跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+2新增论文
+2其中 AI 相关
+0已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-13 05:02 · 全站最近入库：2026-11-12 06:37各信源进度 →

统计口径与数据新鲜度

统计 2026-11-12 05:58 — 2026-11-13 05:58（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-13 05:02最近发现新增版本：2026-11-12 06:37库内论文最新更新时间：2026-11-11 08:00

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

21,675 已收录论文18,323 AI 相关6,056 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 5,654 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-13 05:00（北京时间）
首次观测 · 记录 #1CVF · CVPR 2026:cvf:caadf918f2dd39f41c72a92810003e65CVF · CVPR 2026

GeoMMBench and GeoMMAgent: Toward Expert-Level Multimodal Intelligence in Geoscience and Remote Sensing

Xiao, Aoran, Cheng, Shihao, Xu, Yonghao, Ren, Yexian, Chen, Hongruixuan, Yokoya, Naoto

原文摘要

Recent advances in multimodal large language models (MLLMs) have accelerated progress in domain-oriented AI, yet their development in geoscience and remote sensing (RS) remains constrained by distinctive challenges: wide-ranging disciplinary knowledge, heterogeneous sensor modalities, and a fragmented spectrum of tasks. To bridge these gaps, we introduce GeoMMBench, a comprehensive multimodal question-answering benchmark covering diverse RS disciplines, sensors, and tasks, enabling broader and more rigorous evaluation than prior benchmarks. Using GeoMMBench, we assess 36 open-source and proprietary large language models (LLMs), uncovering systematic deficiencies in domain knowledge, perceptual grounding, and reasoning--capabilities essential for expert-level geospatial interpretation. Beyond evaluation, we propose GeoMMAgent, a multi-agent framework that strategically integrates retrieval, perception, and reasoning through domain-specific RS models and tools. Extensive experimental results demonstrate that GeoMMAgent significantly outperforms standalone LLMs, underscoring the importance of tool-augmented agents for dynamically tackling complex geoscience and RS challenges.

cs.CV · cs.CL · cs.MA

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:caae1a4d84f7f91f80e4b399c3a79decCVF · CVPR 2026

HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models

Zhu, Qihui, Zhang, Tao, Wang, Yuchen, Chen, Shuangwu, Tan, Xiaobin, Yang, Jian, Liu, Yang, Pan, Yinfei

原文摘要

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.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:caf3b275b65234ba018ab3d722f6f3aaCVF · CVPR 2026

3D-VCD: Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive Decoding

Ogunleye, Makanjuola Adekunmi, Abdelrahman, Eman, Lourentzou, Ismini

原文摘要

Large Language Models are increasingly integrated as the cognitive core of 3D embodied agents to enable complex environmental reasoning. However, these agents tend to inherit the critical flaw of hallucination, often failing to ground their responses to their 3D view. While Visual Contrastive Decoding (VCD) is a powerful training-free method for mitigating hallucinations in 2D image-based models, it has not been adapted to the complex 3D embodied environment. In this paper, we embarked on the ambitious goal of being the very first to bridge this gap by introducing a VCD framework for 3D embodied agents. Our method operates at inference time by generating a "negative" 3D context, not by blurring an image, but by applying novel distortions directly to a 3D scene graph, such as swapping object category labels or noising positional coordinates. We evaluate our approach on standard evaluation benchmarks and find that it consistently outperforms existing models. For example, in the random category of 3D-POPE, our 3D-VCD method reduced Yes-rate from 99.9% to 75.1% while simultaneously increasing precision from 50.0% to 62.2%. These results demonstrate that our training-free approach effectively curbs hallucination, yielding 3D agents that are significantly more reliable and grounded.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cb12f40b152f45c35ecb7e4323862b84CVF · CVPR 2026

LaMoGen: Language to Motion Generation Through LLM-Guided Symbolic Inference

Jiang, Junkun, Au, Ho Yin, Xiang, Jingyu, Chen, Jie

原文摘要

Human motion is highly expressive and naturally aligned with language, yet prevailing methods relying heavily on joint text-motion embeddings struggle to synthesize temporally accurate, detailed motions and often lack explainability. To address these limitations, we introduce LabanLite, a motion representation developed by adapting and extending the Labanotation system. Unlike black-box text-motion embeddings, LabanLite encodes each atomic body-part action (e.g., a single left-foot step) as a discrete Laban symbol paired with a textual template. This abstraction decomposes complex motions into interpretable symbol sequences and body-part instructions, establishing a symbolic link between high-level language and low-level motion trajectories. Building on LabanLite, we present LaMoGen, a Text-to-LabanLite-to-Motion Generation framework that enables large language models (LLMs) to compose motion sequences through symbolic reasoning. The LLM interprets motion patterns, relates them to textual descriptions, and recombines symbols into executable plans, producing motions that are both interpretable and linguistically grounded. To support rigorous evaluation, we introduce a Labanotation-based benchmark with structured description-motion pairs and three metrics that jointly measure text-motion alignment across symbolic, temporal, and harmony dimensions. Experiments demonstrate that LaMoGen establishes a new baseline for both interpretability and controllability, outperforming prior methods on our benchmark and two public datasets. These results highlight the advantages of symbolic reasoning and agent-based design for language-driven motion synthesis.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cba5b77c46a7dbde60258f7040da28f2CVF · CVPR 2026

Adversarial Style Optimization: Enhancing VLM Jailbreaks by GRPO-based Stylistic Triggers Optimization

Luo, Bingjun, Guo, Jialin, Yao, Yue, Ding, Xinpeng

原文摘要

Multimodal Large Language Models (MLLMs) have achieved impressive performance, but their safety alignment remains vulnerable to jailbreak attacks. Existing content-based jailbreaks are often inconsistent and show unsatisfying performance against the rapidly evolving MLLMs, failing to exploit non-content-based vulnerabilities. Unlike previous research, we empirically find that MLLMs exhibit a Stylistic Inconsistency between their comprehension ability and safety ability: MLLMs can robustly understand content regardless of visual style, yet their defense mechanisms can be easily bypassed by specific stylistic triggers. Based on this finding, we propose Adversarial Style Optimization (ASO), a plug-and-play enhancement module to amplify existing visual jailbreaks. ASO fine-tunes an image-editing model to superimpose an optimized stylistic modification onto a given adversarial image, using a Group Relative Policy Optimization (GRPO) agent guided by a Structurally-Tiered Reward Function that combines a logit-based signal for detecting explicit refusals with a high-fidelity semantic evaluation from a powerful judge model. Extensive experiments show that ASO significantly enhances the ASR of SOTA attacks, demonstrating that stylistic biases are a scalable vector for red-teaming MLLMs. Our code is available at https://github.com/bingjunluo/ASO.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cba61b4940bd665ba17fdd05f17c1678CVF · CVPR 2026

Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models

Zhang, Chengsheng, Sun, Chenghao, Jiang, Xinyan, Li, Wei, Tian, Xinmei

原文摘要

Large Vision-Language Models (LVLMs) have achieved remarkable progress in visual-textual understanding, yet their reliability is critically undermined by hallucinations, i.e., the generation of factually incorrect or inconsistent responses.While recent studies using steering vectors demonstrated promise in reducing hallucinations, a notable challenge remains: they inadvertently amplify the severity of residual hallucinations. We attribute this to their exclusive focus on the decoding stage, where errors accumulate autoregressively and progressively worsen subsequent hallucinatory outputs.To address this, we propose Prefill-Time Intervention (PTI), a novel steering paradigm that intervenes only once during the prefill stage, enhancing the initial Key-Value (KV) cache before error accumulation occurs.Specifically, PTI is modality-aware, deriving distinct directions for visual and textual representations. This intervention is decoupled to steer keys toward visually-grounded objects and values to filter background noise, correcting hallucination-prone representations at their source.Extensive experiments demonstrate PTI's significant performance in mitigating hallucinations and its generalizability across diverse decoding strategies, LVLMs, and benchmarks. Moreover, PTI is orthogonal to existing decoding-stage methods, enabling plug-and-play integration and further boosting performance.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cbbb078827e51f80e42da0b008147f34CVF · CVPR 2026

Rethinking BCE Loss for Multi-Label Image Recognition with Fine-Tuning

Zhou, Ao, Jiang, Zhiwei, Cheng, Zifeng, Wang, Cong, Yin, Yafeng, Yang, Shufan, Gu, Qing

原文摘要

Fine-tuning vision-language models such as CLIP has become the mainstream paradigm for multi-label image recognition, and prompt tuning is widely adopted due to its lightweight parameter cost and strong transferability. However, we find that when these methods use Binary Cross-entropy as the supervision loss, the model's confidence structure becomes systematically distorted, leading to pronounced miscalibration. Existing calibration techniques, such as temperature scaling or regularization-based methods, largely fail in multi-label settings because they cannot capture inherent semantic dependencies between classes, nor can they correct the global structural shifts introduced during fine-tuning. To address this issue, we propose Class-wise Covariance Regularization, which aligns the predicted covariance structure of class confidences with the semantic correlations encoded in pretrained text embeddings. This alignment preserves the geometric consistency of the class space throughout fine-tuning, resulting in more stable and interpretable confidence distributions across categories. Experiments on multi-label benchmarks show that CCR significantly reduces calibration errors while maintaining or even improving recognition performance.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cc0a87d8e64aca532a9d8df18ab152e4CVF · CVPR 2026

F$^2$-Assist: Multi-Phase Fetal Growth Forecast and Report Generation from Ultrasound Examination

Pu, Bin, Liang, Xusheng, Ding, Xinpeng, Wu, Jinlin, Lei, Zhen, Li, Shengli, Li, Kenli, Ma, Jiawei

原文摘要

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.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cc4782b80378d5be304350eeb59cee81CVF · CVPR 2026

Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving

Xiong, Minhao, Wen, Zichen, Gu, Zhuangcheng, Liu, Xuyang, Zhang, Rui, Kang, Hengrui, Yang, Jiabing, Zhang, Junyuan 等 11 位作者

原文摘要

Vision-Language Models (VLMs) have emerged as a promising paradigm in autonomous driving (AD), providing a unified framework for perception and decisionmaking. However, their real-world deployment is hindered by significant computational overhead when processing high-resolution, multi-view images. This complexity stems from the massive number of visual tokens, which increases inference latency and memory consumption due to the quadratic complexity of self-attention. To address these challenges, we propose Prune2Drive, a plug-and-play visual token pruning framework for multi-view VLMs in AD. Prune2Drive introduces two core innovations: (i) a diversity-aware token selection mechanism that prioritizes semantic and spatial coverage across views, and (ii) a view-adaptive pruning controller that automatically learns optimal pruning ratios based on camera importance to downstream tasks. Unlike prior methods, Prune2Drive requires no model retraining or access to attention maps, ensuring compatibility with modern efficient attention implementations. Extensive experiments on the DriveLM and DriveLMM-o1 benchmarks demonstrate that Prune2Drive achieves significant speedups and memory savings with minimal performance impact. When retaining only 10% of visual tokens, our method achieves a 6.40x speedup in the prefilling phase and consumes only 13.4% of the original FLOPs, with a mere 3% average performance drop on the DriveLM benchmark. Code is available at: https://github.com/MinhaoXiong/Prune2Drive.git

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cc6d61db91fb1e25661ebb1bc36669ffCVF · CVPR 2026

Widget2Code: From Visual Widgets to UI Code via Multimodal LLMs

Zhang, Houston H., Zhang, Tao, Lin, Baoze, Xue, Yuanqi, Zhu, Yincheng, Liu, Huan, Gu, Li, Ye, Linfeng 等 13 位作者

原文摘要

User interface to code (UI2Code) aims to generate executable code that can faithfully reconstruct a given input UI. Prior work focuses largely on web pages and mobile screens, leaving app widgets underexplored. Unlike web or mobile UIs with rich hierarchical context, widgets are compact, context-free micro-interfaces that summarize key information through dense layouts and iconography under strict spatial constraints. Moreover, while (image, code) pairs are widely available for web or mobile UIs, widget designs are proprietary and lack accessible markup. We formalize this setting as the Widget-to-Code (Widget2Code) and introduce an image-only widget benchmark with fine-grained, multi-dimensional evaluation metrics. Benchmarking shows that although generalized multimodal large language models (MLLMs) outperform specialized UI2Code methods, they still produce unreliable and visually inconsistent code. To address these limitations, we develop a baseline that jointly advances perceptual understanding and structured code generation. At the perceptual level, we follow widget design principles to assemble atomic components into complete layouts, equipped with icon retrieval and UI composition modules. At the system level, we design an end-to-end infrastructure, WidgetFactory, which includes a framework-agnostic widget-tailored domain-specific language (WidgetDSL) and a compiler that translates it into multiple front-end implementations (e.g., React, HTML). An adaptive rendering module further refines spatial dimensions to satisfy compactness constraints. Together, these contributions substantially enhance visual fidelity, establishing a strong baseline and unified infrastructure for future Widget2Code research.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cce7ef9540d46f44d26d9a5453c97aa2CVF · CVPR 2026

Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval

Fu, Zhiheng, Hu, Yupeng, Yang, Qianyun, Zhang, Shiqi, Chen, Zhiwei, Li, Zixu

原文摘要

Composed Image Retrieval (CIR) has attracted significant attention due to its flexible multimodal query method, yet its development is severely constrained by the Noisy Triplet Correspondence (NTC) problem. Most existing robust learning methods rely on the "small loss hypothesis", but the unique semantic ambiguity in NTC, such as "partial matching", invalidates this assumption, leading to unreliable noise identification. This entraps the model in a self dependent vicious cycle where the learner is intertwined with the arbiter, ultimately causing catastrophic "representation pollution". To address this critical challenge, we propose a novel "Expert-Proxy-Diversion" decoupling paradigm, named Air-Know (ArbIteR calibrated Knowledge iNternalizing rObust netWork). Air-Know incorporates three core modules: (1) The External Prior Arbitration (EPA) module, which utilizes Multimodal Large Language Models (MLLMs) as an offline expert to construct a high precision anchor dataset; (2) Expert Knowledge Internalization (EKI) module, which efficiently guides a lightweight proxy "arbiter" to internalize the expert's discriminative logic; (3) Dual Stream Reconciliation (DSR) module, which leverages the EKI's matching confidence to divert the training data, achieving a clean alignment stream and a representation feedback reconciliation stream. Extensive experiments on multiple CIR benchmark datasets demonstrate that Air-Know significantly outperforms existing SOTA methods under the NTC setting, while also showing strong competitiveness in traditional CIR.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:ccfa2d060497d89aac94df4735b739acCVF · CVPR 2026

Tokenization Allows Multimodal Large Language Models to Understand, Generate and Edit Architectural Floor Plans

Qin, Sizhong, Weber, Ramon Elias, Lu, Xinzheng

原文摘要

Architectural floor plan design demands joint reasoning over geometry, semantics, and spatial hierarchy, which remains a major challenge for current AI systems. Although recent diffusion and language models improve visual fidelity, they still struggle with coherent spatial reasoning and controllable generation. We present HouseMind, a multimodal large language model that unifies floor plan understanding, generation, and editing in one framework. We introduce discrete room-instance tokens to construct a unified vocabulary that bridges layouts and symbolic reasoning. With multimodal alignment and instruction tuning, the model synthesizes coherent, controllable layouts from text instructions. Experiments show how the framework achieves superior geometric validity and controllability while remaining efficient and locally deployable.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cd280ec1f023ca105d2ca779eec0f27bCVF · CVPR 2026

