Jiajun Wu
- From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries
- Model-Based Policy Adaptation for Closed-Loop End-to-end Autonomous Driving
- Seeing the Wind from a Falling Leaf
- Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals
- Taming generative video models for zero-shot optical flow extraction
- VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
- Web-Scale Collection of Video Data for 4D Animal Reconstruction