1
Video Reasoning without Training
无需昂贵训练与冗长思维链，探索视频推理的高效新路径。
arXiv:2510.17045v2 Announce Type: replace-cross Abstract: Video reasoning using Large Multimodal Models (LMMs) relies on costly reinforcement learning…
2
VISD: Enhancing Video Reasoning via Structured Self-Distillation
视频推理新突破：结构化自蒸馏方法VISD可显著提升模型理解能力
arXiv:2605.06094v4 Announce Type: replace-cross Abstract: Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level re…
3
Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding
AI视频推理新突破：用时空提示增强第一人称视频理解，还附带中间步骤评估，填补了基准空白。
arXiv:2605.15342v1 Announce Type: cross Abstract: Video reasoning models are a core component of egocentric and embodied agents. However, standard ben…