CVPR 2026 论文列表

One-stream Transformer-based trackers achieve advanced performance in visual object tracking suffer from significant computational overhead that hinders real-time deployment. While token pruning offers a path to efficiency, a critical limitation persists: no existing work performs pruning jointly across all three critical components--the search region, dynamic template, and static template. This isolation overlooks interdependencies, yielding suboptimal pruning and degraded accuracy. To address this, we introduce UTPTrack, a simple and Unified Token Pruning framework that, for the first time, jointly compresses all three components. UTPTrack employs an attention-guided, token type-aware strategy to holistically model redundancy, a design that seamlessly supports unified tracking across multi-modal and language-guided tasks within a single model. Comprehensive evaluations on 10 benchmarks demonstrate that UTPTrack achieves a new state-of-the-art in the accuracy-efficiency trade-off for pruning-based trackers, pruning 65.4% of vision tokens in RGB-based tracking and 67.5% in unified tracking while preserving 99.7% and 100.5% of baseline performance, respectively. This strong performance across both RGB and multimodal scenarios underlines its potential as a robust foundation for future research in efficient visual tracking.

Text-to-image (T2I) diffusion models such as SDXL and FLUX have achieved impressive photorealism, yet small-scale distortions remain pervasive in limbs, face, text and so on. Existing refinement approaches either perform costly iterative re-generation or rely on vision-language models (VLMs) with weak spatial grounding, leading to semantic drift and unreliable local edits. To close this gap, we propose **Agentic Retoucher**, a hierarchical decision-driven framework that reformulates post-generation correction as a human-like *perception-reasoning-action* loop.Specifically, we design (1) a **perception agent** that learns contextual saliency for fine-grained distortion localization under text-image consistency cues, (2) a **reasoning agent** that performs human-aligned inferential diagnosis via progressive preference alignment, and (3) an **action agent** that adaptively plans localized inpainting guided by user preference. This design integrates perceptual evidence, linguistic reasoning, and controllable correction into a unified, self-corrective decision process. To enable fine-grained supervision and quantitative evaluation, we further construct **GenBlemish-27K**, a dataset of 6K T2I images with 27K annotated artifact regions across 12 categories.Extensive experiments demonstrate that Agentic Retoucher consistently outperforms state-of-the-art methods in perceptual quality, distortion localization and human preference alignment, establishing a new paradigm for self-corrective and perceptually reliable T2I generation.

Self-consistency has proven to be an effective technique for improving LLM performance on natural language reasoning tasks in a lightweight, unsupervised manner. In this work, we study how to adapt self-consistency to visual domains. Specifically, we consider the generation and verification of LLM-produced motion graphics trajectories. Given a prompt (e.g., "Move the circle in a spiral path"), we first sample diverse motion trajectories from an LLM, and then identify groups of consistent trajectories via clustering. Our key insight is to model the family of shapes associated with a prompt as a prototype trajectory paired with a group of geometric transformations (e.g., rigid, similarity, and affine). Two trajectories can then be considered consistent if one can be transformed into the other under the warps allowable by the transformation group. We propose an algorithm that automatically recovers a shape family, using hierarchical relationships between a set of candidate transformation groups. Our approach improves the accuracy of LLM-based trajectory generation by 4-6%. We further extend our method to support verification, observing 11% precision gains over VLM baselines. Our code and dataset are available at https://majiaju.io/trajectory-self-consistency

Although reinforcement learning (RL) has significantly advanced reasoning capabilities in large multimodal language models (MLLMs), its efficacy remains limited for lightweight models essential for edge deployments. To address this issue, we leverage causal analysis and experiment to reveal the underlying phenomenon of perceptual bias, demonstrating that RL-based fine-tuning compels lightweight models to preferentially adopt perceptual shortcuts induced by data biases, rather than developing genuine reasoning abilities. Motivated by this insight, we propose VideoThinker, a causal-inspired framework that cultivates robust reasoning in lightweight models through a two-stage debiasing process. First, the Bias Aware Training stage forges a dedicated "bias model" to embody these shortcut behaviors. Then, the Causal Debiasing Policy Optimization (CDPO) algorithm fine-tunes the primary model, employing an innovative repulsive objective to actively push it away from the bias model's flawed logic while simultaneously pulling it toward correct, generalizable solutions. Our model, VideoThinker-R1, establishes a new state-of-the-art in video reasoning efficiency. For same-scale comparison, requiring no Supervised Fine-Tuning (SFT) and using only 1% of the training data for RL, it surpasses VideoRFT-3B with a 3.2% average gain on widely-used benchmarks and a 7% lead on VideoMME. For cross-scale comparison, it outperforms the larger Video-UTR-7B model on multiple benchmarks, including a 2.1% gain on MVBench and a 3.8% gain on TempCompass. Code is available at https://github.com/falonss703/VideoThinker.

