CVPR 2026 Papers

Audio-driven human animation has attracted wide attention thanks to its practical applications. However, critical challenges remain in generating high-resolution, long-duration videos with consistent appearance and natural hand motions. Existing methods extend videos using overlapping motion frames but suffer from error accumulation, leading to identity drift, color shifts, and scene instability. Additionally, hand movements are poorly modeled, resulting in noticeable distortions and misalignment with the audio. In this work, we propose InfinityHuman, a coarse-to-fine framework that first generates audio-synchronized representations, then progressively refines them into high-resolution, long-duration videos using a pose-guided refiner. Since pose sequences are decoupled from appearance and resist temporal degradation, our pose-guided refiner employs stable poses and the initial frame as a visual anchor to reduce drift and improve lip synchronization. Moreover, to enhance semantic accuracy and gesture realism, we introduce a hand-specific reward mechanism trained with high-quality hand motion data. Experiments on the EMTD and HDTF datasets show that InfinityHuman achieves state-of-the-art performance in video quality, identity preservation, hand accuracy, and lip-sync. Ablation studies further confirm the effectiveness of each module. And our project page is available at https://infinityhuman.github.io/.

Vision-language models (VLMs) have achieved impressive performance across a wide range of multimodal reasoning tasks, but they often struggle to disentangle fine-grained visual attributes and reason about underlying causal relationships. In-context learning (ICL) offers a promising avenue for VLMs to adapt to new tasks, but its effectiveness critically depends on the selection of demonstration examples. Existing retrieval-augmented approaches typically rely on passive similarity-based retrieval, which tends to select correlated but non-causal examples, amplifying spurious associations and limiting model robustness. We introduce CIRCLES (Composed Image Retrieval for Causal Learning Example Selection), a novel framework that actively constructs demonstration sets by retrieving counterfactual-style examples through targeted, attribute-guided composed image retrieval. By incorporating counterfactual-style examples, CIRCLES enables VLMs to implicitly reason about the causal relations between attributes and outcomes, moving beyond superficial correlations and fostering more robust and grounded reasoning. Comprehensive experiments on four diverse datasets demonstrate that CIRCLES consistently outperforms existing methods across multiple architectures, especially on small-scale models, with pronounced gains under information scarcity. Furthermore, CIRCLES retrieves more diverse and causally informative examples, providing qualitative insights into how models leverage in-context demonstrations for improved reasoning. Our code is available at https://github.com/gzxiong/CIRCLES.

Universal Multimodal Embeddings (UMEs) aim to unify various modalities and tasks into a shared representation space. In recent years, this field has witnessed substantial progress driven by the development of Multimodal Large Language Models (MLLMs). However, a crucial capability, visual identity discrimination, remains underexplored in existing UME methods, despite its critical role in a wide range of tasks, including instance retrieval, re-identification, and identity preservation in AI-generated content. To bridge this gap, we propose a unified formulation for visual identity discrimination (VisID) and introduce MVEB (Multimodal Visual Identity Embedding Benchmark), a large-scale benchmark curated from both real-world and synthetic datasets to support evaluation and training. Furthermore, we present a simple yet effective learning framework that jointly optimizes general multimodal and visual identity representations through a carefully designed identity-aware sampling mechanism. Extensive experiments demonstrate that our approach successfully endows UMEs with strong identity discrimination capability and maintains competitive general multimodal performance. We believe this work not only illuminates a critical yet neglected capability, but also takes a step toward more holistic universal multimodal embeddings. Code and data are available at \href https://chrisclear3.github.io/MVEB MVEB .

Human sketches provide a compact and expressive form of visual communication, but their sparse structural cues, while capturing essential object structures, introduce ambiguity because a single sketch can correspond to multiple plausible images, making cross-domain alignment uncertain and unstable. Such ambiguity fundamentally limits sketch-based vision tasks that rely on precise sketch--image correspondence. To address this challenge, we introduce AmbiScore, a metric that quantifies the ambiguity of sketch-image pairs, and use Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) as a testbed to reveal how ambiguous supervision leads to performance collapse in existing methods. We further propose DisAmb (Disentangling Ambiguity), a framework that explicitly models and mitigates ambiguity through two components: (1) Elastic Matching, which adaptively adjusts supervision strength using AmbiScore, and (2) Purified Matching, which employs ambiguity-agnostic masks to disentangle structure and appearance via shape jigsaw and texture swapping. DisAmb establishes new benchmarks under high ambiguity and provides a robust, transferable supervisory signal for downstream sketch-guided tasks.

Despite the success of audio-visual large-language models (LLMs), they can produce plausible but ungrounded outputs, termed hallucination. Existing benchmarks focus on environmental sounds (e.g., dog barking) to indicate event occurrence. In contrast, human speech carries fundamentally different, rich semantics and temporal structures, yet it remains unexplored whether current models can accurately align speech content with corresponding visual signals. In this work, we show that speech content can induce hallucinations in audio-visual LLMs. To systematically study this, we introduce SVHalluc, the first comprehensive benchmark for evaluating speech-vision hallucination in audio-visual LLMs. Our benchmark diagnoses speech-vision hallucinations from two critical and complementary aspects: semantic and temporal. Experimental results demonstrate that state-of-the-art open-source audio-visual LLMs struggle with aligning speech content with corresponding visual signals, with a near-random accuracy on multiple tasks. In contrast, Gemini-2.5 Pro significantly outperforms the open-source models. Our analysis suggests that their failures stem from limited ability in cross-modality understanding, despite strong performance in single-modality perception. Our work uncovers a new and fundamental limitation of current audio-visual LLMs and highlights the need for speech-grounded video comprehension. Project page: https://chenshuang-zhang.github.io/projects/svhalluc/.

Multimodal Large Language Models (MLLMs) incorporating 3D geometry demonstrate significant power in 3D scene understanding. Their primary bottleneck, however, is the substantial computational burden associated with processing multi-view, lengthy visual token sequences. To surmount this challenge, we propose Merge3D, a geometry-aware token merging framework that integrates both 3D geometry and 2D semantic information. Conventional 2D compression methods, which rely solely on semantic signals, prove inadequate for 3D tasks, as they tend to discard spatially critical tokens and damage grounding performance. Merge3D bridges the modalities with a Semantic-Geometric Token Merger (SemGeo Merger): 2D attention is used to select semantically salient dominant tokens, while a hybrid 2D+3D similarity assigns and aggregates contextual tokens from spatially coherent 3D neighborhoods. This preserves 3D structural priors and inter-frame correspondences under aggressive compression. Merge3D achieves up to 70% visual token reduction and up to ~3xinference speedup, while retaining strong performance on 3D grounding, captioning, and spatial reasoning benchmarks such as Scan2Cap, CV-Bench, and BLINK.

Open-Set Object Detection (OSOD) enables recognition of novel categories beyond fixed classes but faces challenges in aligning text representations with complex visual concepts and the scarcity of image-text pairs for rare categories. This results in suboptimal performance in specialized domains or with complex objects. Recent visual-prompted methods partially address these issues but often involve complex multi-modal designs and multi-stage optimizations, prolonging the development cycle. Additionally, effective training strategies for data-driven OSOD models remain largely unexplored. To address these challenges, we propose PET-DINO, a universal detector supporting both text and visual prompts. Our Alignment-Friendly Visual Prompt Generation (AFVPG) module builds upon an advanced text-prompted detector, addressing the limitations of text representation guidance and reducing the development cycle. We introduce two prompt-enriched training strategies: Intra-Batch Parallel Prompting (IBP) at the iteration level and Dynamic Memory-Driven Prompting (DMD) at the overall training level. These strategies enable simultaneous modeling of multiple prompt routes, facilitating parallel alignment with diverse real-world usage scenarios. Comprehensive experiments demonstrate that PET-DINO exhibits competitive zero-shot object detection capabilities across various prompt-based detection protocols. These strengths can be attributed to inheritance-based philosophy and prompt-enriched training strategies, which play a critical role in building an effective generic object detector. Project page: https://fuweifuvtoo.github.io/pet-dino.

