Qian Liu
- Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization
- General-Reasoner: Advancing LLM Reasoning Across All Domains
- MuSLR: Multimodal Symbolic Logical Reasoning
- SkyLadder: Better and Faster Pretraining via Context Window Scheduling
- SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines
- ZeCO: Zero-Communication Overhead Sequence Parallelism for Linear Attention