CVPR 2025 论文列表

Recent advancements in multimodal large language models (MLLMs) have significantly improved performance in visual question answering. However, they often suffer from hallucinations. In this work, hallucinations are categorized into two main types: initial hallucinations and snowball hallucinations. We argue that adequate contextual information can be extracted directly from the token interaction process. Inspired by causal inference in decoding strategy, we propose to leverage causal masks to establish information propagation between multimodal tokens. The hypothesis is that insufficient interaction between those tokens may lead the model to rely on outlier tokens, overlooking dense and rich contextual cues. Therefore, we propose to intervene in the propagation process by tackling outlier tokens to enhance in-context inference. With this goal, we present FarSight, a versatile plug-and-play decoding strategy to reduce attention interference from outlier tokens merely by optimizing the causal mask. The heart of our method is effective token propagation. We design an attention register structure within the upper triangular matrix of the causal mask, dynamically allocating attention capture attention diverted to outlier tokens. Moreover, a positional awareness encoding method with a diminishing masking rate is proposed, allowing the model to attend to further preceding tokens, especially for video sequence tasks. With extensive experiments, FarSight demonstrates significant hallucination-mitigating performance across different MLLMs on both image and video benchmarks, proving its effectiveness.

3D Visual Grounding (3DVG) aims to locate objects in 3D scenes based on textual descriptions, essential for applications like augmented reality and robotics. Traditional 3DVG approaches rely on annotated 3D datasets and predefined object categories, limiting scalability and adaptability. To overcome these limitations, we introduce SeeGround, a zero-shot 3DVG framework leveraging 2D Vision-Language Models (VLMs) trained on large-scale 2D data. SeeGround represents 3D scenes as a hybrid of query-aligned rendered images and spatially enriched text descriptions, bridging the gap between 3D data and 2D-VLMs input formats. We propose two modules: the Perspective Adaptation Module, which dynamically selects viewpoints for query-relevant image rendering, and the Fusion Alignment Module, which integrates 2D images with 3D spatial descriptions to enhance object localization. Extensive experiments on ScanRefer and Nr3D demonstrate that our approach outperforms existing zero-shot methods by large margins. Notably, we exceed weakly supervised methods and rival some fully supervised ones, outperforming previous SOTA by 7.7% on ScanRefer and 7.1% on Nr3D, showcasing its effectiveness in complex 3DVG task. Project website (with demo and code): https://seeground.github.io/.

Large vision-language models (LVLMs) have shown remarkable capabilities in interpreting visual content. While existing works demonstrate these models' vulnerability to deliberately placed adversarial texts, such texts are often easily identifiable as anomalous. In this paper, we present the first approach to generate scene-coherent typographic adversarial attacks that mislead advanced LVLMs while maintaining visual naturalness through the capability of the LLM-based agent. Our approach addresses three critical questions: what adversarial text to generate, where to place it within the scene, and how to integrate it seamlessly. We propose a training-free, multi-modal LLM-driven scene-coherent typographic adversarial planning (SceneTAP) that employs a three-stage process: scene understanding, adversarial planning, and seamless integration. The SceneTAP utilizes chain-of-thought reasoning to comprehend the scene, formulate effective adversarial text, strategically plan its placement, and provide detailed instructions for natural integration within the image. This is followed by a scene-coherent TextDiffuser that executes the attack using a local diffusion mechanism. We extend our method to real-world scenarios by printing and placing generated patches in physical environments, demonstrating its practical implications. Extensive experiments show that our scene-coherent adversarial text successfully misleads state-of-the-art LVLMs, including ChatGPT-4o, even after capturing new images of physical setups. Our evaluations demonstrate a significant increase in attack success rates while maintaining visual naturalness and contextual appropriateness. This work highlights vulnerabilities in current vision-language models to sophisticated, scene-coherent adversarial attacks and provides insights into potential defense mechanisms. We release our code at https://github.com/tsingqguo/scenetap.

