Maosong Sun
- A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings
- DCAD-2000: A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detection
- Multi-Agent Collaboration via Evolving Orchestration
- ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
- The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training