Paper Note on robot-related physical AI

Around Jiajun Wu and Yilun Du

1. Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas
2. Spatial Mental Modeling from Limited Views
3. Autoregressive Flow Matching for Motion Prediction
4. Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow
5. Diffusion policy: Visuomotor policy learning via action diffusion
6. Training diffusion models with reinforcement learning
7. Improving factuality and reasoning in language models through multiagent debate
8. Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making