Recent advancements in Large Language Models (LLMs) and Vision-Language Models (VLMs) have sparked significant interest in developing GUI visual agents. We introduce MONDAY (Mobile OS Navigation Task Dataset for Agents from YouTube), a large-scale dataset of 313K annotated frames from 20K instructional videos capturing diverse real-world mobile OS navigation across multiple platforms. Models that include MONDAY in their pretraining phases demonstrate robust cross-platform generalization capabilities, consistently outperforming models trained on existing single OS datasets while achieving an average performance gain of 18.11%p on an unseen mobile OS platform. To enable continuous dataset expansion as mobile platforms evolve, we present an automated framework that leverages publicly available video content to create comprehensive task datasets without manual annotation. Our framework comprises robust OCR-based scene detection (95.04% F1-score), near-perfect UI element detection (99.87% hit ratio), and novel multi-step action identification to extract reliable action sequences across diverse interface configurations. We contribute both the MONDAY dataset and our automated collection framework to facilitate future research in mobile OS navigation, available at https://github.com/runamu/monday.

Existing human recognition systems often rely on separate, specialized models for face and body analysis, limiting their effectiveness in real-world scenarios where pose, visibility, and context vary widely. This paper introduces SapiensID, a unified model that bridges this gap, achieving robust performance across diverse settings. SapiensID introduces (i) Retina Patch (RP), a dynamic patch generation scheme that adapts to subject scale and ensures consistent tokenization of regions of interest; (ii) Semantic Attention Head (SAH), an attention mechanism that learns pose-invariant representations by pooling features around key body parts; and (iii) a masked recognition model (MRM) that learns from variable token length. To facilitate training, we introduce WebBody4M, a large-scale dataset capturing diverse poses and scale variations. Extensive experiments demonstrate that SapiensID achieves state-of-the-art results on various body ReID benchmarks, outperforming specialized models in both short-term and long-term scenarios while remaining competitive with dedicated face recognition systems. Furthermore, SapiensID establishes a strong baseline for the newly introduced challenge of Cross Pose-Scale ReID, demonstrating its ability to generalize to complex, real-world conditions.The dataset, code and models will be released.

Adversarial patches are capable of misleading computer vision systems based on convolutional neural networks. Existing recovery methods suffer of at least one of three fundamental shortcomings: no information about the presence of patches in the scene, inability to efficiently handle noncontiguous patch attacks, and a strong reliance on fixed saliency thresholds. We propose Saliuitl, a recovery method independent of the number of patches and their shape, which unlike prior works, explicitly detects patch attacks before attempting recovery. In our approach, detection is based on the attributes of a binarized feature map ensemble, which is generated by using an ensemble of saliency thresholds. If an attack is detected, Saliuitl recovers clean predictions locating patches guided by an ensemble of binarized feature maps and inpainting them. We evaluate Saliuitl on widely used object detection and image classification benchmarks from the adversarial patch literature, and our results show that compared to recent state-of-the-art defenses, Saliuitl achieves a recovery rate up to 97.81 and 42.63 percentage points higher at the same rate of lost predictions for image classification and object detection, respectively. By design, Saliuitl has low computational complexity and is robust to adaptive white-box attacks. Our code is available at https://github.com/Saliuitl/Saliuitl/tree/main.

Global effective receptive field plays a crucial role for image style transfer (ST) to obtain high-quality stylized results. However, existing ST backbones (e.g., CNNs and Transformers) suffer huge computational complexity to achieve global receptive fields. Recently, the State Space Model (SSM), especially the improved variant Mamba, has shown great potential for long-range dependency modeling with linear complexity, which offers a approach to resolve the above dilemma. In this paper, we develop a Mamba-based style transfer framework, termed SaMam. Specifically, a mamba encoder is designed to efficiently extract content and style information. In addition, a style-aware mamba decoder is developed to flexibly adapt to various styles. Moreover, to address the problems of local pixel forgetting, channel redundancy and spatial discontinuity of existing SSMs, we introduce both local enhancement and zigzag scan. Qualitative and quantitative results demonstrate that our SaMam outperforms state-of-the-art methods in terms of both accuracy and efficiency.

