Vision-Language Models (VLMs) excel at 2D recognition but often fail to maintain consistent 3D relations across sparse viewpoints, leading to spatial hallucinations under occlusion and perspective changes. Existing methods commonly fuse all frames with dense geometry, incurring substantial computation and context overh...
Jun-Jie Wang, Zhi-Hao Yuan, Yun-Han Tang et al.· 0 citations
PILOT (Physical Inference for Latent Optimized Trajectories) bridges the gap between high-level physical condition evolution and low-level action trajectory generation within the Action Model, creating a structural bottleneck while weakening the predictive capability of world evolution modeling for action generation.
Xiangkai Ma, Yue Ma, Junjie Wang et al.· 0 citations
This work formalizes Observable Simulator Contract, a minimal contract that any action-conditioned physical simulator should satisfy: supplied actions must induce corresponding agent motion, and environment responses must be grounded in that realized motion.
P. Co, Sichen Hu, Chun-Xuan Jiao et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.