Vision-language models (VLMs) have achieved remarkable success across numerous domains, yet they lag significantly in animal behavior understanding due to severe data scarcity. Annotated animal behavior videos are prohibitively expensive and time-consuming to collect, requiring domain expertise and controlled observation conditions. To address this challenge, we leverage structured domain knowledge as an inductive bias from the Neuro Behavior Ontology (NBO), which provides professional annotations, hierarchical behavior structures, and comprehensive semantic coverage. We construct AnimalBand, an NBO-consistent dataset integrating 74,671 videos across multiple species and behaviors with semantic standardization and extended knowledge. Based on this resource, we present EthoCLIP, an ontology-enhanced vision-language contrastive learning framework that embeds ontology semantics through an ontology-aware graph module to capture hierarchical relationships among behaviors and learn structured semantic dependencies. Incorporating ontological information reduces reliance on purely data-driven learning, thereby alleviating needs for large-scale datasets. Extensive experiments validate both our dataset and method. Results demonstrate that EthoCLIP pretrained on AnimalBand substantially improves behavior recognition accuracy and transfer learning performance across diverse benchmarks, confirming that ontology-driven semantic enrichment effectively mitigates data scarcity in animal behavior understanding. Our data and code will be released at https://github.com/PRIS-CV/AnimalBand.

In multimodal large language models (MLLMs), the surge of visual tokens significantly increases the inference time and computational overhead, making them impractical for real-time or resource-constrained applications.Visual token pruning is a promising strategy for reducing the cost of MLLM inference by removing redundant visual tokens.Existing researches usually assume that all attention heads contribute equally to the visual interpretation.However, our study reveals that different heads may capture distinct visual semantics and inherently play distinct roles in visual processing.In light of this observation, we propose HAWK, a head importance-aware visual token pruning method that perceives the varying importance of attention heads in visual tasks to maximize the retention of crucial tokens.By leveraging head importance weights and text-guided attention to assess visual token significance, HAWK effectively retains task-relevant visual tokens while removing redundant ones.The proposed HAWK is entirely training-free and can be seamlessly applied to various MLLMs.Extensive experiments on multiple mainstream vision-language benchmarks demonstrate that HAWK achieves state-of-the-art accuracy. When applied to Qwen2.5-VL, HAWK retains 96.0% of the original accuracy after pruning 80.2% of the visual tokens. Additionally, it reduces end-to-end latency to 74.4% of the original and further decreases GPU memory usage across the tested models.

Despite recent advances, Vision Language Models (VLMs) still struggle to grasp the dynamics of the world. We note that the ability to reason about a 4D scene, challenging in itself, is further complicated by two factors. First, VLMs observe motion indirectly via its projection onto 2D images. Second, existing datasets fail to disentangle object and camera motion. To address these challenges, we present a QA generation pipeline that focuses on motion-related scene understanding. We take particular care of the entanglement of camera and object motion by casting tracking in both the traditional way and in a novel, fixed reference system, dubbed True-Motion Tracking, which provides an intuitive description of motion. From this pipeline, we generate a large-scale training dataset of 400K samples, 4DP-QA (4D Perception QA), and a 2.2K-sample benchmark, 4DP-QA-Bench. Training existing models on our dataset yields performance improvements on an external benchmark, validating the effectiveness of our method.

Document understanding is a long-standing practical task. Vision-Language Models (VLMs) have gradually become a primary approach in this domain, demonstrating effective performance on single-page tasks. However, their effectiveness diminishes when handling long documents. In such scenarios, clues are often scattered across multiple pages and modalities, and redundancy from lengthy inputs can impair the model's judgment. While retrieval-augmented generation mitigates this issue by filtering for question-relevant content, the retrieved results still contain substantial redundancy. To address these limitations, we propose SLEUTH, a multi-agent framework. Concretely, SLEUTH orchestrates a retriever and four collaborative agents in a coarse-to-fine process. The framework identifies key textual and visual clues within the retrieved pages, filters for salient visual evidence such as tables and charts, and analyzes the query to devise a reasoning strategy. It ultimately synthesizes a distilled, evidence-dense multimodal context to generate the final prediction. SLEUTH is model-agnostic and scalable. When paired with advanced VLM backbones, it consistently improves performance on multiple long-document benchmarks, achieving SOTA results. Ablation studies verify each module's effectiveness and confirm the benefits of our hierarchical refinement paradigm.

