisms. The proposed model enhances feature representation by selectively focusing on the most discriminative regions while suppressing irrelevant background information, thereby improving identification performance. The framework incorporates efficient preprocessing, attention based feature refinement, and a robust classification strategy optimized using the Adam Optimizer. Experiments were conducted on benchmark face recognition datasets, including Labelled Faces in the Wild (LFW), CASIA-WebFace, and a subset of VGGFace2, under realistic conditions with variations in illumination, pose, and occlusion. The results demonstrate that the proposed model achieves a high classification accuracy of 97.8%, outperforming conventional models such as baseline CNN, ResNet, and standard MobileNet. The confusion matrix analysis indicates strong class-wise discrimination with minimal misclassification, while ROC-AUC evaluation confirms robust performance across all classes. Additionally, the proposed approach maintains low computational complexity and reduced inference time, making it suitable for real-time surveillance and edge-based applications.

Road traffic accidents remain a significant global concern, with the majority attributed to human factors such as driver distraction and fatigue. This study proposes a camera-based approach to derive useful indicators to assess driver attentiveness and alertness. The proposed pipeline jointly satisfies the stringent real-time requirements imposed by the critical application and minimizes the computational requirements to allow for deployment on a tight computational budget. To this end, we develop a lightweight multi-task neural network that predicts multiple indicators for the face region in a single forward pass. The developed model is integrated into a complete execution workflow to produce a real-time estimate of attentiveness, fatigue, and engagement in distracting activities.

Zero-shot vision-language models (VLMs) offer a promptable alternative to task-specific training for gross tumor volume (GTV) delineation in non-small-cell lung cancer (NSCLC), but the prompt dimensions that govern their spatial behavior remain poorly understood. We study this question by probing alignment directions in VoxTell on a held-out internal NSCLC tumor dataset through sub-prompt decomposition into diagnosis, demographic, staging, anatomical, generic, and irrelevant controls; attribute-wise perturbation robustness; specificity ladders; and cross-case prompt swaps, while benchmarking against fine-tuned and zero-shot baselines using the Dice Similarity Coefficient (DSC) with Wilcoxon signed-rank tests and Benjamini-Hochberg correction. Alignment analyses revealed that anatomical location is the dominant driver of VoxTell's spatial attention: 63.4 percent of location perturbations caused catastrophic drops, prompt specificity improved from generic to full descriptions except for diagnosis-only prompts, irrelevant prompts correctly yielded zero segmentation, and cross-case prompt swaps confirmed patient-specific conditioning (matched DSC 0.906 vs. mismatched 0.406). Histology and stage substitutions had minimal effect, indicating that the model prioritizes "where to look" over "what to look for." In this context, VoxTell, operating fully zero-shot, achieved a mean DSC of 0.613, statistically indistinguishable from nnUNet (0.690, adjusted p = 0.156) and Ahmed et al. (0.675, adjusted p = 0.679), while significantly outperforming all other zero-shot models. Together, these findings argue that segmentation VLMs should be evaluated not only by Dice, but also by the prompt dimensions to which they align.

Robots operating in open, unstructured real-world environments must rely on onboard visual perception while autonomously moving across different locations. Continuous changes in onboard camera viewpoints cause significant visual scale variations in target objects, affecting vision-based motion generation. In this work, we present a stereo multistage spatial attention-based deep predictive learning method for real-time mobile manipulation. The proposed methods extracts task-relevant spatial attention points from stereo images and integrates them with robot states through a hierarchical recurrent architecture for closed-loop action prediction. We evaluate the system on four real-world mobile manipulation tasks using a mobile manipulator, including rigid placement, articulated object manipulation, and deformable object interaction. Experiments under randomized initial positions and visual disturbance conditions demonstrate improved robustness and task success rates compared to representative imitation learning and vision-language-action baselines under identical control settings. The results indicate that structured stereo spatial attention combined with predictive temporal modeling provides an effective solution within the evaluated mobile manipulation scenarios.

