- Improving Code Localization with Long-Term Repository Memory
- Is the Reversal Curse a Binding Problem? Uncovering Limitations of Transformers from a Basic Generalization Failure
- Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization
- LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error
- Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate
- Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters
- Mind2Web: Towards a Generalist Agent for the Web
- Iteratively Prompt Pre-trained Language Models for Chain of Thought
- Homomorphic Sensing: Sparsity and Noise
- Awards: Honorable Mention at ACL-23, Oral Presentation at EMNLP-22, Spotlight at NeurIPS-23 Dataset Track
Research Experience
- May 2025 - August 2025: Microsoft GenAI, Research Intern
- June 2023 - August 2023: Semantic Machines, Research Intern
- January 2021 - June 2021: Microsoft Research Asia, Research Intern
Education
- PhD: The Ohio State University, August 2021 - Present, Advisor: Prof. Huan Sun
- Bachelor's Degree: ShanghaiTech University, Computer Science, September 2016 - July 2020
- Robotics Institute Summer Scholars: Carnegie Mellon University, June 2019 - September 2019
Background
- Research Interests: Building intelligent systems to help us better understand the world, focusing on understanding and improving the reasoning capabilities of (large) language models
- Personal Introduction: Interested in entropy and consciousness, enjoys reading 'Gödel, Escher, Bach: an Eternal Golden Braid' by Douglas Hofstadter
Miscellany
Personal Interests: Enjoys reading and thinking about entropy and consciousness