AVFakeBench: A Comprehensive Audio-Video Forgery Detection Benchmark for AV-LMMs

Xia, Shuhan, Li, Peipei, Liu, Xuannan, Zhang, Dongsen, Guo, Xinyu, Li, Zekun

原文摘要

The threat of Audio-Video (AV) forgery is rapidly evolving beyond human-centric deepfakes to include more diverse manipulations across complex natural scenes. However, existing benchmarks are still confined to DeepFake-based forgeries and single-granularity annotations, thus failing to capture the diversity and complexity of real-world forgery scenarios. To address this, we introduce AVFakeBench, the first comprehensive audio-video forgery detection benchmark that spans rich forgery semantics across both human subject and general subject. AVFakeBench comprises 12K carefully curated audio-video questions, covering seven forgery types and four levels of annotations. To ensure high-quality and diverse forgeries, we propose a multi-stage hybrid forgery framework that integrates proprietary models for task planning with expert generative models for precise manipulation. The benchmark establishes a multi-task evaluation framework covering binary judgment, forgery types classification, forgery detail selection, and explanatory reasoning. We evaluate 11 Audio-Video Large Language Models (AV-LMMs) and 2 prevalent detection methods on AVFakeBench, demonstrating the potential of AV-LMMs as emerging forgery detectors while revealing their notable weaknesses in fine-grained perception and reasoning.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cd680747d24ea40381301375d1abf97eCVF · CVPR 2026

SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoning

Zhang, Jian, Zhou, Shijie, Liu, Bangya, Kadambi, Achuta, Fan, Zhiwen

原文摘要

Large vision-language models (VLMs) still struggle with reliable 3D spatial reasoning, a core capability for embodied and physical AI systems. This limitation arises from their inability to capture fine-grained 3D geometry and spatial relationships. While recent efforts have introduced multi-view geometry transformers into VLMs, they typically fuse only the deep-layer features from vision and geometry encoders, discarding rich hierarchical signals and creating a fundamental bottleneck for spatial understanding. To overcome this, we propose SpatialStack, a general hierarchical fusion framework that progressively aligns vision, geometry, and language representations across the model hierarchy. Moving beyond conventional late-stage vision-geometry fusion, SpatialStack stacks and synchronizes multi-level geometric features with the language backbone, enabling the model to capture both local geometric precision and global contextual semantics. Building upon this framework, we develop VLM-SpatialStack, a model that achieves state-of-the-art performance on multiple 3D spatial reasoning benchmarks. Extensive experiments and ablations demonstrate that our multi-level fusion strategy consistently enhances 3D understanding and generalizes robustly across diverse spatial reasoning tasks, establishing SpatialStack as an effective and extensible design paradigm for vision-language-geometry integration in next-generation multimodal physical AI systems.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cd7931550f470b9732deb2e862888615CVF · CVPR 2026

Same Content, Different Answers: Cross-Modal Inconsistency in MLLMs

van Sprang, Angela, Samson, Laurens, Lucic, Ana, Acar, Erman, Ghebreab, Sennay, Asano, Yuki M.

原文摘要

We introduce two new benchmarks REST and REST+ (Render-Equivalence Stress Tests) to enable systematic evaluation of cross-modal inconsistency in multimodal large language models (MLLMs). MLLMs are trained to represent vision and language in the same embedding space, yet they cannot perform the same tasks in both modalities. Our benchmarks contain samples with the same semantic information in three modalities (image, text, mixed) and we show that state-of-the-art MLLMs cannot consistently reason over these different modalities. We evaluate 15 MLLMs and find that the degree of modality inconsistency varies substantially, even when accounting for problems with text recognition (OCR). Neither rendering text as image nor rendering an image as text solves the inconsistency. Even if OCR is correct, we find that visual characteristics (text colour and resolution, but not font) and the number of vision tokens have an impact on model performance. Finally, we find that our consistency score correlates with the modality gap between text and images, highlighting a mechanistic interpretation of cross-modal inconsistent MLLMs.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cd7ce316d1674f006944ca369fb1ba83CVF · CVPR 2026

Probabilistic Prompt Adaptation for Unified Image Aesthetics and Quality Assessment

Hara, Takayuki, Otsuka, Yuya

原文摘要

Recent advances in vision-language foundation models have enabled text-driven evaluation of image aesthetics and visual quality. However, existing models are typically optimized for fixed prompts or specific datasets, limiting their adaptability to diverse evaluation criteria. This paper presents Probabilistic Prompt Adaptation (PPA), a unified probabilistic framework that flexibly predicts aesthetic and quality scores conditioned on arbitrary text prompts. PPA formulates score prediction as a mixture over prompts, dynamically estimating prompt suitability based on both image content and task context. By marginalizing over prompts pre-sampled from a large language model (LLM), it enables annotation-free training using only triplets of task, image, and score. Experiments across multiple IAA and IQA benchmarks demonstrate that PPA achieves consistent and perceptually aligned prompt-based scoring, allowing fine-grained control over evaluation semantics.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cdb29255f744b3d208121b1466cf681fCVF · CVPR 2026

Learning Transferable Temporal Primitives for Video Reasoning via Synthetic Videos

Jiang, Songtao, Song, Sibo, Zhou, Chenyi, Wang, Yuan, Chen, Ruizhe, Guan, Tongkun, Luo, Ruilin, Zhang, Yan 等 15 位作者

原文摘要

The transition from image to video understanding requires vision-language models (VLMs) to shift from recognizing static patterns to reasoning over temporal dynamics such as motion trajectories, speed changes, and state transitions. Yet current post-training methods fall short due to two critical limitations: (1) existing datasets often lack temporal-centricity, where answers can be inferred from isolated keyframes rather than requiring holistic temporal integration; (2) training data generated by proprietary models contains systematic errors in fundamental temporal perception, such as confusing motion directions or misjudging speeds. We introduce SynRL, a post-training framework that teaches models temporal primitives, the fundamental building blocks of temporal understanding including direction, speed, and state tracking. Our key insight is that these abstract primitives, learned from programmatically generated synthetic videos, transfer effectively to real-world scenarios. We decompose temporal understanding into short-term perceptual primitives (speed, direction) and long-term cognitive primitives (state tracking, retrodictive inference), constructing 7.7K CoT and 7K RL samples with ground-truth frame-level annotations through code-based video generation. Despite training on simple geometric shapes, SynRL achieves substantial improvements across 15 benchmarks spanning temporal grounding, complex reasoning, and general video understanding. Remarkably, our 7.7K synthetic CoT samples outperform Video-R1's 165K real-world samples. We attribute this to fundamental temporal skills--such as tracking frame-by-frame changes and comparing velocity--that transfer effectively from abstract synthetic patterns to complex real-world scenarios. This establishes a new paradigm for video post-training: video temporal learning through carefully designed synthetic data provides a more cost-efficient scaling path. Code is released on https://github.com/jiangsongtao/Synthetic-Video.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cdc1bacc90460e00a7981baf990d03f3CVF · CVPR 2026

Breaking the Regional Perception Bottleneck of Multimodal Large Language Models via External Reasoning Framework

Zhang, Jinrong, Xu, Zhaoyang, He, Xusheng, Li, Xinrui, Zheng, Na, Wu, Jianlong

原文摘要

High-quality pixel-level responses remain a major bottleneck for multimodal large language models (MLLMs) in regional perception. Existing approaches generally attach regression decoders to MLLM features, achieving strong grounding performance but compromising end-to-end design and increasing training costs. Researchers have applied parameter and data scaling to improve pure MLLMs' ability to generate pixel coordinates in natural language, yet the performance gains on grounding tasks remain markedly weaker than those in standard QA tasks. Our analysis shows the primary bottleneck is that conventional scaling fails to effectively enhance the key reasoning stage required for pixel-level regional perception. To address this, we propose R-Ground, a reasoning framework for MLLM-based grounding built upon a multimodal Monte Carlo Tree Search algorithm. R-Ground leverages structured reasoning actions, multimodal feature alignment scoring, and regional feature weighted voting to perform scaling at the designated reasoning stage. Extensive experiments demonstrate that R-Ground achieves effective reasoning scaling, enabling a 7B MLLM to match or even surpass a 72B model on the grounding task.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cde074ce8a8f207300da7e75c7b200e9CVF · CVPR 2026

MM-OVSeg: Multimodal Optical-SAR Fusion for Open-Vocabulary Segmentation in Remote Sensing

Wei, Yimin, Xiao, Aoran, Chen, Hongruixuan, Xia, Junshi, Yokoya, Naoto

原文摘要

Open-vocabulary segmentation enables pixel-level recognition from an open set of textual categories, allowing generalization beyond fixed classes. Despite great potential in remote sensing, progress in this area remains largely limited to clear-sky optical data and struggles under cloudy or haze-contaminated conditions. We present MM-OVSeg, a multimodal Optical-SAR fusion framework for resilient open-vocabulary segmentation under adverse weather conditions. MM-OVSeg leverages the complementary strengths of the two modalities--optical imagery provides rich spectral semantics, while synthetic aperture radar (SAR) offers cloud-penetrating structural cues. To address the cross-modal domain gap and the limited dense prediction capability of current vision-language models, we propose two key designs: a cross-modal unification process for multi-sensor representation alignment, and a dual-encoder fusion module that integrates hierarchical features from multiple vision foundation models for text-aligned multimodal segmentation. Extensive experiments demonstrate that MM-OVSeg achieves superior robustness and generalization across diverse cloud conditions. The source dataset and code are available at https://github.com/Jimmyxichen/MM-OVSeg.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:ce1c7255cfba0765c6524c49c95a058eCVF · CVPR 2026

InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity

Wang, Haoming, Xue, Qiyao, Gao, Wei

原文摘要

Modern vision-language models (VLMs) are expected to have abilities of spatial reasoning with diverse scene complexities, but evaluating such abilities is difficult due to the lack of benchmarks that are not only diverse and scalable but also fully customizable. Existing benchmarks offer limited customizability over the scene complexity and are incapable of isolating and analyzing specific VLM failure modes under distinct spatial conditions. To address this gap, instead of individually presenting benchmarks for different scene complexities, in this paper we present InfiniBench, a fully automated, customizable and user-friendly benchmark generator that can synthesize a theoretically infinite variety of 3D scenes with parameterized control on scene complexity. InfiniBench uniquely translates scene descriptions in natural language into photo-realistic videos with complex and physically plausible 3D layouts. This is achieved through three key innovations: 1) a LLM-based agentic framework that iteratively refines procedural scene constraints from scene descriptions; 2) a flexible cluster-based layout optimizer that generates dense and cluttered scenes previously intractable for procedural methods; and 3) a task-aware camera trajectory optimization method that renders scenes into videos with full object coverage as VLM input. Experiments demonstrate that InfiniBench outperforms state-of-the-art procedural and LLM-based 3D generation methods in prompt fidelity and physical plausibility, especially in high-complexity scenarios. We further showcased the usefulness of InfiniBench, by generating benchmarks for representative spatial reasoning tasks including measurement, perspective-taking and spatiotemporal tracking. The source codes of InfiniBench are available at https://github.com/pittisl/infinibench, and some sample benchmarks being generated by InfiniBench are available at https://huggingface.co/datasets/Haoming645/infinibench.