Temporal modeling remains a fundamental challenge in video understanding, particularly as sequence lengths scale. Traditional video models relying on dense spatiotemporal attention suffer from quadratic computational costs for long videos. To circumvent these costs, recent approaches adapt image models for videos via Parameter-Efficient Fine-Tuning (PEFT) methods such as adapters. However, deeply inserting these modules incurs prohibitive activation memory overhead during back-propagation. While recent efficient State Space Models (SSMs) introduce linear complexity, they disrupt 2D spatial relationships and rely on extensive masked pre-training to recover spatial awareness. To overcome these limitations, we propose Parallel Kinematic Selective State Space Scanners (PKS$^4$). We retain a standard 2D vision backbone for spatial semantics and insert a single plug-and-play PKS$^4$ module with linear-complexity temporal scanning, avoiding temporal attention and multi-layer adapters. We first extract kinematic priors via a Kinematic Prior Encoder, which captures local displacements and motion boundaries through inter-frame correlations and differences. These priors drive linear-complexity SSMs to track underlying kinematic states, adaptively modulating update speeds and read-write strategies at each time step. Instead of global scanning, we deploy parallel scanners along the temporal dimension for each spatial location, preserving spatial structures while reducing overhead. Experiments on spatial-heavy and temporal-heavy action recognition benchmarks show that PKS$^4$ achieves state-of-the-art performance. Remarkably, our method converges in merely $20$ epochs, achieving approximately $10\times$ lower training compute than pure video SSMs, establishing a new paradigm for efficient video understanding.

While large models demonstrate the strong representational power of vanilla attention, this core mechanism cannot be directly applied to Dense Object Tracking: its quadratic all-to-all interactions are computationally prohibitive for dense motion estimation on high-resolution features. This mismatch prevents Dense Object Tracking from fully leveraging attention-based modeling in crowded and occlusion-heavy scenes. To address this challenge, we introduce GateMOT, an online tracking framework centered on Q-Gated Attention (Q-Attention), an efficient and spatially aware attention variant. Our key idea is to repurpose the Query from a similarity-conditioning term into a learnable gating unit. This Gating-Query (Gating-Q) produces a probabilistic gate that modulates Key features in an element-wise manner, enabling explicit relevance selection instead of costly global aggregation. Built on this mechanism, parallel Q-Attention heads transform one shared feature map into task-specific yet consistent representations for detection, motion, and re-identification, yielding a tightly coupled multi-task decoder with linear-complexity gating operations. GateMOT achieves state-of-the-art HOTA of 48.4, MOTA of 67.8, and IDF1 of 64.5 on BEE24, and demonstrates strong performance on additional Dense Object Tracking benchmarks. These results show that Q-Attention is a simple, effective, and transferable building block for attention-based tracking in dense tracking scenarios.

Image classification remains a fundamental yet challenging task in computer vision, particularly when fine-grained feature extraction and background noise suppression are required simultaneously. Conventional convolutional neural networks, despite their remarkable success in hierarchical feature learning, often struggle with capturing multi-scale contextual information and are susceptible to overfitting when confronted with noisy or irrelevant image regions. In this paper, we propose RDCNet (Image Classification Network with Random Dilated Convolution), a novel architecture built upon ResNet-34 that integrates three synergistic innovations to address these limitations: (1) a Multi-Branch Random Dilated Convolution (MRDC) module that employs parallel branches with varying dilation rates combined with a stochastic masking mechanism to capture fine-grained features across multiple scales while enhancing robustness against noise and overfitting; (2) a Fine-Grained Feature Enhancement (FGFE) module embedded within MRDC that bridges global contextual information with local feature representations through adaptive pooling and bilinear interpolation, thereby amplifying sensitivity to subtle visual patterns; and (3) a Context Excitation (CE) module that leverages softmax-based spatial attention and channel recalibration to dynamically emphasize task-relevant features while suppressing background interference. Extensive experiments conducted on five benchmark datasets -- CIFAR-10, CIFAR-100, SVHN, Imagenette, and Imagewoof -- demonstrate that RDCNet consistently achieves state-of-the-art classification accuracy, outperforming the second-best competing methods by margins of 0.02%, 1.12%, 0.18%, 4.73%, and 3.56%, respectively, thereby validating the effectiveness and generalizability of the proposed approach across diverse visual recognition scenarios.

In the hyperspectral image (HSI) classification task, each pixel is categorized into a specific land-cover category or material. Convolutional neural networks (CNNs) and transformers have been widely used to extract local and non-local features in HSI classification. Recent works have utilized a multi-scale vision transformer (ViT) to enhance spectral feature capture and yield promising results. However, most existing methods still face challenges in the effective joint use of spatial-spectral information and in preserving information across layers during the propagation process. To address these issues, we propose a synergistic CNN-Transformer network with pooling attention fusion for HSI classification, which collaboratively utilizes CNNs and ViT to process spatial and spectral features separately. Specifically, we propose a Twin-Branch Feature Extraction (TBFE) module, which employs 3D and 2D convolution in parallel to comprehensively extract spectral and spatial features from HSI. A hybrid pooling attention (HPA) module is designed to aggregate spatial attention. Moreover, a cascade transformer encoder is employed for global spectral feature extraction, and a simple yet efficient cross-layer feature fusion (CFF) module is designed to reduce the loss of crucial information in the previous network layers. Extensive experiments are conducted on several representative datasets to demonstrate the superior performance of our proposed method compared to the state-of-the-art works. Code is available at https://github.com/chenpeng052/SCT-Net.git.

Emotionally talking head video generation aims to generate expressive portrait videos with accurate lip synchronization and emotional facial expressions. Current methods rely on simple emotional labels, leading to insufficient semantic information. While introducing high-level semantics enhances expressiveness, it easily causes lip-sync degradation. Furthermore, mainstream generation methods struggle to balance computational efficiency and global motion awareness in long videos and suffer from poor temporal coherence. Therefore, we propose an \textbf{E}motion-\textbf{A}ware \textbf{D}iffusion model-based \textbf{Net}work, called \textbf{EAD-Net}. We introduce SyncNet supervision and Temporal Representation Alignment (TREPA) to mitigate lip-sync degradation caused by multi-modal fusion. To model complex spatio-temporal dependencies in long video sequences, we propose a Spatio-Temporal Directional Attention (STDA) mechanism that captures global motion patterns through strip attention. Additionally, we design a Temporal Frame graph Reasoning Module (TFRM) to explicitly model temporal coherence between video frames through graph structure learning. To enhance emotional semantic control, a large language model is employed to extract textual descriptions from real videos, serving as high-level semantic guidance. Experiments on the HDTF and MEAD datasets demonstrate that our method outperforms existing methods in terms of lip-sync accuracy, temporal consistency, and emotional accuracy.

We propose FlowAnchor, a training-free framework for stable and efficient inversion-free, flow-based video editing. Inversion-free editing methods have recently shown impressive efficiency and structure preservation in images by directly steering the sampling trajectory with an editing signal. However, extending this paradigm to videos remains challenging, often failing in multi-object scenes or with increased frame counts. We identify the root cause as the instability of the editing signal in high-dimensional video latent spaces, which arises from imprecise spatial localization and length-induced magnitude attenuation. To overcome this challenge, FlowAnchor explicitly anchors both where to edit and how strongly to edit. It introduces Spatial-aware Attention Refinement, which enforces consistent alignment between textual guidance and spatial regions, and Adaptive Magnitude Modulation, which adaptively preserves sufficient editing strength. Together, these mechanisms stabilize the editing signal and guide the flow-based evolution toward the desired target distribution. Extensive experiments demonstrate that FlowAnchor achieves more faithful, temporally coherent, and computationally efficient video editing across challenging multi-object and fast-motion scenarios. The project page is available at https://cuc-mipg.github.io/FlowAnchor.github.io/.

