AI.info

Yongyuan Liang

Explore Yongyuan Liang on AI.info.

• On-Policy Self-Distillation in Diffusion Models
• Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation
• TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos