I am currently a second-year PhD student at ASI Lab, National University of Singapore, mentored by Prof. Dianbo Liu. I received my master's degree from the Department of Automation, Tsinghua University, advised by Prof. Xiangyang Ji, where I worked on unsupervised learning and human motion generation.
My research interests lie in Autonomous AI Research, Representation Learning, and Multimodality & Generative Models, with the broader goal of building AI Scientists that can transform how scientific research is conducted.
- Autonomous AI Research: Enable AI to autonomously conduct research and improve AI itself.
- Representation Learning: Equip AI with structured and generalizable representations to better understand and reason about scientific problems.
- Multimodality & Generative Models: Enable AI to interact with complex real-world environments through diverse modalities for scientific discovery.
News
- [2026] Our paper FML-bench, a controlled study of AI research agent strategies, is accepted to NeurIPS 2026.
- [2026] Our paper LanSE on human-like content analysis for generative AI is accepted to npj Artificial Intelligence.
- [2026] Our paper HypoSpace on evaluating LLMs as set-valued hypothesis generators is accepted to ICML 2026 (Spotlight).
Selected Publications
Full list on Google Scholar
NeurIPS 2026
NeurIPS 2026
ICML 2026
Spotlight
ICML 2026. Spotlight.
npj AI
npj Artificial Intelligence, 2026. To appear.
NeurIPS Workshop
NeurIPS Safe Generative AI Workshop, 2024
AAAI 2023
Oral
AAAI 2023. Main Track.
Nanotechnology
Nanotechnology (Journal), 2021
Services
Conference Reviewer: ICLR'25, AAAI'26, ICLR'26, ICML'26