AI.info

Yi Wu

Explore Yi Wu on AI.info.

• LLMs Are Not Good Strategists, Yet Memory-Enhanced Agency Boosts Reasoning
• AREAL-DTA: Dynamic Tree Attention for Efficient Reinforcement Learning of Large Language Models
• From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents
• Principled RL for Diffusion LLMs Emerges from a Sequence-Level Perspective