新方法「潜在自强制」提升视频语言学习效率，无需逐帧解码即可对齐语义。
arXiv:2606.22870v1 Announce Type: cross Abstract: Recent advancements in chain-of-thought (CoT) reasoning have shown promise in enhancing video unders…
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 …
多模态先验注入表示空间去噪，RepFusion实现更鲁棒的跨模态表征融合。
arXiv:2606.14700v1 Announce Type: new Abstract: Large language models (LLMs) are widely used in text-to-image (T2I) systems, but they are typically li…
新方法通过交换感知的令牌剪枝，高效提升音频-视觉字幕生成性能，论文来自arXiv最新研究。
arXiv:2606.10533v1 Announce Type: new Abstract: Audio-visual captioning generates natural language descriptions from video and audio content. Multimod…
提出LongMoE模型，用轨迹感知混合专家机制应对多模态临床数据的任意模态缺失挑战。
arXiv:2606.09907v1 Announce Type: cross Abstract: Multimodal clinical learning is increasingly important for integrating diverse patient data, includi…
提出DecepGPT框架，通过Schema驱动和多文化数据集实现高可解释性、跨域鲁棒的多模态欺骗检测。
arXiv:2603.23916v3 Announce Type: replace Abstract: Multimodal deception detection aims to identify deceptive behavior by analyzing audiovisual cues f…
提出了一种鲁棒的视觉-表格多模态学习方法，即使数据缺失也能高效融合图文特征。
arXiv:2512.19602v2 Announce Type: replace Abstract: Large-scale medical biobanks provide imaging data complemented by extensive tabular information, s…
多模态AI框架突破资源限制，为肺炎筛查提供低成本高效方案
arXiv:2605.02207v2 Announce Type: replace-cross Abstract: Pneumonia remains a leading global cause of morbidity and mortality, particularly in low-res…