AI RESEARCH
Video-ToC: Video Tree-of-Cue Reasoning
arXiv CS.CV
•
ArXi:2604.20473v1 Announce Type: new Existing Video Large Language Models (Video LLMs) struggle with complex video understanding, exhibiting limited reasoning capabilities and potential hallucinations. In particular, these methods tend to perform reasoning solely relying on the pretrained inherent reasoning rationales whilst lacking perception-aware adaptation to the input video content. To address this, we propose \textbf{Video-ToC}, a novel video reasoning framework that enhances video understanding through tree-of-cue reasoning. Specifically, our approach.