Min Cai
Scholar

Min Cai

Google Scholar ID: QMTSC0oAAAAJ
PhD Student, University of Alberta
Natural Language ProcessingReinforcement Learning
Citations & Impact
All-time
Citations
132
 
H-index
4
 
i10-index
4
 
Publications
7
 
Co-authors
9
list available
Resume (English only)
Academic Achievements
  • - Paper 'How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence' received Outstanding Paper Award at the New England NLP Workshop
  • - Paper 'Strategist: Learning Strategic Skills by LLMs via Bi-Level Tree Search' covered by State of AI Report 2024, published by Air Street Capital
  • - Paper 'Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller'
  • - Paper 'AvalonBench: Evaluating LLMs Playing the Game of Avalon'
Research Experience
  • - Intern, Zhipu AI, mentored by Dr. Dan Zhang
  • - Works closely with Dr. Ziniu Hu, Dr. Shichang Zhang, and Dr. Difan Zou
Education
  • - PhD Student, University of Alberta, supervised by Dr. Xi Ye
  • - M.S. Graduate, Shenzhen University, supervised by Prof. Haodi Zhang
  • - B.A. in Translation, Beijing Language and Culture University
Background
  • Research Interests: ML and NLP, particularly in understanding the mechanisms behind neural language models (LMs), developing LLM agents capable of solving complex problems, and enhancing LLM reasoning abilities. Currently, the primary focus is on inference-time algorithms for alignment and reasoning in LLMs.
Miscellany
  • In spare time, enjoys playing and listening to music (jazz, classical, R&B, etc.), playing the Pokémon Trading Card Game (PTCG), and trying all kinds of food.