无需训练就能用不确定性指导复杂视觉任务，MLLMs新方法提升多模态模型可靠性。
arXiv:2510.00705v3 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) often struggle with fine-grained perception, such as iden…
多模态大模型实时指导拍照，让摄影新手也能拍出专业级照片。
arXiv:2606.25763v1 Announce Type: new Abstract: Real-world photography requires capture-time guidance for both camera framing and subject pose. Yet ex…
针对MLLMs视觉STEM感知难题，CodePercept创新引入代码接地机制，为多模态理解开辟新路径，已被CVPR2026收录。
arXiv:2603.10757v2 Announce Type: replace Abstract: When MLLMs fail at Science, Technology, Engineering, and Mathematics (STEM) visual reasoning, a fu…
多模态大模型持续学习基准够用吗？ICML 2026 Workshop论文深度剖析现有评估体系的不足。
arXiv:2606.20961v1 Announce Type: cross Abstract: Continual adaptation is essential for multimodal large language models (MLLMs) deployed across evolv…
研究发现，多模态大模型的社会偏见主要源于少量人类视觉线索，而非文本信息，挑战传统认知。
arXiv:2606.20527v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly deployed in personally and societally conseq…
多模态大语言模型在配对时表现准确、拆分时出错，研究通过解耦编辑特定模态神经元来修复这一现象。
arXiv:2606.17057v1 Announce Type: cross Abstract: Although Knowledge Editing provides an efficient mechanism for updating the knowledge of Multimodal …
MLLMs从调用API到操纵物理工具，一文揭示其能力边界与核心挑战。
arXiv:2606.10803v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) excel at utilizing digital APIs and increasingly serve as t…
新基准ChronoPhyBench直击核心：多模态大模型靠语言先验伪装理解？物理时序推理能力堪忧！
arXiv:2606.07962v1 Announce Type: new Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have demonstrated remarkable proficien…
首个衡量多模态大模型理解界面引导用户行为的基准，来自ACL 2026，揭示MLLMs在UI/UX设计认知中的能力与局限。
arXiv:2505.05026v5 Announce Type: replace Abstract: User interface (UI) design goes beyond visuals to shape user experience (UX), underscoring the shi…
为多模态大模型打造的通用代理框架，MUSE统一多种能力，解锁LLM新玩法。
arXiv:2606.03005v1 Announce Type: new Abstract: Despite rapid progress, multimodal large language models (MLLMs) still fail on tasks that humans solve…
多模态大模型能看懂抽象图案却选不对答案，揭示规则与实例之间的认知鸿沟
arXiv:2606.00148v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) often know the rule but pick the wrong answer: on abstract …
论文提出ValueGround基准，评估多模态大模型对不同文化背景下的视觉价值理解能力，揭示现有模型在文化适应性上的不足。
arXiv:2604.06484v3 Announce Type: replace Abstract: Cultural values are expressed not only through language but also through visual scenes and everyda…
首个评估多模态大模型在连续信息流中主动交互智能的基准框架，揭示当前模型主动性的短板。
arXiv:2605.27074v1 Announce Type: new Abstract: Recent multimodal large language models (MLLMs) achieve strong performance on reactive question answer…
多模态大模型能否胜任复杂路线规划？这篇论文构建MapTab基准，系统性评估MLLMs在异构图中的多标准路径规划能力。
arXiv:2602.18600v3 Announce Type: replace Abstract: Systematic evaluation of Multimodal Large Language Models (MLLMs) is crucial for advancing Artific…
多模态大模型对视频时间定位不可靠？这篇论文通过注意力线索揭示并恢复时间感知，有望突破时序理解瓶颈。
arXiv:2605.21954v1 Announce Type: new Abstract: Video temporal grounding (VTG), which localizes the start and end times of a queried event in an untri…
锚定并强化视觉注意力，解决多模态大模型强化学习中的忠实感知难题
arXiv:2605.22072v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a promising paradigm for advancin…
新基准Artifact-Bench，专门评估多模态大模型识别AI视频伪影的能力，揭示模型真实短板。
arXiv:2605.18984v1 Announce Type: new Abstract: Recent video generative models have greatly improved the realism of AI-generated videos, yet their out…
重新思考高分辨率多模态大模型中的Zoom-IN方法，提出Hierarchical Decoupling框架，显著提升视觉理解性能。
arXiv:2510.00054v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have made significant strides in visual understanding tas…