5 papers
Asking the World: Generalist Physical Reasoning through Agentic World Modeling and Probing
Shenxiang Zeng, Chen Yang, Peiyao Chen +3
Physical reasoning from video requires inferring latent physical properties and dynamics beyond direct observation. Direct VLM inference remains unreliable on complex physical task…
BlueprintAgent: Constraint-Triggered Targeted Revisits for Simulation-Ready Generation from Scanned Structural Blueprints
Zhouyuan Xu, Chen Yang, Linhao Wang +2
Converting in-service reinforced-concrete (RC) building blueprints into simulation-ready models---structured frame representations that support deterministic FEM export and qualifi…
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…
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…
Leakage-Free Evaluation and Distribution-Robust Spatio-Temporal Graph Learning for Inductive Kriging
Chen Yang, Changhao Zhao, Haoyang Zhao +3
Inductive kriging estimates values at unobserved locations from sparse sensor data, enabling continuous field reconstruction when dense deployment is impractical. However, common 2…