Vision-language temporal alignment is a crucial capability for human dynamic recognition and cognition in real-world scenarios. While existing research focuses on capturing vision-language relevance, it faces limitations due to biased temporal distributions, imprecise annotations, and insufficient compositionally. To achieve fair evaluation and comprehensive exploration, our objective is to investigate and evaluate the ability of models to achieve alignment from a temporal perspective, specifically focusing on their capacity to synchronize visual scenarios with linguistic context in a temporally coherent manner. As a preliminary step, we present the statistical analysis of existing benchmarks and reveal the existing challenges from a decomposed perspective. To this end, we introduce SVLTA, the synthetic vision-language temporal alignment derived via a well-designed and feasible control generation method within a simulation environment. The approach considers commonsense knowledge, manipulable action, and constrained filtering, which generates reasonable, diverse, and balanced data distributions for diagnostic evaluations. Our experiments reveal diagnostic insights through the evaluations in temporal question answering, distributional shift sensitiveness, and temporal alignment adaptation.

Multimodal image-tabular learning is gaining attention, yet it faces challenges due to limited labeled data. While earlier work has applied self-supervised learning (SSL) to unlabeled data, its task-agnostic nature often results in learning suboptimal features for downstream tasks. Semi-supervised learning (SemiSL), which combines labeled and unlabeled data, offers a promising solution. However, existing multimodal SemiSL methods typically focus on unimodal or modality-shared features, ignoring valuable task-relevant modality-specific information, leading to a Modality Information Gap. In this paper, we propose STiL, a novel SemiSL tabular-image framework that addresses this gap by comprehensively exploring task-relevant information. STiL features a new disentangled contrastive consistency module to learn cross-modal invariant representations of shared information while retaining modality-specific information via disentanglement. We also propose a novel consensus-guided pseudo-labeling strategy to generate reliable pseudo-labels based on classifier consensus, along with a new prototype-guided label smoothing technique to refine pseudo-label quality with prototype embeddings, thereby enhancing task-relevant information learning in unlabeled data. Experiments on natural and medical image datasets show that STiL outperforms the state-of-the-art supervised/SSL/SemiSL image/multimodal approaches. Our code is available at https://github.com/siyi-wind/STiL.

In this work, we study Weakly Supervised Spatio-Temporal Video Grounding (WSTVG), a challenging task of localizing subjects spatio-temporally in videos using only textual queries and no bounding box supervision. Inspired by recent advances in vision-language foundation models, we investigate their utility for WSTVG, leveraging their zero-shot grounding capabilities. However, we find that a simple adaptation lacks essential spatio-temporal grounding abilities. To bridge this gap, we introduce Tubelet Referral Grounding (TRG), which connects textual queries to tubelets to enable spatio-temporal predictions. Despite its promise, TRG struggles with compositional action understanding and dense scene scenarios. To address these limitations, we propose STPro, a progressive learning framework with two key modules: Sub-Action Temporal Curriculum Learning (SA-TCL), which incrementally builds compositional action understanding, and Congestion-Guided Spatial Curriculum Learning (CG-SCL), which adapts the model to complex scenes by spatially increasing task difficulty. STPro achieves state-of-the-art results on three benchmark datasets, with improvements of 1.0% on VidSTG-Declarative and 3.0% on HCSTVG-v1.

