CVPR 2026 论文列表

Large Vision-Language Models (LVLMs) often suffer from object hallucination, generating objects that are absent from the image. Prior work largely attributes this to insufficient visual attention. However, in this work, we are surprised to find that both real and hallucinated objects receive equally strong visual attention in the model's mid-to-late layers. This indicates that the key issue may not be how much the model attends, but **what it attends to and why**. To this end, we decode the visual features of high-attention regions using Logit Lens, and observe that high-attention regions corresponding to real objects can be correctly decoded to the target object token, whereas those for hallucinated objects cannot. Building on this, we identify two distinct hallucination mechanisms: **(i) visual uncertainty**, triggered by semantically similar or confusable regions, masking these regions eliminates the hallucination. **(ii) contextual prior**, triggered by strong co-occurrence priors, even when the initially attended region is masked, the hallucination persists and attention drifts to other regions. Based on these findings, we propose a simple yet effective training-free **Detect-Mitigate framework** comprising a Logit-Lens Consistency Check to detect hallucination and targeted remedies: High-Attention Regions Masking (HARM) for visual uncertainty hallucination, and Visual Evidence Enhanced Decoding (VEED) for contextual prior hallucination, which leverages genuine visual evidence to suppress erroneous priors. Our approach achieves state-of-the-art results on multiple hallucination benchmarks.

Transforming sparse, partial pixel sketches from diverse media into complete, editable vector drawings is essential yet underexplored in digital creation. Prior methods either generate from scratch or inpaint local gaps without predicting global structure, leading to coarse contours and limited detail. To address this, we introduce SketchRevive, a two-stage framework for fine-grained pixel-to-vector sketch completion that couples diffusion-based pixel completion with MLLM-driven refinement and vectorization to produce coherent, detail-faithful SVG results. Specifically, we first construct a practical benchmark by augmenting stroke-annotated sketches from paper and whiteboards. Stage I trains a diffusion model with a line-distribution head to predict per-pixel stroke presence, producing structurally and visually consistent completions. Stage II fine-tunes an MLLM for structure-aware SVG vectorization with iterative refinement, optimized by instance-level stroke attribute similarities. To align key clues, e.g., spatial structure, appearance details across both stages, we introduce a diffusion-prior aggregated encoding module by injecting multi-scale UNet features from Stage I into the MLLM's visual embeddings and using line prediction logits for token compression to prioritize informative tokens. Experiments indicate that SketchRevive completes topology-coherent vector outputs with high fidelity and recognizability while preserving user intent, suitable for interactive creation and artistic design.

We present ReMatch, a framework that leverages the generative strength of MLLMs for multimodal retrieval. Previous approaches treated an MLLM as a simple encoder, ignoring its generative nature, and under-utilising its compositional reasoning and world knowledge. We train the embedding MLLM end-to-end with a chat-style generative matching stage. The matching stage uses the same MLLM to autoregressively decide relevance from multi-view inputs, including both raw data and its own projected embeddings for each query and document. It provides instance-wise discrimination supervision that complements a standard contrastive loss, offering stronger gradients on hard negatives and preserving the compositional strengths of the original MLLM. To obtain semantically richer multimodal embeddings, we use multiple learnable tokens to augment each input, generating fine-grained contextual, mutually orthogonal embeddings with low inference cost. Leveraging our established high-performance baseline, we assemble the ideas mentioned above into a powerful training recipe and achieve a new state-of-the-art on the Massive Multimodal Embedding Benchmark(MMEB). Our experiments show particularly strong zero-shot generalization results on five datasets, highlighting the robustness and transferability of ReMatch.

Evaluations of image compression performance which include human preferences have generally found that naive distortion functions such as MSE are insufficiently aligned to human perception.In order to align compression models to human perception, prior work has employed differentiable perceptual losses consisting of neural networks calibrated on large-scale datasets of human psycho-visual judgments. We show that, surprisingly, state-of-the-art vision-language models (VLMs) can replicate binary human two-alternative forced choice (2AFC) judgments zero-shot when asked to reason about the differences between pairs of images. Motivated to exploit the powerful zero-shot visual reasoning capabilities of VLMs, we propose Vision Language Models for Image Compression (VLIC), a diffusion-based image compression system designed to be post-trained with binary VLM judgments. VLIC leverages existing techniques for diffusion model post-training with preferences, rather than distilling the VLM judgments into a separate perceptual loss network. We show that calibrating this system on VLM judgments produces competitive or state-of-the-art performance on human-aligned visual compression depending on the dataset, according to perceptual metrics and large-scale user studies. We additionally conduct an extensive analysis of the VLM-based reward design and training procedure and share important insights.

The rapid evolution of generative AI, including such models as Sora, has intensified the threat of video misinformation. A critical challenge in detecting these AI-generated video misinformation lies in a fundamental disconnect between existing datasets and practical deception tactics. Current datasets often disrupt cross-modal consistency through editing techniques, resulting in unrealistic and easily detectable artifacts. By contrast, generative video misinformation strives for semantic consistency across modalities to remain realism. To address this gap, we introduce RAVM: the first Realistic AI-Generated Video Misinformation Detection Dataset. Unlike existing Video Misinformation Detection (VMD) datasets that are limited to single-source manipulations, RAVM encompasses multiple manipulation sources--Claim, Video, Audio, and Cross-Modal Manipulation--each incorporating diverse manipulation techniques to generate realistic AI-generated video misinformation. To achieve this, we introduce an agent-driven framework for generating realistic video misinformation. Furthermore, we propose an IEEG model that represents multimodal evidence, fact-checking results, and their dependencies as an evidence graph for interpretable detection of AI-generated video misinformation. Extensive experiments on RAVM reveal the vulnerability of existing Multimodal Large Language Models (MLLMs) in detecting AI-generated video misinformation, while the proposed IEEG achieves state-of-the-art performance on RAVM. The dataset is publicly available at: https://gitee.com/VR_NAVE/ravm

Humans learn by observing, interacting with environments, and internalizing physics and causality. We explore whether agents can similarly acquire human-like reasoning through interaction and experience. To study this, we introduce a Game-to-Unseen (G2U) benchmark of 1,000+ heterogeneous games that exhibit significant visual domain gaps. Existing approaches, including VLMs and world models, struggle with underlying physics and causality due to overfitting on visual details. VLM/VLA agents reason but lack look-ahead in interactive settings, while world models imagine but imitate visual patterns rather than analyze physics and causality. We therefore propose IPR (Interactive Physical Reasoner), using world-model rollouts to score and reinforce a VLM's policy, and introduce PhysCode, a physics-centric action code aligning semantic intent with dynamics to provide a shared action space for prediction and reasoning. Pretrained on 1,000+ games, IPR performs robustly on levels from primitive intuition to goal-driven reasoning, and even surpasses GPT-5 overall. We find that performance improves with more training games and interaction steps, and that the model also zero-shot transfers to unseen games. These results support physics-centric interaction as a path to steadily improving physical reasoning. Further demos and details can be found at https://mybearyzhang.github.io/ipr-1.

Scaling vision foundation models is constrained by the quadratic complexity of self-attention. Although subquadratic attention alternatives like linear attention variants and state-space models successfully reduce the model complexity, they typically serialize images into 1D token sequences, compromising spatial coherence and efficiency. Generalized Spatial Propagation Networks (GSPN) offer a linear-time alternative that propagates context directly on the 2D grid via line-scan propagation and removes positional embeddings, yet the original design hits GPU-scaling limits: growing batch/channels saturate SM concurrency, serializing scans, and spiking latency. We introduce Compact GSPN (C-GSPN), a ViT block that compresses the propagation space to preserve accuracy while cutting propagation latency by nearly 10x. We further improve efficiency with lightweight projections and fused CUDA kernels. To enable large-scale pretraining, we adopta two-stage cross-operator distillation strategy that combines layer-wise supervision with end-to-end alignment. In a representative 1K configuration (batch 32, C=1152), C-GSPN achieves up to 2x speedup, maintains competitive zero-shot accuracy, and improves segmentation by +2.1%. Extensive experiments and ablations show that the proposed compression and two-stage distillation are criticalfor strong transfer while substantially reducing compute, enabling the first extension of a subquadratic operator to foundation-scale (CLIP-style) vision pretraining.

