人类记忆是重构的而非忠实记录，这篇论文提出三阶段架构DoYouRemember，让多模态大模型具备类人记忆能力，解决现有模型丢弃内部表征的缺陷。
arXiv:2607.11919v1 Announce Type: cross Abstract: Human memory is reconstructive, not a faithful recording. Current multimodal LLMs (MLLMs) lack this …
多模态大模型定位幻觉问题新解法，无需训练即可评估置信度，基于多令牌局部注意力机制。
arXiv:2607.05978v1 Announce Type: cross Abstract: Multimodal large language models can emit localized predictions, bounding boxes for objects and temp…
提出「先分割再回答」新范式，让多模态大模型在视觉推理中实现像素级精准定位
arXiv:2607.05798v1 Announce Type: cross Abstract: Recent advancements in Multimodal Large Language Models (MLLMs) have evolved from static perception …
ViPo-MLLM融合视觉与姿态信息，实现无标注的手语到自然语言翻译，是多模态大模型在手语理解领域的重要突破。
arXiv:2607.03657v1 Announce Type: cross Abstract: Gloss-free Sign Language Translation (SLT) translates sign language videos into spoken-language sent…
评估多模态大模型视觉知识理解新基准，揭示AI对物理与社会常识的认知短板
arXiv:2511.20272v2 Announce Type: replace Abstract: While Multimodal Large Language Models (MLLMs) have become adept at recognizing objects, they ofte…
用可验证解剖证据为医学多模态大模型装上“可信护栏”，感知-推理协同治理框架获MICCAI 2026早期接收（Top 9%）。
arXiv:2607.00060v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) show strong promise for clinical VQA and radiology report gen…
多模态大模型新方法，实现视觉token高效嵌入，已被ECCV 2026录用。
arXiv:2602.05275v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have shown immense promise in universal multimodal retrie…
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…
理论严谨的曲率引导混合方法，有效缓解多模态大模型微调中的灾难性遗忘。
arXiv:2606.24963v1 Announce Type: cross Abstract: Fine-tuning Multimodal Large Language Models (MLLMs) on specialized tasks often leads to catastrophi…
MLLM主动感知纠错新方法：让模型像人类一样主动发现并修正视觉错误，提升多模态理解准确性。
arXiv:2606.24292v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive vision-language understanding, y…
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…
提出一种自适应交错代码推理方法，让多模态大语言模型在混合推理中更灵活高效
arXiv:2606.23678v1 Announce Type: cross Abstract: Following the paradigm shift initiated by OpenAI o3, interleaved reasoning with code to enhance mult…
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…
多模态大模型当评委也有偏见？论文揭示文化模糊下校准失败的关键漏洞。
arXiv:2606.20676v1 Announce Type: cross Abstract: MLLM-as-a-Judge is conventionally validated by agreement with human annotations, but this metric is …
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…
探索扩散模型中内生思维链推理新机制，突破MLLM文本编码器的推理瓶颈。
arXiv:2603.12252v4 Announce Type: replace-cross Abstract: Recently, Multimodal Large Language Models (MLLMs) have been widely integrated into diffusio…
多模态大模型统一检测并解释AI生成内容，跨模态鉴别新范式。
arXiv:2507.14632v4 Announce Type: replace Abstract: The rapid advancement of generative AI has substantially improved image and video synthesis, ampli…
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 …
视频嵌入新基准MVEB：23项任务全面评估33个模型，揭示无模型独大现状
arXiv:2606.14958v1 Announce Type: cross Abstract: We introduce the Massive Video Embedding Benchmark (MVEB), a 23-task benchmark for video embeddings …