Pre-trained on tremendous image-text pairs, vision-language models like CLIP have demonstrated promising zero-shot generalization across numerous image-based tasks. However, extending these capabilities to video tasks remains challenging due to limited labeled video data and high training costs. Recent video prompting methods attempt to adapt CLIP for video tasks by introducing learnable prompts, but they typically rely on a single static prompt for all video sequences, overlooking the diverse temporal dynamics and spatial variations that exist across frames. This limitation significantly hinders the model's ability to capture essential temporal information for effective video understanding. To address this, we propose an integrated Spatial-TempOral dynamic Prompting (STOP) model which consists of two complementary modules, the intra-frame spatial prompting and inter-frame temporal prompting. Our intra-frame spatial prompts are designed to adaptively highlight discriminative regions within each frame by leveraging intra-frame attention and temporal variation, allowing the model to focus on areas with substantial temporal dynamics and capture fine-grained spatial details. Additionally, to highlight the varying importance of frames for video understanding, we further introduce inter-frame temporal prompts, dynamically inserting prompts between frames with high temporal variance as measured by frame similarity. This enables the model to prioritize key frames and enhances its capacity to understand temporal dependencies across sequences. Extensive experiments on various video benchmarks demonstrate that STOP consistently achieves superior performance against state-of-the-art methods. The code is available at https://github.com/zhoujiahuan1991/CVPR2025-STOP

Advancements in Computer-Aided Screening (CAS) systems are essential for improving the detection of security threats in X-ray baggage scans. However, current datasets are limited in representing real-world, sophisticated threats and concealment tactics, and existing approaches are constrained by a closed-set paradigm with predefined labels. To address these challenges, we introduce STCray, the first multimodal X-ray baggage security dataset, comprising 46,642 image-caption paired scans across 21 threat categories, generated using an X-ray scanner for airport security. STCray is meticulously developed with our specialized protocol that ensures domain-aware, coherent captions, that lead to the multi-modal instruction following data in X-ray baggage security. This allows us to train a domain-aware visual AI assistant named STING-BEE that supports a range of vision-language tasks, including scene comprehension, referring threat localization, visual grounding, and visual question answering (VQA), establishing novel baselines for multi-modal learning in X-ray baggage security. Further, STING-BEE shows state-of-the-art generalization in cross-domain settings. Code, data, and models are available at https://divs1159.github.io/STING-BEE/.

Video Large Language Models (Video-LLMs) have recently shown strong performance in basic video understanding tasks, such as captioning and coarse-grained question answering, but struggle with compositional reasoning that requires multi-step spatio-temporal inference across object relations, interactions, and events. The hurdles to enhancing this capability include extensive manual labor, the lack of spatio-temporal compositionality in existing training data and the absence of explicit reasoning supervision. In this paper, we propose STEP, a novel graph-guided self-training method that enables Video-LLMs to generate reasoning-rich fine-tuning data from any raw videos to improve itself. Specifically, we first induce Spatio-Temporal Scene Graph (STSG) representation of diverse videos to capture fine-grained, multi-granular video semantics. Then, the STSGs guide the derivation of multi-step reasoning Question-Answer (QA) data with Chain-of-Thought (CoT) rationales. Both answers and rationales are integrated as training objective, aiming to enhance model's reasoning abilities by supervision over explicit reasoning steps. Experimental results demonstrate the effectiveness of STEP across models of varying scales, with a significant 21.3% improvement in tasks requiring three or more reasoning steps. Furthermore, it achieves superior performance with a minimal amount of self-generated rationale-enriched training samples in both compositional reasoning and comprehensive understanding benchmarks, highlighting the broad applicability and vast potential.

3D occupancy and scene flow offer a detailed and dynamic representation of 3D scene. Recognizing the sparsity and complexity of 3D space, previous vision-centric methods have employed implicit learning-based approaches to model spatial and temporal information. However, these approaches struggle to capture local details and diminish the model's spatial discriminative ability. To address these challenges, we propose a novel explicit state-based modeling method designed to leverage the occupied state to renovate the 3D features. Specifically, we propose a sparse occlusion-aware attention mechanism, integrated with a cascade refinement strategy, which accurately renovates 3D features with the guidance of occupied state information. Additionally, we introduce a novel method for modeling long-term dynamic interactions, which reduces computational costs and preserves spatial information. Compared to the previous state-of-the-art methods, our efficient explicit renovation strategy not only delivers superior performance in terms of RayIoU and mAVE for occupancy and scene flow prediction but also markedly reduces GPU memory usage during training, bringing it down to 8.7GB. Our code is available on https://github.com/lzzzzzm/STCOcc

