Yafu Li
Scholar

Yafu Li

Google Scholar ID: gEceD-sAAAAJ
The Chinese University of Hong Kong
ReasoningTrustworthy AIMultilinguality
Citations & Impact
All-time
Citations
2,743
 
H-index
13
 
i10-index
19
 
Publications
20
 
Co-authors
19
list available
Resume (English only)
Academic Achievements
  • ExGRPO: Learning to Reason from Experience (preprint)
  • Scaling Reasoning, Losing Control: Evaluating Instruction Following in Large Reasoning Models (preprint)
  • Learning to Reason under Off-Policy Guidance (NeurIPS 2025)
  • A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyond (preprint)
  • Test-Time Preference Optimization: On-the-Fly Alignment via Iterative Textual Feedback (ICML 2025)
  • Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberation (preprint)
  • Unveiling Attractor Cycles in Large Language Models: A Dynamical Systems View of Successive Paraphrasing (ACL 2025)
  • MAGE: Machine-generated Text Detection in the Wild (ACL 2024)
  • Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models (Computational Linguistics)
  • Lost in Literalism: How Supervised Training Shapes Translationese in LLMs
Research Experience
  • Interned at Tencent AI Lab during PhD, collaborating closely with Dr. Leyang Cui and Dr. Wei Bi; currently a postdoctoral researcher at The Chinese University of Hong Kong, supervised by Prof. Yu Cheng.
Education
  • Bachelor's Degree: Wuhan University; Master's Degree: University of Edinburgh, supervised by Prof. Alex Lascarides; PhD: Joint program between Zhejiang University and Westlake University, advised by Prof. Yue Zhang.
Background
  • Research Interests: reasoning, trustworthy AI, and multilinguality. Professional Field: Artificial Intelligence, particularly large language models.
Miscellany
  • Open Positions: full-time researchers, research interns, and joint PhD students (with THU, PKU, etc.)