Model editing aims to update knowledge to add new concepts and change relevant information without retraining. Lifelong editing is a challenging task, prone to disrupting previously learned concepts, especially for Vision Language Models (VLMs), because sequential edits can lead to degraded reasoning and cross-modal misalignment. Existing VLM knowledge editing methods based on gated adapters, activation edits, and parameter merging techniques address catastrophic forgetting seen in full fine-tuning; however, they still operate in the shared representation space of the VLM, where concepts are entangled, so edits interfere with other non-relevant concepts. We hypothesize that this instability persists because current methods algorithmically control edits via optimization rather than structurally separating knowledge. We introduce Dynamic Subspace Concept Alignment (DSCA) which by design mitigates this limitation by decomposing the representation space into a set of orthogonal semantic subspaces and proposing edits only in those transformed spaces. These subspaces are obtained through incremental clustering and PCA on joint vision-language representations. This process structurally isolates concepts, enabling precise, non-interfering edits by turning isolation from a soft training objective into an architectural property. The surgical edits are guided by a multi-term loss function for maintaining task fidelity, edit locality, and cross-modal alignment. With the base model frozen, our method achieves 98% single-edit success, remains over 95% after 1,000 sequential edits, lowers hallucination by 3-5%, and achieves the best backward transfer (BWT) scores on continual instruction-tuning benchmarks. Extensive experiments demonstrate DSCA's state-of-the-art stability and knowledge retention capability in continual lifelong editing across various datasets and benchmarks.

The temporal evolution patterns of surface spatial structures constitute a central concern within the field of intelligent remote sensing interpretation.However, constrained by the availability of only two temporal phases, modeling sparse spatio-temporal change processes to effectively interpret surface alterations remains a core challenge in intelligent remote sensing analysis. To address this, this paper proposes SpikeAdapter, a lightweight enhancement framework. This framework comprises Geo-Spike Interpolation (GSI-P), an spiking neural network (SNN) feature extractor, and the spatio-temporal fusion module STSpikeFuse. Inspired by the brain's perceptual response to new and fading stimuli, the core GSI-P module transforms bi-temporal radiometric differences into sparse spike sequences with time-to-first-spike characteristics.Then we use a feature extractor of SNN to capture dynamic variations of land-surface targets. The STSpkeFuse module employs a learnable temporal decay mechanism to adaptively fuse the SNN features with the semantic representations. This representations are generated by a traditional artificial neural network (ANN) backbone.Extensive experiments on change detection datasets demonstrate that SpikeAdapter effectively enhances temporal awareness and interpretability.

The rapid advancement of Large Multimodal Models (LMMs) for 2D images and videos has sparked interest in extending these models to 3D scenes, with the goal of human-like visual-spatial intelligence. However, achieving deep spatial understanding comparable to human capabilities remains challenging for both model design and data acquisition. Existing methods often rely on external depth sensors for geometry capture or off-the-shelf algorithms for pre-constructing 3D maps, which limits their scalability.In this work, we introduce VLM-3R, a framework for Vision-Language Models that couples 3D reconstructive instruction tuning with scalable training data curation and a new benchmark for temporal reasoning. Specifically, VLM-3R processes monocular video frames with a geometry encoder that derives implicit 3D tokens representing scene context (spatial tokens) and camera motion (view tokens). In parallel, we build a scalable data creation pipeline with over 200K 3D reconstructive instruction-tuning question-answer pairs. To evaluate temporal reasoning, we further introduce the Vision-Spatial-Temporal Intelligence benchmark (VSTI-Bench), which contains over 138.6K question-answer pairs across five distinct tasks focused on evolving spatial relationships. Extensive experiments show that VLM-3R supports robust visual-spatial reasoning and improves the understanding of temporal 3D context changes, enabling monocular 3D spatial assistance and embodied reasoning.

We present a dataset for force-grounded, cross-view articulated manipulation that couples what is seen with what is done and what is felt during real human interaction. The dataset contains 3048 sequences across 381 articulated objects in 38 environments. Each object is operated in four embodiments - (i) human hand, (ii) human hand with a wrist-mounted camera, (iii) handheld UMI gripper, and (iv) a custom Hoi! gripper, where the tool embodiment provides end-effector forces and tactile sensing. Our dataset offers a holistic view of interaction understanding from video, enabling researchers to evaluate how well methods transfer between human and robotic viewpoints, but also investigate underexplored modalities such as interaction forces. The Project Website can be found at https://hoi-dataset.ethz.ch.

Recent text-to-image (T2I) diffusion models achieve remarkable realism, yet faithful prompt-image alignment remains challenging, particularly for complex prompts with multiple objects, relations, and fine-grained attributes. Existing training-free inference-time scaling methods rely on fixed iteration budgets that cannot adapt to prompt difficulty, while reflection-tuned models require carefully curated reflection datasets and extensive joint fine-tuning of diffusion and vision-language models, often overfitting to reflection paths data and lacking transferability across models. We introduce RAISE (Requirement-Adaptive Self-Improving Evolution), a training-free, requirement-driven evolutionary framework for adaptive T2I generation. RAISE formulates image generation as a requirement-driven adaptive scaling process, evolving a population of candidates at inference time through a diverse set of refinement actions--including prompt rewriting, noise resampling, and instructional editing. Each generation is verified against a structured checklist of requirements, enabling the system to dynamically identify unsatisfied items and allocate further computation only where needed. This achieves adaptive test-time scaling that aligns computational effort with semantic query complexity. On GenEval and DrawBench, RAISE attains state-of-the-art alignment (0.94 overall GenEval) while incurring fewer generated samples (reduced by 30-40%) and VLM calls (reduced by 80%) than prior scaling and reflection-tuned baselines, demonstrating efficient, generalizable, and model-agnostic multi-round self-improvement. Code is available at https://github.com/LiyaoJiang1998/RAISE.

To enhance the precision of cancer prognosis, recent research has increasingly focused on multimodal survival methods by integrating genomic data and histology images. However, current approaches overlook the fact that the proteome serves as an intermediate layer bridging genomic alterations and histopathological features while providing complementary biological information essential for survival prediction. This biological reality exposes another architectural limitation: existing integrative analysis studies fuse these heterogeneous data sources in a flat manner that fails to capture their inherent biological hierarchy. To address these limitations, we propose HFGPI, a hierarchical fusion framework that models the biological progression from genes to proteins to histology images from a systems biology perspective. Specifically, we introduce Molecular Tokenizer, a molecular encoding strategy that integrates identity embeddings with expression profiles to construct biologically informed representations for genes and proteins. We then develop Gene-Regulated Protein Fusion (GRPF), which employs graph-aware cross-attention with structure-preserving alignment to explicitly model gene-protein regulatory relationships and generate gene-regulated protein representations. Additionally, we propose Protein-Guided Hypergraph Learning (PGHL), which establishes associations between proteins and image patches, leveraging hypergraph convolution to capture higher-order protein-morphology relationships. The final features are progressively fused across hierarchical layers to achieve precise survival outcome prediction. Extensive experiments on five benchmark datasets demonstrate the superiority of HFGPI over state-of-the-art methods.

Recent advances in multimodal large language models (MLLMs) have shown impressive progress in integrating visual and linguistic understanding. However, most existing MLLMs inject visual information into the input space of large language models (LLMs), which substantially increases context length and computational overhead, while often disrupting pretrained linguistic priors by forcing the LLM to optimize on vision-dominant multimodal sequences. In this work, we propose a rotation-based vision injection paradigm that aligns visual information with the parameter space of LLMs. Visual semantics are encoded as rotation matrices and applied directly to the pretrained parameters. This parameter-space injection eliminates the need for long input sequences, thus avoiding the quadratic computational overhead inherent in input-space injection. Besides, it preserves the linguistic competence of the LLM by maintaining the intrinsic geometric structure of the pretrained parameters. Building upon this paradigm, we develop ROSE, a 7B MLLM that achieves fine-grained vision-language alignment with remarkable computational efficiency. Extensive experiments across 12 multimodal benchmarks show that ROSE delivers superior or competitive performance compared with leading models.At comparable accuracy, ROSE reduces FLOPs by 80.7% and inference latency by 56.4% relative to Qwen2.5-VL-7B, demonstrating the effectiveness and scalability. The code and model weights will be publicly released.

Recent adapter-based CLIP tuning (e.g., Tip-Adapter) is a strong few-shot learner, achieving efficiency by caching support features for fast prototype matching. However, these methods rely on global uni-modal feature vectors, overlooking fine-grained patch relations and their structural alignment with class text. To bridge this gap without incurring inference costs, we introduce a novel asymmetric training-only framework. Instead of altering the lightweight adapter, we construct a high-capacity auxiliary Heterogeneous Graph Teacher that operates solely during training. This teacher (i) integrates multi-scale visual patches and text prompts into a unified graph, (ii) performs deep cross-modal reasoning via a Modality-aware Graph Transformer (MGT), and (iii) applies discriminative node filtering to extract high-fidelity class features. Crucially, we employ a cache-aware dual-objective strategy to supervise this relational knowledge directly into the Tip-Adapter's key-value cache, effectively upgrading the prototypes while the graph teacher is discarded at test time. Thus, inference remains identical to Tip-Adapter with zero extra latency or memory. Across standard 1-16-shot benchmarks, our method consistently establishes a new state-of-the-art. Ablations confirm that the auxiliary graph supervision, text-guided reasoning, and node filtering are the essential ingredients for robust few-shot adaptation.

Image Super-Resolution (SR) aims to reconstruct high-resolution images from degraded low-resolution inputs. While diffusion-based SR methods offer powerful generative capabilities, their performance heavily depends on how semantic priors are structured and integrated into the generation process. Existing approaches often rely on entangled or coarse-grained priors that mix global layout with local details, or conflate structural and textural cues, thereby limiting semantic controllability and interpretability. In this work, we propose DTPSR, a novel diffusion-based SR framework that introduces disentangled textual priors along two complementary dimensions: spatial hierarchy (global vs. local) and frequency semantics (low- vs. high-frequency). By explicitly separating these priors, DTPSR enables the model to simultaneously capture scene-level structure and object-specific details with frequency-aware semantic guidance. The corresponding embeddings are injected via specialized cross-attention modules, forming a progressive generation pipeline that reflects the semantic granularity of visual content--from global layout to fine-grained textures. To support this paradigm, we construct DisText-SR, a large-scale dataset containing approximately 95,000 image-text pairs with carefully disentangled global, low-frequency, and high-frequency descriptions. To further enhance controllability and consistency, we adopt a multi-branch classifier-free guidance strategy with frequency-aware negative prompts to suppress hallucinations and semantic drift. Extensive experiments on synthetic and real-world benchmarks show that DTPSR achieves high perceptual quality, competitive fidelity, and strong generalization across diverse degradation scenarios.

Diffusion transformers have recently delivered strong text-to-image generation around 1K resolution, but we show that extending them to native 4K across diverse aspect ratios exposes a tightly coupled failure mode spanning positional encoding, VAE compression, and optimization. Tackling any of these factors in isolation leaves substantial quality on the table. We therefore take a data--model co-design view and introduce UltraFlux, a Flux-based DiT trained natively at 4K on MultiAspect-4K-1M, a 1M-image 4K corpus with controlled multi-AR coverage, bilingual captions, and rich VLM/IQA metadata for resolution- and AR-aware sampling. On the model side, UltraFlux couples (i) Resonance 2D RoPE with YaRN for training-window-, frequency-, and AR-aware positional encoding at 4K; (ii) a simple, non-adversarial VAE post-training scheme that improves 4K reconstruction fidelity; (iii) an SNR-Aware Huber Wavelet objective that rebalances gradients across timesteps and frequency bands; and (iv) a Stage-wise Aesthetic Curriculum Learning strategy that concentrates high-aesthetic supervision on high-noise steps governed by the model prior. Together, these components yield a stable, detail-preserving 4K DiT that generalizes across wide, square, and tall ARs. On the Aesthetic-Eval@4096 benchmark and multi-AR 4K settings, UltraFlux consistently outperforms strong open-source baselines across fidelity, aesthetic, and alignment metrics, and--with a LLM prompt refiner--matches or surpasses the proprietary Seedream 4.0.

Forecasting fetal growth from sequential ultrasound examinations is essential for personalized prenatal care. Existing medical vision-language models (MLLMs) are limited to single-phase/organ evaluations and qualitative reasoning, neglecting longitudinal history and precise continuous biometric values. To address this gap, we introduce the novel task of multi-phase fetal growth forecasting and report generation. To support this task, we first present GrowthFetus, the interesting multi-phase, multi-organ fetal ultrasound dataset to date, containing 9,280 examinations from 2,000 fetuses. Based on this dataset, we propose F^2-Assist, a unified MLLM framework with three key components: (i) a Cross-Phase Organ Alignment module for for heterogeneous multi-organ feature fusion across phases, (ii) a History-Aware Temporal Encoding module for modeling irregular temporal dynamics, and (iii) a Growth Parameter Adapter that encodes continuous biometric values as differentiable tokens for numerically precise reasoning. Extensive experiments show that F^2-Assist achieves temporally coherent predictions and clinically consistent reports, significantly outperforming state-of-the-art MLLMs. Our study establishes a practical framework for longitudinal ultrasound analysis, bridging growth forecasting and report generation in a unified model.