User Interface (UI) display defect detection poses challenges far beyond UI understanding, requiring fine-grained element boundary understanding, missing-content detection, and reasoning about sequential interface semantic consistency. However, the capabilities of multimodal large language models (MLLMs) and vision-language models (VLMs) for detecting UI defects in realistic, complex interfaces have not been systematically validated. To fill this gap, we present UI-Lens, the first multi-dimensional UI display detection benchmark for Chinese-language UI scenarios. The dataset comprises 4,759 pages meticulously annotated by design experts, covering six core display defect categories. We conduct a systematic evaluation of 10 mainstream models (8 closed-source, 2 open-source). Results show clear shortcomings in current models: for tasks requiring fine-grained element boundary understanding, performance is near random, with task-average F1 scores of 20.36% and 31.21% on Text Overflow and Container Overlap, respectively; for sequential interface semantic consistency (e.g., Text Inconsistency), the task-average F1 score is only 10.61%, indicating severe underperformance. We release UI-Lens to catalyze research toward more robust UI display defect detection with fine-grained boundary awareness in realistic, complex interfaces.

With the rapid development of large multimodal models, reliable judge and critic models have become essential for open-ended evaluation and preference alignment, providing pairwise preferences, numerical scores, and explanatory justifications for assessing model-generated responses. However, existing critics are primarily trained in general visual domains such as captioning or image question answering, leaving physical AI tasks involving perception, causal reasoning, and planning largely underexplored. We introduce PhyCritic, a multimodal critic model optimized for physical AI through a two-stage RLVR pipeline: a physical skill warmup stage that enhances physically oriented perception and reasoning, followed by self-referential critic finetuning, where the critic generates its own prediction as an internal reference before judging candidate responses, improving judgment stability and physical correctness. Across both physical and general-purpose multimodal judge benchmarks, PhyCritic achieves strong performance gains over open-source baselines and, when applied as a policy model, further improves perception and reasoning in physically grounded tasks.

Adapting image-pretrained backbones to video typically relies on time-domain adapters tuned to a single temporal scale. Our experiments show that these modules pick up static image cues and very fast flicker changes, while overlooking medium-speed motion. Capturing dynamics across multiple time-scales is, however, crucial for fine-grained temporal analysis (i.e., opening vs. closing bottle).To address this, we introduce Frame2Freq -- a family of frequency-aware adapters that perform spectral encoding during image-to-video adaptation of pretrained Vision Foundation Models (VFMs), improving fine-grained action recognition. Frame2Freq uses Fast Fourier Transform (FFT) along time and learns frequency-band specific embeddings that adaptively highlight the most discriminative frequency ranges. Across five fine-grained activity recognition datasets, Frame2Freq outperforms prior PEFT methods and even surpasses fully fine-tuned models on four of them. These results provide encouraging evidence, that frequency analysis methods are a powerful tool for modeling temporal dynamics in image-to-video transfer.

Vision Language Models (VLMs) exhibit a fundamental semantic-to-geometric gap in spatial reasoning: they excel at qualitative semantic inference but their reasoning operates within a lossy semantic space, misaligned with high-fidelity geometry. Current paradigms fail to bridge this gap. Training-based methods suffer from an "oracle paradox," learning flawed spatial logic from imperfect oracles. Tool-integrated methods constrain the final computation but critically leave the VLM's planning process unconstrained, resulting in geometrically flawed plans. In this work, we propose Geometrically-Constrained Agent (GCA), a training-free agentic paradigm that resolves this gap by introducing a formal task constraint. Specifically, we strategically decouples the VLM's role into two stages. First, acting as a semantic analyst, the VLM translates the user's ambiguous query into the formal, verifiable task constraint, which defines the reference frame and objective. Second, acting as a task solver, the VLM generates and executes tool calls strictly within the deterministic bounds defined by the constraint. This geometrically-constrained strategy successfully resolve the semantic-to-geometric gap, yielding a robust and verifiable reasoning pathway for complex spatial tasks. Comprehensive experiments demonstrate that GCA achieves SOTA performance on multiple spatial reasoning benchmarks, surpassing existing training-based and tool-integrated methods by 27%.

