Publications: 'When Human Gold Breaks: Co-Evolving Agents and Benchmarks for Evaluating Factuality in Deep Research Reports' and other papers under review or accepted to ICLR 2025.
Research Experience
Internships at Amazon AGI and ByteDance.
Education
PhD: Duke University, advised by Prof. Bhuwan Dhingra; Master’s degree: Columbia University, advised by Prof. Zhou Yu and Prof. Kathleen McKeown; Bachelor’s degree: Tsinghua University.
Background
Research Interests: Improving the factuality, reliability, and efficiency of large language models (LLMs) with the goal of making them more trustworthy and practical for real-world use. Personal Background: Third-year CS PhD student at Duke University.