Visual Autoregressive (VAR) models have demonstrated competitive performance with diffusion models in image generation by adopting a "next-scale" prediction paradigm that significantly reduces inference steps. However, VAR's progressive multi-scale generation leads to severe memory overhead due to KV cache accumulation across all scales, limiting practical deployment. Existing solutions either require training and deploying multiple specialized models or sacrifice generation quality.We observe a critical scale-depth asymmetric dependency in VAR: small scales (low-resolution tokens) are highly sensitive to network depth and require deep layers to capture global semantic information, while large scales (high-resolution tokens) exhibit remarkable robustness to depth reduction.Motivated by this insight, we propose VARiant, a unified supernet framework that enables dynamic depth adjustment within a single model through parameter sharing. Our approach employs an even-spacing layer selection strategy to construct quality-preserving subnetworks, and introduces a dynamic-ratio progressive training strategy that gradually transitions from joint optimization (full network to subnetwork ratio 2:8) to subnetwork optimization (ratio 10:0), effectively resolving the inherent optimization conflicts between full network and subnetworks in supernet training.Extensive experiments on ImageNet demonstrate that our method achieves Pareto-optimal trade-offs between generation quality and inference efficiency: by using full depth (30 layers) for the first 7 scales and a 16-layer subnetwork (50% depth) for subsequent scales, we obtain 50% cache reduction and 1.8x inference speedup with minimal quality loss (FID increases by only 0.3).Unlike approaches requiring deployment of multiple models, our single-model solution eliminates deployment complexity, supports zero-cost runtime depth switching, and seamlessly integrates into standard transformer inference frameworks, making it highly practical for resource-constrained scenarios.

Self-supervised pre-training has driven rapid progress in foundation models for language, 2D images, and video, yet remains largely unexplored for learning 3D-aware representations from multi-view images. In this paper, we present E-RayZer, a self-supervised 3D vision model that learns geometrically grounded representations directly from unlabeled images. Unlike prior self-supervised methods such as RayZer, which infer 3D indirectly through latent-space view synthesis, E-RayZer operates directly in 3D space, performing self-supervised 3D reconstruction with Explicit geometry. This formulation eliminates shortcut solutions and yields representations that are 3D-aware. To ensure convergence and scalability, we introduce a fine-grained learning curriculum that organizes training from easy to hard samples and harmonizes heterogeneous data sources without any supervision. Experiments show that E-RayZer significantly outperforms RayZer on pose estimation and matches or sometimes surpasses fully supervised reconstruction models such as VGGT. Furthermore, its learned representations outperform leading visual pre-training models (e.g., DINOv3, CroCo v2, VideoMAE V2, and RayZer) on 3D downstream tasks, establishing E-RayZer as a promising paradigm for spatial visual pre-training.

Recent advances in video generation have been remarkable, enabling models to produce visually compelling videos with synchronized audio. While existing video generation benchmarks provide comprehensive metrics for visual quality, they lack convincing evaluations for audio-video generation, especially for models aiming to generate synchronized audio-video outputs. To address this gap, we introduce VABench, a comprehensive and multi-dimensional benchmark framework designed to systematically evaluate the capabilities of synchronous audio-video generation. VABench encompasses three primary task types: text-to-audio-video (T2AV), image-to-audio-video (I2AV), and stereo audio-video generation. It further establishes two major evaluation modules covering 15 dimensions. These dimensions specifically assess pairwise similarities (text-video, text-audio, video-audio), audio-video synchronization, lip-speech consistency, and carefully curated audio and video question-answering (QA) pairs, among others. Furthermore, VABench covers seven major content categories: animals, human sounds, music, environmental sounds, synchronous physical sounds, complex scenes, and virtual worlds. We provide a systematic analysis and visualization of the evaluation results, aiming to establish a new standard for assessing video generation models with synchronous audio capabilities and to promote the comprehensive advancement of the field.

Hierarchical image recognition aims to predict labels across a semantic taxonomy, typically assuming fine-grained annotations for every image. However, real-world supervision may appear at any level: a distant bird may only be labeled as "Bird", while a clear image allows "Bald eagle". To reflect this reality, we introduce free-grained hierarchical recognition, where training labels can appear at any level of a taxonomy, requiring consistent predictions under partial and mixed supervision. We construct benchmark datasets with varying label granularity and show that existing hierarchical methods degrade significantly in this setting. To address this, we propose simple yet effective approaches that leverage 1) semantic guidance from vision-language models and 2) visual structure through semi-supervised learning. Finally, we study free-grained inference, where the model adaptively selects prediction depth, enabling reliable coarse predictions when fine-grained ones are uncertain. Together, our task, datasets, and methods provide a practical step toward hierarchical recognition in real-world scenarios.

The rapid advances in deep learning have significantly enhanced the accuracy of multimodal 3D human pose estimation (HPE). However, the state-of-the-art (SOTA) HPE pipelines still rely on Transformers, whose quadratic complexity makes real-time processing for long sequences impractical. Mamba addresses this issue through selective state-space modeling, enabling efficient sequence processing without sacrificing representational power. Nevertheless, it struggles to capture complex spatial dependencies in multimodal settings. To bridge this gap, we propose VIMCAN, a hybrid architecture that combines the efficient sequence modeling of Mamba with the spatial reasoning of Cross-Attention, and performs robust visual-inertial fusion and human pose estimation between RGB keypoints and wearable IMU data. By leveraging Mamba's dynamic parameterization for temporal modeling and Attention for spatial dependency extraction, VIMCAN achieves superior accuracy, with mean per-joint position errors (MPJPE) of 17.2 mm on TotalCapture and 45.3 mm on 3DPW. VIMCAN outperforms prior Transformer-based and other SOTA approaches while supporting real-time inference at over 60 frames per second on consumer-grade hardware. The source code will be available on GitHub.

Inspired by how humans communicate spatial information, language-guided geo-localization has gained significant traction for its intuitive and practical value. Despite this progress, most methods still rely on a static, one-shot retrieval paradigm, which fails to handle the ambiguity and incompleteness inherent in real-world natural language descriptions. We propose a paradigm shift to reasoning retrieval and introduce Dialogue Place Recognition (DlgPR), which casts localization as an interactive, dialogue-driven reasoning process. To support this new task, we present DlgQuest-Cities, the first large-scale dialogue-based benchmark for place recognition, and a unified reasoning framework that couples a cross-modal multi-level retriever with an intelligent questioner, DQ-pilot. DQ-pilot is trained in a curriculum: supervised fine-tuning on a curated DQ-cities-20k subset followed by reinforcement refinement on a harder DQ-cities-10k split via GRPO. Two task-aligned metrics guide learning: a Discriminative Difficulty Index (DDI) for curriculum sampling and a Positional Retrieval Gain (PRG) reward that directly measures retrieval improvement induced by a question. Experiments show this reasoning-based approach significantly outperforms baselines. The code will be made publicly available upon acceptance.

We introduce VisualToolAgent (VisTA), a new reinforcement learning framework that empowers visual agents to dynamically explore, select, and compose tools from a diverse library based on empirical performance. Existing methods for tool-augmented visual reasoning either rely on training-free prompting or large-scale supervised fine-tuning; both lack active tool exploration and typically assume limited tool diversity, and fine-tuning methods additionally demand extensive human supervision. In contrast, VisTA leverages end-to-end reinforcement learning to iteratively refine sophisticated, query-specific tool selection strategies, guided solely by task outcomes. Leveraging reinforcement learning with verifiable rewards (RLVR), our framework enables an agent to autonomously discover effective tool-selection pathways without requiring explicit reasoning supervision. Experiments on the ChartQA, Geometry3K, MathVerse, and BlindTest benchmarks demonstrate that VisTA achieves significant performance gains over training-free and fine-tuning baselines, especially on out-of-distribution examples. These results highlight VisTA's ability to enhance generalization, adaptively utilize diverse tools, and pave the way for flexible, experience-driven visual reasoning systems.

While the most fundamental pretraining paradigm typically trains modality-specific models on their respective datasets, the Platonic Representation Hypothesis that representations eventually align across modalities as data and model scale suggests an intriguing possibility: large language models (LLMs) could be pretrained on visual corpora to reach parity with text-pretrained models, thereby expanding data sources to break the text-scaling bottlenecks, and leveraging richer visual cues for more comprehensive corpus understanding. This paper makes the first attempt to demonstrate the feasibility of this implication by introducing Masked Autoregressive Pretraining for Learning language intelligencE (MAPLE), a novel visual pretraining paradigm for LLMs that leverages raw document images to improve language intelligence. MAPLE is universal to integrate masked auto-regressive models with various LLM backbones, where the LLMs are incentivized to generate latent hypotheses for the masked regions based on the unmasked regions. We verify MAPLE in the domain of math reasoning with multiple LLM backbones and show that MAPLE consistently surpasses text-only pretraining relatively by at most 40.2% on average accuracy across four math reasoning benchmarks. Further analyses show that visually pretrained LLMs learn a shared latent space that aligns document visuals with text and exploits layout and structural cues, supporting visual pretraining as a feasible and scalable route to stronger language models.