Zero-shot multi-label recognition (MLR) with Vision-Language Models (VLMs) faces significant challenges without training data, model tuning, or architectural modifications. Existing approaches require prompt tuning or architectural adaptations, limiting zero-shot applicability. Our work proposes a novel solution treating VLMs as black boxes, leveraging scores without training data or ground truth. We make two contributions. First, we find that VLM scores suffer from image- and prompt-specific biases, and that simple standardization is surprisingly effective at removing these and boosting MLR performance. And second, we introduce compound prompts grounded in realistic object combinations. Our analysis reveals "AND"/"OR" signal ambiguities that cause maximum compound scores to be surprisingly suboptimal compared to second-highest scores. We introduce an adaptive fusion method to address this issue. Our method enhances other zero-shot approaches, consistently improving their results. Experiments show superior mean Average Precision (mAP) compared to methods requiring training data, achieved through refined object ranking for robust zero-shot MLR. Code can be found at https://github.com/kjmillerCURIS/SPARC.

The emergence of Vision Language Models (VLMs) has brought unprecedented advances in understanding multimodal information. The combination of textual and visual semantics in VLMs is highly complex and diverse, making the safety alignment of these models challenging. Furthermore, due to the limited study on the safety alignment of VLMs, there is a lack of large-scale, high-quality datasets. To address these limitations, we propose a Safety Preference Alignment dataset for Vision Language Models named SPA-VL. In terms of breadth, SPA-VL covers 6 harmfulness domains, 13 categories, and 53 subcategories, and contains 100,788 samples of the quadruple (question, image, chosen response, rejected response). In terms of depth, the responses are collected from 12 open-source (e.g., QwenVL) and closed-source (e.g., Gemini) VLMs to ensure diversity. The construction of preference data is fully automated, and the experimental results indicate that models trained with alignment techniques on the SPA-VL dataset exhibit substantial improvements in harmlessness and helpfulness while maintaining core capabilities. SPA-VL, as a large-scale, high-quality, and diverse dataset, represents a significant milestone in ensuring that VLMs achieve both harmlessness and helpfulness.

The integration of Vision-Language Models (VLMs) into autonomous driving systems has shown promise in addressing key challenges such as learning complexity, interpretability, and common-sense reasoning. However, existing approaches often struggle with efficient integration and real-time decision-making due to computational demands. In this paper, we introduce SOLVE, an innovative framework that synergizes VLMs with end-to-end (E2E) models to enhance autonomous vehicle planning. Our approach emphasizes knowledge sharing at the feature level through a shared visual encoder, enabling comprehensive interaction between VLM and E2E components. We propose a Trajectory Chain-of-Thought (T-CoT) paradigm, which progressively refines trajectory predictions, reducing uncertainty and improving accuracy. By employing a temporal decoupling strategy, SOLVE achieves efficient asynchronous cooperation, aligning high-quality VLM outputs with E2E real-time performance. Evaluated on the nuScenes dataset, our method demonstrates significant improvements in trajectory prediction accuracy, paving the way for more robust and reliable autonomous driving systems.

Human beings are social animals. How to equip 3D autonomous characters with similar social intelligence that can perceive, understand and interact with humans remains an open yet foundamental problem. In this paper, we introduce SOLAMI, the first end-to-end Social vision-Language-Action (VLA) Modeling framework for Immersive interaction with 3D autonomous characters. Specifically, SOLAMI builds 3D autonomous characters from three aspects: 1) Social VLA Architecture: We propose a unified social VLA framework to generate multimodal response (speech and motion) based on the user's multimodal input to drive the character for social interaction. 2) Interactive Multimodal Data: We present SynMSI, a synthetic multimodal social interaction dataset generated by an automatic pipeline using only existing motion datasets to address the issue of data scarcity. 3) Immersive VR Interface: We develop a VR interface that enables users to immersively interact with these characters driven by various architectures. Extensive quantitative experiments and user studies demonstrate that our framework leads to more precise and natural character responses (in both speech and motion) that align with user expectations with lower latency.