Daixuan Cheng
Scholar

Daixuan Cheng

Google Scholar ID: flRAZJQAAAAJ
Gaoling School of AI, Renmin University of China
LLM Pre-TrainingDomain AdaptationReasoning
Citations & Impact
All-time
Citations
467
 
H-index
8
 
i10-index
7
 
Publications
19
 
Co-authors
7
list available
Resume (English only)
Academic Achievements
  • Notable works include 'Reasoning with Exploration: An Entropy Perspective' (AAAI 2026), FlowRL, and STILL.
Research Experience
  • Since 2021, a research student in the GenAI Group of Microsoft Research, advised by Shaohan Huang and Furu Wei; previously a research assistant in the CoAI Group, Tsinghua University, advised by Yuxian Gu and Minlie Huang; also worked as a research engineer at BIGAI, collaborating with Xuekai Zhu.
Education
  • Ph.D. student at Gaoling School of AI, Renmin University of China, advised by Xin Zhao.
Background
  • Research Interests: Reinforcement Learning for LLM Reasoning, especially Exploration Mechanisms. Professional Field: Artificial Intelligence.