Weixiang Zhao
- L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models
- On Reasoning Strength Planning in Large Reasoning Models
- RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards
- Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment
- When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners