Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
PhysMind: From Video to Executable Worlds for Training-Free Physical Reasoning
Chen Yang, Shenxiang Zeng, Haoyang Zhao +6
Reliable physical reasoning from video requires understanding how objects move, interact, and respond to interventions. Existing vision-language models (VLMs) often struggle to int…
cs.CV2026
Attend to Evidence: Evidence-Anchored Spatial Attention Supervision for Multimodal RLVR
Ruina Hu, Chen Wang, Lai Wei +5
Reinforcement learning with verifiable rewards (RLVR) improves vision-language models (VLMs) by optimizing outcome rewards derived from final answers. However, such outcome-only re…
cs.CV2026
Thinking in Structures: Evaluating Spatial Intelligence in Constraint-Governed Spaces
Chen Yang, Guanxin Lin, Youquan He +10
Spatial intelligence is crucial for vision--language models (VLMs), yet many scene-centric benchmarks evaluate unconstrained environments where a single image may admit multiple pl…