视频多模态大模型如何应对连续演化的新领域？该论文探索了模型在异构域数据流中持续学习的难题。
arXiv:2607.18716v1 Announce Type: new Abstract: Video multimodal large language models have shown strong capability in video understanding, yet their …
视频多模态推理新基准MMR-V，挑战模型理解“未言说”的深层语义。
arXiv:2506.04141v2 Announce Type: replace-cross Abstract: The sequential structure of videos poses a challenge to the ability of multimodal large lang…
探索视频多模态大模型对人类运动推理能力的极限，最新基准测试揭示关键短板。
arXiv:2606.27999v1 Announce Type: new Abstract: Despite the rapid advance of Multimodal Large Language Models (MLLMs) in high-level video understandin…
视频大语言模型是否真的需要音频？这篇被Interspeech 2026接收的研究给出了基准审计与可扩展修复方案。
arXiv:2509.17901v4 Announce Type: replace Abstract: Speech and audio encoders developed over years of community effort are routinely excluded from vid…
视频大模型推理长度不再是死板固定，CARE用能力感知奖励塑形实现自适应思考，效率与精度兼顾。
arXiv:2606.19927v1 Announce Type: new Abstract: In multimodal video reasoning, reinforcement learning-based methods typically rely on simplistic and i…
看广告如何懂你心？新模型GRACE用动作推理破解观众隐藏情感。
arXiv:2606.16198v1 Announce Type: new Abstract: Viewer sentiment prediction in video advertisements aims to infer the latent affective response evoked…
最新研究为视频多模态大模型的时间感知能力设计诊断基准，聚焦瞬时视觉事件，暴露模型在极短事件上的理解缺陷。
arXiv:2606.02522v1 Announce Type: cross Abstract: Video multimodal large language models (MLLMs) have made rapid progress on general and long-form vid…