AI RESEARCH
Act2See: Emergent Active Visual Perception for Video Reasoning
arXiv CS.CV
•
ArXi:2605.01657v1 Announce Type: new Vision-Language Models (VLMs) typically rely on static initial frames for video reasoning, restricting their ability to incorporate essential dynamic information as the reasoning process evolves. Existing methods that augment Chain-of-Thought (CoT) with additional frame information often exhibit suboptimal CoT quality and lack the crucial ability to synthesize visual information for hypothetical or counterfactual scenarios. We.