cs.CV · cs.CL · cs.AI

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:ce3329f7aed2a5225a3e196a5e6fbb61CVF · CVPR 2026

Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection

Wang, Shan, Shen, Maying, Chang, Nadine, Nguyen, Chuong, Li, Hongdong, Alvarez, Jose M.

原文摘要

Multimodal large language models (MLLMs) achieve strong performance across diverse tasks but remain prone to hallucinations, where outputs are not grounded in visual inputs. This issue can be attributed to two main biases: text-visual bias, the overreliance on prompts and prior outputs, and co-occurrence bias, spurious correlations between frequently paired objects. We propose Gradient-based Influence-Aware Constrained Decoding (GACD), an inference-based method, that addresses both biases without auxiliary models, and is readily applicable to existing models without finetuning. The core of our approach is bias estimation, which uses first-order Taylor gradients to understand the contribution of individual tokens--visual features and text tokens--to the current output. Based on this analysis, GACD mitigates hallucinations through two components: (1) suppressing spurious visual features correlated with the output objects, and (2) rebalancing cross-modal contributions by strengthening visual features relative to text. Experiments across multiple benchmarks demonstrate that GACD effectively reduces hallucinations and improves the visual grounding of MLLMs outputs.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:ce51b22cff0349f05ea2d73566377c29CVF · CVPR 2026

Granulon: Awakening Pixel-Level Visual Encoders with Adaptive Multi-Granularity Semantics for MLLM

Mao, Junyuan, Li, Qiankun, Meng, Linghao, He, Zhicheng, Zhou, Xinliang, Wang, Kun, Liu, Yang, Jin, Yueming

原文摘要

Recent advances in multimodal large language models largely rely on CLIP-based visual encoders, which emphasize global semantic alignment but struggle with fine-grained visual understanding. In contrast, DINOv3 provides strong pixel-level perception yet lacks coarse-grained semantic abstraction, leading to limited multi-granularity reasoning. To address this gap, we propose Granulon, a novel DINOv3-based MLLM with adaptive granularity augmentation. Granulon introduces a text-conditioned granularity Controller that dynamically adjusts the visual abstraction level according to the semantic scope of the textual input, and an Adaptive Token Aggregation module that performs granularity-guided pooling and relation-aware clustering to produce compact, semantically rich visual tokens. This design enables unified "pixel-to-fine-to-coarse" reasoning within a single forward pass. Extensive and interpretable experiments demonstrate that Granulon improves accuracy by 30% and reduces hallucination by 20%, outperforming all visual encoders under identical settings. Code is available at the Supplementary.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:ced7109d62bb4514d4670f869e6899c8CVF · CVPR 2026

Percept-WAM: Perception-Enhanced World-Awareness-Action Model for Robust End-to-End Autonomous Driving

Han, Jianhua, Tian, Meng, Zhu, Jiangtong, He, Fan, Zhang, Huixin, Guo, Sitong, Zhu, Dechang, Tang, Hao 等 19 位作者

原文摘要

Autonomous driving heavily relies on accurate and robust spatial perception. Many failures arise from inaccuracies and instability, especially in long-tail scenarios and complex interactions. However, current vision-language models are weak at spatial grounding and understanding, and VLA systems built on them therefore show limited perception and localization ability.To address these challenges, we introduce Percept-WAM, a perception-enhanced World-Awareness-Action Model that is the first to implicitly integrate 2D/3D scene understanding abilities within a single vision-language model (VLM).Instead of relying on QA-style spatial reasoning, Percept-WAM unifies 2D/3D perception tasks into World-PV and World-BEV tokens, which encode both spatial coordinates and confidence.We propose a grid-conditioned prediction mechanism for dense object perception, incorporating IoU-aware scoring and parallel autoregressive decoding, improving stability in long-tail, far-range, and small-object scenarios. Additionally, Percept-WAM leverages pretrained VLM parameters to retain general intelligence (e.g., logical reasoning) and can output perception results and trajectory control outputs directly. Experiments show that Percept-WAM matches or surpasses classical detectors and segmenters on downstream perception benchmarks, achieving 51.7/58.9 mAP on COCO 2D detection and nuScenes BEV 3D detection. When integrated with trajectory decoders, it further improves planning performance on nuScenes and NAVSIM, e.g., surpassing DiffusionDrive by 2.1 in PMDS on NAVSIM.Qualitative results further highlight its strong open-vocabulary and long-tail generalization.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cef8b2db5cb6b51f187f307e000db53fCVF · CVPR 2026

Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models

Zhao, Dachuan, Li, Weiyue, Shen, Zhenda, Qiu, Yushu, Xu, Bowen, Chen, Haoyu, Chen, Yongchao

