Fan Wang
- CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step
- EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?
- EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval
- FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion
- GeoVideo: Introducing Geometric Regularization into Video Generation Model
- PlayerOne: Egocentric World Simulator
- PlayerOne: Egocentric World Simulator
- Solving Discrete (Semi) Unbalanced Optimal Transport with Equivalent Transformation Mechanism and KKT-Multiplier Regularization
- SparseDiT: Token Sparsification for Efficient Diffusion Transformer
- SpiderSolver: A Geometry-Aware Transformer for Solving PDEs on Complex Geometries
- Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds
- UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback