AI.info
Dawei Yin
Explore Dawei Yin on AI.info.
- Not All Preferences Deserve Gradients: Understanding Gradient Utility in Offline Reasoning Alignment
- Reinforced Efficient Reasoning via Semantically Diverse Exploration
- Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoning
- Efficient Thought Space Exploration Through Strategic Intervention