Vision-Language Models (VLMs) often over-rely on linguistic priors even when images are provided, leading to object hallucinations. We revisit object-wise hallucination from the perspective of how visual evidence shapes the model's uncertainty. For each input, we measure decision uncertainty with and without the image, and define a Visual Evidence Sensitivity (VES) signal as the image-attributable change in entropy. Building on this signal, we introduce Visual Evidence Sensitivity Reinforcement Fine-Tuning (VES-RFT), a training-time reinforcement fine-tuning method that explicitly rewards reliance on correct visual evidence. We pair this continuous, annotation-free signal with a verifiable reward that enforces factual object correctness by automatically checking generated object mentions against the image, yielding a computable objective without human annotations. We optimize the dual objective using critic-free GRPO with KL regularization, requiring only parallel image and no-image passes during training while preserving single-pass inference. Across multiple VLM families and benchmarks, VES-RFT consistently suppresses object hallucinations and improves robustness under ambiguity. Specifically, on LLaVA-7B, VES-RFT reduces 12.8 and 1.8 on CHAIR_S/CHAIR_I of MS-COCO, and increases POPE accuracy by 4.92%. Extensive experiments indicate that turning uncertainty into a learnable reward, paired with verifiable correctness signals, provides a scalable mechanism for training-time hallucination mitigation and stronger visual grounding.

We address the problem of tactile localization, where the goal is to identify image regions that share the same material properties as a tactile input. Existing visuo-tactile methods rely on global alignment and thus fail to capture the fine-grained local correspondences required for this task. The challenge is amplified by existing datasets, which predominantly contain close-up, low-diversity images. We propose a model that learns local visuo-tactile alignment via dense cross-modal feature interactions, producing tactile saliency maps for touch-conditioned material segmentation. To overcome dataset constraints, we introduce: (i) in-the-wild multi-material scene images that expand visual diversity, and (ii) a material-diversity pairing strategy that aligns each tactile sample with visually varied yet tactilely consistent images, improving contextual localization and robustness to weak signals. We also construct two new tactile-grounded material segmentation datasets for quantitative evaluation. Experiments on both new and existing benchmarks show that our approach substantially outperforms prior visuo-tactile methods in tactile localization.

Although industrial inspection systems should be capable of recognizing unprecedented defects, most existing approaches operate under a closed-set assumption, which prevents them from detecting novel anomalies. While visual prompting offers a scalable alternative for industrial inspection, existing methods often suffer from prompt embedding collapse due to high intra-class variance and subtle inter-class differences. To resolve this, we propose UniSpector, which shifts the focus from naive prompt-to-region matching to the principled design of a semantically structured and transferable prompt topology. UniSpector employs the Spatial-Spectral Prompt Encoder to extract orientation-invariant, fine-grained representations; these serve as a solid basis for the Contrastive Prompt Encoder to explicitly regularize the prompt space into a semantically organized angular manifold. Additionally, Prompt-guided Query Selection generates adaptive object queries aligned with the prompt. We introduce Inspect Anything, the first benchmark for visual-prompt-based open-set defect localization, where UniSpector significantly outperforms baselines by at least 19.7% and 15.8% in AP50b and AP50m, respectively. These results show that our method enable a scalable, retraining-free inspection paradigm for continuously evolving industrial environments, while offering critical insights into the design of generic visual prompting.

When MLLMs fail at Science, Technology, Engineering, and Mathematics (STEM) visual reasoning, a fundamental question arises: is it due to perceptual deficiencies or reasoning limitations? Through systematic scaling analysis that independently scales perception and reasoning components, we uncover a critical insight: scaling perception consistently outperforms scaling reasoning. This reveals perception as the true lever limiting current STEM visual reasoning. Motivated by this insight, our work focuses on systematically enhancing the perception capabilities of MLLMs by establishing code as a powerful perceptual medium--executable code provides precise semantics that naturally align with the structured nature of STEM visuals. Specifically, we construct ICC-1M, a large-scale dataset comprising 1M Image-Caption-Code triplets that materializes this code-as-perception paradigm through two complementary approaches: (1) Code-Grounded Caption Generation treats executable code as ground truth for image captions, eliminating the hallucinations inherent in existing knowledge distillation methods; (2) STEM Image-to-Code Translation prompts models to generate reconstruction code, mitigating the ambiguity of natural language for perception enhancement. To validate this paradigm, we further introduce STEM2Code-Eval, a novel benchmark that directly evaluates visual perception in STEM domains. Unlike existing work relying on problem-solving accuracy as a proxy that only measures problem-relevant understanding, our benchmark requires comprehensive visual comprehension through executable code generation for image reconstruction, providing deterministic and verifiable assessment. Code is available at https://github.com/TongkunGuan/Qwen-CodePercept.