AI RESEARCH
ICPRL: Acquiring Physical Intuition from Interactive Control
arXiv CS.AI
•
ArXi:2603.13295v1 Announce Type: cross VLMs excel at static perception but falter in interactive reasoning in dynamic physical environments, which demands planning and adaptation to dynamic outcomes. Existing physical reasoning methods often depend on abstract symbolic inputs or lack the ability to learn and adapt from direct, pixel-based visual interaction in novel scenarios. We