原文摘要

Vision-Language Models (VLMs) have become indispensable for multimodal reasoning, yet their representations often encode and amplify demographic biases, resulting in biased associations and misaligned predictions in downstream tasks. Such behavior undermines fairness and distorts the intended alignment between vision and language. Recent post-hoc approaches attempt to mitigate bias by replacing the most attribute-correlated embedding coordinates with neutral values. However, our systematic analysis reveals three critical limitations of this coordinate-wise approach: feature entanglement, poor cross-dataset generalization, and incomplete bias removal. We find that bias is not localized to a few coordinates but is instead distributed across a few linear subspaces. To address these limitations, we propose Subspace Projection Debiasing (SPD), a geometrically principled framework that identifies and removes the entire subspace of linearly decodable bias while reinserting a neutral mean component to preserve semantic fidelity. Extensive experiments across zero-shot classification, text-to-image retrieval, and image generation validate the effectiveness of SPD: our method achieves more robust debiasing with an average improvement of 18.5% across four fairness metrics, while maintaining minimal loss in task performance compared to the best debiasing baseline.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cf3e972a6f149228bb4593b6b2a68690CVF · CVPR 2026

CrossHOI-Bench: A Unified Benchmark for HOI Evaluation across Vision-Language Models and HOI-Specific Methods

Lei, Qinqian, Wang, Bo, Tan, Robby T.

原文摘要

HOI detection has long been dominated by task-specific models, sometimes with early vision-language backbones such as CLIP. With the rise of large generative VLMs, a key question is whether standalone VLMs can perform HOI detection competitively against specialized HOI methods. Existing benchmarks such as HICO-DET require exact label matching under incomplete annotations, so any unmatched prediction is marked wrong. This unfairly penalizes valid outputs, especially from less constrained VLMs, and makes cross-paradigm comparison unreliable. To address this limitation, we introduce CrossHOI-Bench, a multiple-choice HOI benchmark with explicit positives and curated negatives, enabling unified and reliable evaluation of both VLMs and HOI-specific models. We further focus on challenging scenarios, such as multi-person scenes and fine-grained interaction distinctions, which are crucial for revealing real differences between the two paradigms. Experiments show that large VLMs achieve competitive, sometimes superior, zero-shot performance, yet they struggle with multiple concurrent actions and with correctly assigning interactions to the target person. Conversely, HOI-specific methods remain weaker in general HOI reasoning but demonstrate stronger multi-action recognition and more reliable identification of which person performs which action. These findings expose complementary strengths and weaknesses of VLMs and HOI-specific methods, which existing benchmarks fail to reveal due to incorrect penalization.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cf3ecb82d9aa3d4a6f7b4571126ac438CVF · CVPR 2026

CausalLens: Sensitivity-Guided Multi-Head Causal Intervention for Hallucination Mitigation in Large Vision-Language Models

Ji, Junyang, Liu, Qifan, Yang, Wenming, He, Zhihai

原文摘要

Recent Large Vision-Language Models (LVLMs) have shown impressive capabilities in multimodal understanding and generation. Despite this progress, they remain prone to *hallucination*, where model outputs conflict with the visual input due to an over-reliance on textual priors. Existing inference-time mitigation approaches frequently depend on multi-pass or contrastive decoding, which increases latency and limits their applicability in real-time settings. To address this limitation, we propose **CausalLens**, a training-free and single-pass intervention that directly adjusts the decoder hidden states to strengthen visual grounding. By decomposing attention heads into visual, textual, and system prompt pathways, CausalLens identifies visually reliable heads using a sensitivity measure and selectively adjusts their mid-layer hidden-state contributions. A projection-aligned correction further stabilizes these adjusted states after multi-head fusion, ensuring that the enhanced visual information is preserved throughout decoding. Extensive experiments across multiple hallucination benchmarks and LVLM architectures demonstrate that CausalLens consistently improves visual fidelity while adding negligible computational overhead. The method requires no fine-tuning or architectural changes, making it well-suited for practical, latency-sensitive applications.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:cf66900faa91e5722bd20dc8fa4fe529CVF · CVPR 2026

Think-as-You-See: Streaming Chain-of-Thought Reasoning for Large Vision-Language Models

Zhang, Jialiang, Tong, Junlong, Lin, Junyan, Wu, Hao, Sun, Yirong, Ma, Yunpu, Shen, Xiaoyu

原文摘要

Large Vision Language Models (LVLMs) have demonstrated remarkable capabilities in Chain-of-Thought (CoT) reasoning. However, existing LVLM reasoning paradigms only begin reasoning after the entire video becomes available, introducing unnecessary latency and diminishing attention to early visual cues in dynamic scenes. Inspired by the human ability to think while watching, we introduce a streaming reasoning paradigm for LVLMs, where reasoning unfolds sequentially with incoming frames and deepens after the full video is observed. We instantiate this paradigm through Think-as-You-See (TaYS), a unified framework that enables LVLMs to reason while watching by integrating streaming CoT generation, stream-constrained training, and stream-parallel inference. Specifically, TaYS employs temporally aligned streaming reasoning units with precise CoT supervision, enforces ordered reasoning via streaming attention masks and positional encodings, and utilizes a parallel KV caches mechanism that decouples input encoding from reasoning generation, ensuring alignment and true concurrency. We evaluate TaYS on the Qwen2.5-VL model family across representative video CoT tasks, including event dynamics analysis, causal reasoning, and thematic understanding. Experimental results show that TaYS achieves superior reasoning performance compared with batch-mode CoT, while reducing pre-reasoning latency to under one second and overall answer delay by more than 50%. These findings demonstrate the effectiveness of the streaming paradigm in enabling real-time, human-like reasoning for LVLMs.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:d0782a770f5597d7f408ac51cd3a50ceCVF · CVPR 2026