Creativity is a complex phenomenon. When it comes to representing and assessing creativity, treating it as a single undifferentiated quantity would appear naive and under-whelming. In this work, we learn the first type-specific creativity reward model, coined CREward, which spans three creativity "axes," geometry, material, and texture, to allow us to view creativity through the lens of the image formation pipeline. To build our reward model, we first conduct a human benchmark evaluation to capture human perception of creativity for each type across various creative images. We then analyze the correlation between human judgments and predictions by large vision-language models (LVLMs), confirming that LVLMs exhibit strong alignment with human perception. Building on this observation, we collect LVLM-generated labels to train our CREward model that is applicable to both evaluation and generation of creative images. We explore three applications of CREward: creativity assessment, explainable creativity, and creative sample acquisition for both human design inspiration and guiding creative generation through low-rank adaptation.

Direct Preference Optimization has achieved remarkable success in aligning diffusion models with human feedback. However, existing methods heavily rely on image-level preferences, which suffer from sparse rewards in the spatial dimension. This creates a fundamental misalignment: while an image may be globally preferred, it can contain locally inferior instances. Applying the same positive preference to these areas thus unfairly credits distracting regions while penalizing informative ones, leading to suboptimal performance and inefficient learning. To resolve this issue, we propose IAPO, an Instance-Aware Preference Optimization that introduces instance-level credit assignment to advance alignment from image-level to instance-level. We first construct a high-quality instance-level preference dataset by automatically identifying and relabeling corresponding instances in image pairs using vision-language models and object detection models. Leveraging this fine-grained dataset, we design a novel instance alignment loss with a dynamic reweighting mask that modulates instance-level loss within annotated bounding boxes, suppressing distractors to enforce fine-grained human preference alignment. Extensive experiments demonstrate that our method not only achieves state-of-the-art performance in multiple benchmarks but also attains higher training efficiency due to fine-grained instance-level preference labels.

In this work, we present a panoramic metric depth foundation model that generalizes across diverse scene distances. We explore a data-in-the-loop paradigm from the view of both data construction and framework design. We collect a large-scale dataset by combining public datasets, high-quality synthetic data from our UE5 simulator and text-to-image models, and real panoramic images from the web. To reduce domain gaps between indoor/outdoor and synthetic/real data, we introduce a three-stage pseudo-label curation pipeline to generate reliable ground truth for unlabeled images. For the model, we adopt DINOv3-Large as the backbone for its strong pre-trained generalization, and introduce a plug-and-play range mask head, sharpness-centric optimization, and geometry-centric optimization to improve robustness to varying distances and enforce geometric consistency across views. Experiments on multiple benchmarks (e.g., Stanford2D3D, Matterport3D, and Deep360) demonstrate strong performance and zero-shot generalization, with particularly robust and stable metric predictions in diverse real-world scenes. The project page can be found at: https://insta360-research-team.github.io/DAP_website/

Multimodal large language models (MLLMs) have achieved remarkable progress on various vision-language tasks, yet their visual perception remains limited. Humans, in comparison, perceive complex scenes efficiently by dynamically scanning and focusing on salient regions in a sequential "blink-like" process. Motivated by this strategy, we first investigate whether MLLMs exhibit similar behavior. Our pilot analysis reveals that MLLMs naturally attend to different visual regions across layers and that selectively allocating more computation to salient tokens can enhance visual perception. Building on this insight, we propose Blink, a dynamic visual token resolution framework that emulates the human-inspired process within a single forward pass. Specifically, Blink includes two modules: saliency-guided scanning and dynamic token resolution. It first estimates the saliency of visual tokens in each layer based on the attention map, and extends important tokens through a plug-and-play token super-resolution (TokenSR) module. In the next layer, it drops the extended tokens when they lose focus. This dynamic mechanism balances broad exploration and fine-grained focus, thereby enhancing visual perception adaptively and efficiently. Extensive experiments validate Blink, demonstrating its effectiveness in enhancing visual perception and multimodal understanding.