Leveraging the natural spatiotemporal energy decay in video diffusion offers a path to efficiency, yet relying solely on rigid static masks risks losing critical long-range information in complex dynamics. To address this issue, we propose \textbf{DynamicRad}, a unified sparse-attention paradigm that grounds adaptive selection within a radial locality prior. DynamicRad introduces a \textbf{dual-mode} strategy: \textit{static-ratio} for speed-optimized execution and \textit{dynamic-threshold} for quality-first filtering. To ensure robustness without online search overhead, we integrate an offline Bayesian Optimization (BO) pipeline coupled with a \textbf{semantic motion router}. This lightweight projection module maps prompt embeddings to optimal sparsity regimes with \textbf{minimal runtime overhead}. Unlike online profiling methods, our offline BO optimizes attention reconstruction error (MSE) on a physics-based proxy task, ensuring rapid convergence. Experiments on HunyuanVideo and Wan2.1-14B demonstrate that DynamicRad pushes the efficiency--quality Pareto frontier, achieving \textbf{1.7$\times$--2.5$\times$ inference speedups} with \textbf{over 80% effective sparsity}. In some long-sequence settings, the dynamic mode even matches or exceeds the dense baseline, while mask-aware LoRA further improves long-horizon coherence. Code is available at https://github.com/Adamlong3/DynamicRad.

Driver gaze estimation is essential for understanding the driver's situational awareness of surrounding traffic. Existing gaze estimation models use driver facial information to predict the Point-of-Gaze (PoG) or the 3D gaze direction vector. We propose a benchmark dataset, Urban Driving-Face Scene Gaze (UD-FSG), comprising synchronized driver-face and traffic-scene images. The scene images provide cues about surrounding traffic, which can help improve the gaze estimation model, along with the face images. We propose SGAP-Gaze, Scene-Grid Attention based Point-of-Gaze estimation network, trained and tested on our UD-FSG dataset, which explicitly incorporates the scene images into the gaze estimation modelling. The gaze estimation network integrates driver face, eye, iris, and scene contextual information. First, the extracted features from facial modalities are fused to form a gaze intent vector. Then, attention scores are computed over the spatial scene grid using a Transformer-based attention mechanism fusing face and scene image features to obtain the PoG. The proposed SGAP-Gaze model achieves a mean pixel error of 104.73 on the UD-FSG dataset and 63.48 on LBW dataset, achieving a 23.5% reduction in mean pixel error compared to state-of-the-art driver gaze estimation models. The spatial pixel distribution analysis shows that SGAP-Gaze consistently achieves lower mean pixel error than existing methods across all spatial ranges, including the outer regions of the scene, which are rare but critical for understanding driver attention. These results highlight the effectiveness of integrating multi-modal gaze cues with scene-aware attention for a robust driver PoG estimation model in real-world driving environments.

Generating high-quality videos from complex temporal descriptions that contain multiple sequential actions is a key unsolved problem. Existing methods are constrained by an inherent trade-off: using multiple short prompts fed sequentially into the model improves action fidelity but compromises temporal consistency, while a single complex prompt preserves consistency at the cost of prompt-following capability. We attribute this problem to two primary causes: 1) temporal misalignment between video content and the prompt, and 2) conflicting attention coupling between motion-related visual objects and their associated text conditions. To address these challenges, we propose a novel, training-free attention mechanism, Temporal-wise Separable Attention (TS-Attn), which dynamically rearranges attention distribution to ensure temporal awareness and global coherence in multi-event scenarios. TS-Attn can be seamlessly integrated into various pre-trained text-to-video models, boosting StoryEval-Bench scores by 33.5% and 16.4% on Wan2.1-T2V-14B and Wan2.2-T2V-A14B with only a 2% increase in inference time. It also supports plug-and-play usage across models for multi-event image-to-video generation. The source code and project page are available at https://github.com/Hong-yu-Zhang/TS-Attn.

Data-driven MoCap-to-radar models generate plausible micro-Doppler spectrograms, but do they actually learn the underlying physics? We introduce a physics-based interpretability framework to answer this question via two proposed complementary metrics: one measures alignment between model predictions and the physics-derived Doppler frequency, while the other tests whether predictions preserve the velocity-frequency relationship under velocity intervention. Both metrics require only MoCap input and model predictions, without access to measured radar data. Experiments across several model architectures reveal that low reconstruction error does not guarantee physical consistency: some, but not all, models achieve low error yet perform poorly on the two physics-based metrics. Further analysis shows that temporal attention is critical for transformer-based models to learn the underlying physics.