BiOTPrompt: Bidirectional Optimal Transport Guided Prompting for Disease Evolution-aware Radiology Report Generation

Liu, Tengfei, Fan, Yijian, Wang, Boyue, Hu, Yongli, Li, Mingjie, Li, Jinghua, Gao, Junbin, Chang, Xiaojun 等 10 位作者

原文摘要

Radiology report generation (RRG) aims to automatically describe medical images via free-text reports. In clinical practice, comparing current and prior chest X-rays is essential for assessing disease progression, motivating the development of longitudinal RRG methods. However, most existing approaches often struggle to capture fine-grained temporal changes, as they often rely on unidirectional alignments or static reasoning pipelines, overlooking the bidirectional and asymmetric nature of disease evolution. To tackle these challenges, we propose BiOTPrompt, a novel framework for disease evolution-aware radiology report generation, which introduces a Bidirectional Optimal Transport (BiOT) mechanism to explicitly model progression dynamics between historical and current chest X-rays. By analyzing the asymmetry between bidirectional transport plans, BiOTPrompt can identify newly emerged and resolved regions, which are then used to construct dynamic prompts that guide large language models (LLMs) in generating clinically relevant diagnostic reports. Furthermore, we incorporate a vision-language consistency constraint to ensure alignment between visual evidence and textual descriptions, mitigating hallucinations and enhancing factual correctness. Extensive experiments on the Longitudinal-MIMIC dataset demonstrate that BiOTPrompt achieves state-of-the-art performance in both language metrics and clinical relevance, setting a new standard for longitudinal radiology report generation.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:d07a97be92028c66548c3e2ee841f38aCVF · CVPR 2026

Breaking Multimodal LLM Safety via Video-Driven Prompting

Wang, Dong, He, Xiangyu, Lyu, Xinqi, Xiao, Bin

原文摘要

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in visual reasoning tasks, serving as the core perception engines for emerging AI agents like OpenClaw. While recent studies have introduced several effective image-based jailbreak methods, the vulnerabilities inherent in the video modality remain a largely unexplored frontier. As a pioneering effort to bridge this critical safety gap, we demonstrate that video-driven jailbreak attacks are significantly more effective and robust against pre-defined system prompts than their image-based counterparts. Specifically, we find that simply repeating a harmful image across multiple frames to construct a video can bypass the safety mechanisms of MLLMs. Our analysis reveals that unsafe videos are embedded more similarly to safe videos in the model's representation space than individual harmful images, making them harder to detect. Moreover, videos composed of identical frames are processed more like static images and are more likely to trigger safety defenses compared to videos with diverse frames. Motivated by these findings, we propose an algorithm that injects harmful content into typographic videos by interleaving it with diverse, safety-proximal frames, thereby evading MLLM safety alignment. Extensive experiments demonstrate that our approach achieves state-of-the-art jailbreak performance on several widely-used MLLMs (e.g., VideoLLaMA-2, Qwen2.5-VL, GPT-4.1, and Gemini-2.5) under 16 different safety policies.

cs.CV · cs.CL · cs.AI

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗
首次观测 · 记录 #1CVF · CVPR 2026:cvf:d0f74c412e5e502655e12ab8117f465dCVF · CVPR 2026

RoboAgent: Chaining Basic Capabilities for Embodied Task Planning

Xu, Peiran, Zheng, Jiaqi, Mu, Yadong

原文摘要

This paper focuses on embodied task planning, where an agent acquires visual observations from the environment and executes atomic actions to accomplish a given task. Although recent Vision-Language Models (VLMs) have achieved impressive results in multimodal understanding and reasoning, their performance remains limited when applied to embodied planning that involves multi-turn interaction, long-horizon reasoning, and extended context analysis. To bridge this gap, we propose RoboAgent, a capability-driven planning pipeline in which the model actively invokes different sub-capabilities. Each capability maintains its own context, and produces intermediate reasoning results or interacts with the environment according to the query given by a scheduler. This framework decomposes complex planning into a sequence of basic vision-language problems that VLMs can better address, enabling a more transparent and controllable reasoning process. The scheduler and all capabilities are implemented with a single VLM, without relying on external tools. To train this VLM, we adopt a multi-stage paradigm that consists of: (1) behavior cloning with expert plans, (2) DAgger training using trajectories collected by the model, and (3) reinforcement learning guided by an expert policy. Across these stages, we exploit the internal information of the environment simulator to construct high-quality supervision for each capability, and we further introduce augmented and synthetic data to enhance the model's performance in more diverse scenarios. Extensive experiments on widely used embodied task planning benchmarks validate the effectiveness of the proposed approach.

cs.CV · cs.CL

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition · 2026 · 正式发表

查看论文
CVF · CVPR 2026 ↗PDF ↗