Reasoning segmentation enables open-set object segmentation via implicit text queries, therefore serving as a foundation for embodied agents that should operate autonomously in real-world environments. However, existing methods for reasoning segmentation require multimodal large language models with billions of parameters that exceed the computational capabilities of edge devices that typically deploy the embodied AI systems. Distillation offers a pathway to compress these models while preserving their capabilities. Yet, existing distillation approaches fail to transfer the multi-step reasoning capabilities that reasoning segmentation demands, as they focus on matching output predictions and intermediate features rather than preserving reasoning chains. The emerging paradigm of reasoning over digital twin representations presents an opportunity for more effective distillation by re-framing the problem. Consequently, we propose FastReasonSeg, which employs digital twin representations that decouple perception from reasoning to enable more effective distillation. Our distillation scheme first relies on supervised fine-tuning on teacher-generated reasoning chains. Then it is followed by reinforcement fine-tuning with joint rewards evaluating both segmentation accuracy and reasoning quality alignment. Experiments on two video (JiTBench, RVTBench) and two image benchmarks (ReasonSeg, LLM-Seg40K) demonstrate that our FastReasonSeg achieves state-of-the-art reasoning segmentation performance. Moreover, the distilled 0.6B variant outperforms models with 20 times more parameters while achieving 7.79 FPS throughput with only 2.1GB memory consumption. This efficiency enables deployment in resource-constrained environments to enable real-time reasoning segmentation.

Multimodal large language models (MLLMs) that "think with images" can interactively use tools to reason about visual inputs, but current approaches often rely on a narrow set of tools with limited real-world necessity and scalability. In this work, we first reveal a critical and previously overlooked weakness: even state-of-the-art MLLMs are surprisingly brittle, showing significant performance degradation on images with simple orientation changes, underscoring the need for more robust tool-based reasoning. To address this, we propose CodeVision, a flexible and scalable "code-as-tool" framework where the model generates code as a universal interface to invoke any image operation, moving beyond fixed tool registries. We train our model using a two-stage methodology, beginning with Supervised Fine-Tuning (SFT) on a high-quality dataset curated for complex, multi-turn tool composition and error recovery, followed by Reinforcement Learning (RL) with a dense process reward function to encourage strategic and efficient tool use. To facilitate this research, we construct new SFT and RL datasets and introduce a challenging new benchmark suite designed to rigorously evaluate robustness to orientation changes and multi-tool reasoning. Experiments on Qwen2.5-VL and Qwen3-VL series show that our approach significantly improves model performance and fosters emergent capabilities such as flexible tool composition, efficient chained execution, and robust error recovery from runtime feedback. Code is available at https://github.com/ByteDance-BandAI/CodeVision.

Topology reasoning is crucial for autonomous driving. Current methods primarily focus on instance-level learning for centerline detection, followed by a sequential module for topology reasoning that relies on simplified MLP layers. Moreover, these approaches often neglect the importance of point-to-instance (P2I) relationships in topology reasoning. To address these limitations, we present TopoHR (Topological Hierarchical Representation), a novel end-to-end framework that establishes cyclic interaction between centerline detection and topology reasoning, allowing them to iteratively enhance each other. Specifically, we introduce a hierarchical centerline representation including point queries, instance queries, and semantic representations. These multi-level features are seamlessly integrated and fused within a hierarchical centerline decoder. Furthermore, we design a hierarchical topology reasoning module that captures both fine-grained P2I relationships and global instance-to-instance (I2I) connections within a unified architecture. With these novel components, TopoHR ensures accurate and robust topology reasoning. On the OpenLane-V2 benchmark, TopoHR refreshes state-of-the-art performance with significant improvements. Notably, compared with previous best results, TopoHR achieves +3.8 in \mathrm DET _ \text l , +5.4 in \mathrm TOP _ \text ll on subset_A and +11.0 in \mathrm DET _ \text l , +7.9 in \mathrm TOP _ \text ll on subset_B, validating the effectiveness of the proposed components. The code will be shared publicly upon paper acceptance.

Maritime multimodal vision faces significant challenges due to the complexity and variability of oceanic weather and environmental conditions. While modern vessels are commonly equipped with visible and infrared imaging systems, the complementary nature of these modalities fundamentally depends on accurate cross-modal registration. However, the absence of paired visible-infrared datasets that realistically capture diverse maritime scenarios has severely hindered progress in this field. To overcome this limitation, we present MMVIP, the first large-scale visible-infrared maritime vision dataset covering a wide spectrum of weather conditions and sea states. The dataset contains 128,100 images and 50 video sequences with precise spatial-temporal alignment. Comprehensive evaluations across image registration, fusion, maritime object detection, and cross-modal image translation tasks demonstrate the dataset's effectiveness and challenge. Furthermore, MMVIP establishes a new benchmark for advancing multimodal maritime perception. The dataset and corresponding benchmarks are publicly available at: https://github.com/yyppptjr/MMVIP.