AI.info

Tao Lin

Explore Tao Lin on AI.info.

• Principle-Evolvable Scientific Discovery via Uncertainty Minimization
• Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective
• Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning
• TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows
• Bootstrap Dynamic-Aware 3D Visual Representation for Scalable Robot Learning
• Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment
• Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems
• Don't Just Fine-tune the Agent, Tune the Environment