Scholar
Yuyang Wu
Google Scholar ID: f7KQvukAAAAJ
Undergraduate, Peking University
Citations & Impact
Citations
126
H-index
2
i10-index
2
Publications
2
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- Publications: ICLR-W'25 'When More is Less: Understanding Chain-of-Thought Length in LLMs' (co-first author), NeurIPS 2024 'A Theoretical Understanding of Self-Correction through In-context Alignment' (co-first author). Awards: Best Paper Runner-up Award at ICLR 2025 Workshop, Best Paper Award at ICML 2024 Workshop, Silver Medal at Chinese Mathematical Olympiad 2021.
Research Experience
- 2023.10 - Present, Research Intern at ZERO Lab, Peking University, researching in-context abilities in LLMs, including self-correction and chain-of-thought; Collaborating with Postdoc Yifei Wang (MIT) and advised by Prof. Yisen Wang (PKU). 2025.03 - 2025.06 (terminated due to non-academic political reasons), Research Intern at Sky Computing Lab, UC Berkeley, researching on meta-reasoning ability in LLMs; Collaborating with Dacheng Li and advised by Prof. Ion Stoica.
Education
- 2022.09 - Present, Peking University, School of Electronics Engineering and Computer Science, BS in Computer Science
Background
- Research interest: Developing a mathematical understanding of LLMs, interpreting their diverse behaviors, and providing principled theoretical guidance for the design and optimization of system-2 reasoning agents. Specifically, my approach involves expanding reasoning boundaries (e.g., enabling effective long-context reasoning and precise multi-round backtracking) and calibrating reasoning skills into practical experience via reinforcement learning in the post-training stage.
Miscellany
- Currently looking for 2025 summer intern opportunities!!!