The Transformer, a breakthrough architecture in artificial intelligence, owes its success to the attention mechanism, which utilizes long-range interactions in sequential data, enabling the emergent coherence between large language models (LLMs) and data distributions. However, temporal attention, that is, different forms of long-range interactions in temporal sequences, has rarely been explored in emergence phenomenon of complex systems including oscillatory coherence in quantum, biophysical, or climate systems. Here, by designing dynamical temporal attention (DTA) with time-varying query, key, and value matrices, we propose an Emergence Transformer. This architecture allows each component to interact with its own or its neighbors' past states through dynamical attention kernels, thereby enabling the promotion and/or suppression of the emergent coherence of components. Interestingly, we uncover that neighbor-DTA consistently promotes oscillatory coherence, whereas self-DTA exhibits an optimal attention weight for coherence enhancement, owing to its non-monotonic dependence on network structure. Practically, we demonstrate how DTA reshapes social coherence, suggesting strategies to either enhance agreement or preserve plurality. We further apply DTA to the paradigmatic Hopfield neural network, achieving emergent continual learning without catastrophic forgetting. Together, these results lay a foundation and provide an immediate paradigm for modulating emergence phenomenon in networked dynamics only using DTA.

Structural damage detection is essential for maintaining the safety and reliability of civil infrastructure. However, accurately identifying different types of structural damage from images remains challenging due to variations in damage patterns and environmental conditions. To address these challenges, this paper proposes MS-SSE-Net, a novel deep learning (DL) framework for structural damage classification. The proposed model is built upon the DenseNet201 backbone and integrates novel multi-scale feature extraction with channel and spatial attention mechanisms (MS-SSE-Net). Specifically, parallel depthwise convolutions capture both local and contextual features, while squeeze-and-excitation style channel attention and spatial attention emphasize informative regions and suppress irrelevant noise. The refined features are then processed through global average pooling and a fully connected classification layer to generate the final predictions. Experiments are conducted on the StructDamage dataset containing multiple structural damage categories. The proposed MS-SSE-Net demonstrates superior performance compared with the baseline DenseNet201 and other comparative approaches. Specifically, the proposed method achieves 99.31% precision, 99.25% recall, 99.27% F1-score, and 99.26% accuracy, outperforming the baseline model which achieved 98.62% precision, 98.53% recall, 98.58% F1-score, and 98.53% accuracy.

Trajectory prediction is a key component of autonomous driving systems because future motions directly affect collision checking, behavior planning, and control. The task remains challenging under dense interactions, heterogeneous behaviors, multimodal futures, and limited on-board computation. Existing graph, attention, and generative predictors improve interaction reasoning or uncertainty modeling, but their high-capacity designs are often costly for real-time deployment. Lightweight predictors and conventional distillation reduce inference cost, yet usually rely on static imitation and do not explicitly correct safety-relevant teacher bias. This paper proposes \textbf{MAVEN-T}, a reinforced heterogeneous distillation framework for real-time multi-agent trajectory prediction. A high-capacity teacher models directed local interactions with a surround-aware graph encoder, combines efficient temporal filtering with shifted-window spatial attention, and decodes maneuver-specific futures through a sparse Mixture-of-Experts head. A compact GRU--Squeeze-and-Excitation student with a Low-Rank Adapted policy head is trained by feature-, attention-, and semantic-level distillation. To align prediction with downstream behavior, the student is further refined by Proximal Policy Optimization rewards for collision avoidance, comfort, and progress, while a complexity-aware curriculum and Elastic Weight Consolidation stabilize stage-wise training. Experiments on NGSIM, HighD, MoCAD, Argoverse~2, and the Waymo Open Motion Dataset evaluate accuracy, efficiency, generalization, robustness, and closed-loop safety. The student achieves 6.2$\times$ parameter compression, 3.7$\times$ inference acceleration, and 14.6,ms latency on an NVIDIA Jetson AGX Orin while maintaining competitive accuracy.

Standard attribution heatmaps show where a vision-language model (VLM) focuses, but they do not reveal whether the recovered evidence is organized by the queried spatial relation or merely reflects image layout. To address this problem, we introduce CREG (Compass Relational Evidence Graph), a training-free diagnostic framework that converts token-level attribution into a reference-centered compass distribution and measures its directional alignment. CREG provides a shared directional readout across attribution methods and makes comparison with geometric controls explicit. Across three spatial-relation benchmarks, box-only geometry achieves Direction Alignment Error 28.4 to 34.4 degrees lower than the best current model-based attribution method on each dataset, leaving a substantial gap between attribution structure and simple target localization. To examine this gap, we apply a diagnostic battery including target intervention, reference-center randomization, and variance partition. Taken together, the results suggest that the directional structure recoverable from current attribution methods is limited and often mixed with image layout. We further find that higher task accuracy does not reliably coincide with better directional attribution: small-scale LoRA training and newer model generations can improve task accuracy while leaving Direction Alignment Error unchanged or worse. These findings characterize what current attribution methods reveal rather than the model's internal spatial representation. CREG provides a controlled protocol for testing whether improvements in spatial reasoning are accompanied by more directionally organized evidence.

Event cameras provide sequential visual data with spatial sparsity and high temporal resolution, making them attractive for low-latency object detection. Existing asynchronous event-based neural networks exploit this low-latency advantage by updating predictions event by event, but still suffer from two bottlenecks: recurrent architectures are difficult to train efficiently on long sequences, and improving accuracy often increases per-event computation and latency. Linear attention is appealing because it enables parallel training and recurrent inference. However, its dense state updates make per-event computation scale with the state size, yielding a poor accuracy-efficiency trade-off for object detection, where accurate localization requires fine-grained spatial states. The key challenge is therefore to introduce sparse state activation that exploits the spatial sparsity of events while preserving efficient parallel training. We propose Spatially-Sparse Linear Attention (SSLA), which introduces a mixture-of-spaces state decomposition and a scatter-compute-gather training procedure, enabling state-level sparsity as well as training parallelism. Building on SSLA, we develop an end-to-end asynchronous linear attention model, SSLA-Det, for low-latency event-based object detection. On Gen1 and N-Caltech101, SSLA-Det achieves state-of-the-art accuracy among asynchronous methods, reaching 0.375 mAP and 0.515 mAP, respectively, while reducing per-event computation by over 20 times compared with the strongest prior asynchronous baseline, demonstrating the potential of linear attention for low-latency event-based vision.

Spatial computation in geographic systems increasingly requires query-conditioned, local, interpretable aggregation under metric constraints. Many classical approaches rely on global summation and treat approximation as an implementation concern, limiting interpretability and scalability at large scales. We propose the Adaptive Density Field (ADF), a geometric attention framework that formulates spatial aggregation as a query-conditioned, metric-induced attention operator in continuous space. Given a set of labelled spatial points with associated scalar scores, ADF defines a continuous intensity field over space. For a given query location, the field value is obtained via a local adaptive Gaussian kernel mixture centered on the query's nearest neighbors, where kernel bandwidths are modulated by point-specific scores to evaluate local aggregated influence. Additionally, approximate nearest-neighbor search is introduced, enabling scalable execution while preserving locality. The proposed ADF bridges concepts from adaptive kernel methods, classical GIS methods, and attention mechanisms by reinterpreting spatial influence as geometry-embedded attention, grounded in physical distance rather than learned latent projections. The proposed framework is formulation-level rather than algorithm-specific, allowing flexible kernel choices, score-to-bandwidth mappings, and approximation parameters. This approach provides a unifying perspective on spatial influence modeling that emphasizes structure, scalability, and geometric interpretability, with relevance to geographic information systems and spatial machine learning.

Despite achieving strong results on standard benchmarks, current point tracking methods rely on feature backbones that are rarely designed with the temporal coherence needed for robust real-world performance. While recent works incorporate powerful visual foundation model (VFM) features into tracking pipelines, no prior work has systematically analyzed which VFM provides the most robust representations for point tracking. We present the first such analysis, evaluating diverse VFMs in a zero-shot setting on both standard and robustness benchmarks for point tracking. Our study reveals that video diffusion transformers (DiTs) consistently yield the most temporally coherent and discriminative features, even surpassing ResNet backbones explicitly supervised on tracking data. We hypothesize this advantage stem from large-scale video pretraining, full 3D spatio-temporal attention, and a diffusion training objective. Motivated by this finding, we propose DiTracker, which integrates video DiT features into existing tracking frameworks through query-key matching cost computation, cost-level fusion with a lightweight ResNet branch, and LoRA adaptation. Under the same tracking head, DiTracker is trained solely on synthetic data with far fewer iterations, yet outperforms CoTracker3 trained with additional real-world videos, with the largest gains under challenging and corrupted scenarios. It further generalizes across tracking heads and scales with backbone size, confirming that generative video pretraining provides real-world priors that reduce the dependence on large-scale real-data supervision.

Fashion image editing aims to modify a person's appearance based on a given instruction. Existing methods require auxiliary tools like segmenters and keypoint extractors, lacking a flexible and unified framework. Moreover, these methods are limited in the variety of clothing types they can handle, as most datasets focus on people in clean backgrounds and only include generic garments such as tops, pants, and dresses. These limitations restrict their applicability in real-world scenarios. In this paper, we first extend an existing dataset for human generation to include a wider range of apparel and more complex backgrounds. This extended dataset features people wearing diverse items such as tops, pants, dresses, skirts, headwear, scarves, shoes, socks, and bags. Additionally, we propose AnyDesign, a diffusion-based method that enables mask-free editing on versatile areas. Users can simply input a human image along with a corresponding prompt in either text or image format. Our approach incorporates Fashion DiT, equipped with a Fashion-Guidance Attention (FGA) module designed to fuse explicit apparel types and CLIP-encoded apparel features. Both Qualitative and quantitative experiments demonstrate that our method delivers high-quality fashion editing and outperforms contemporary text-guided fashion editing methods.

InfinityStar extends visual autoregressive generation to video through a sequence of image and clip pyramids. Its changing scale and cross-clip context, however, leave late-scale attention costly and make sparse patterns reused from diffusion or image VAR models unreliable. We introduce SparSTAR, a training-free block-sparse attention method tailored to this setting. At each expensive scale and attention head, SparSTAR scores contiguous key blocks from the current query and key activations, retains required conditioning context, and executes the selected blocks through a forward-only sparse path. We analyze cross-scale consistency within a clip, pattern persistence across clip boundaries, and quality degradation as reuse spans increasingly distant scales. Across these analyses, important key blocks shift, showing that recomputing block selection at each target scale is more reliable than reusing a transferred mask. On 720p text-to-video and image-to-video generation, SparSTAR preserves every token and refinement scale while providing about a 1.6x end-to-end speedup and maintaining VBench and paired-output reconstruction fidelity close to dense InfinityStar.

Dense prediction tasks in surgical computer vision, such as segmentation and surgical zone prediction, can provide valuable guidance for laparoscopic and robotic surgery. However, these models often suffer from distribution shifts, as training datasets rarely cover the variability encountered during deployment, leading to poor generalization. We propose DenseTRF, a self-supervised representation adaptation framework based on texture-centric attention. Our method leverages slot attention to learn texture-aware representations that capture invariant visual structures. By adapting these representations to the target distribution without supervision, DenseTRF significantly improves robustness to domain shifts. The framework is implemented through conditioning dense prediction on slot attention and model merging strategies. Experiments across multiple surgical procedures demonstrate improved cross-distribution generalization in comparison to state-of-the-art segmentation models and test-distribution adaptation methods for dense prediction tasks.