I study how learning systems reason, evaluate, and improve.
I am a researcher at the Shanghai Academy of AI for Science (SAIS) and a master's student at the National University of Singapore.
My research focuses on reinforcement learning, trustworthy language models, and reliable evaluation for reasoning systems.
Publications
TrustJudge: Inconsistencies of LLM-as-a-Judge and How to Alleviate Them
We identify two fundamental inconsistencies in LLM-as-a-judge evaluation: Score-Comparison inconsistency and Pairwise Transitivity inconsistency. We propose TrustJudge, a probabilistic framework with distribution-sensitive scoring and likelihood-aware aggregation to alleviate these issues and improve reliability of automated assessment.
RAGLAB: A Modular and Research-Oriented Unified Framework for Retrieval-Augmented Generation
Two major obstacles hinder RAG's progress: (1) lack of thorough and fair comparisons between emerging RAG algorithms; (2) high-level abstractions in open-source tools reduce transparency and limit innovation. We introduce RAGLAB, a modular, research-focused open-source library that replicates existing algorithms and provides an ecosystem for exploring RAG techniques, enabling fair comparisons across benchmarks.
Talks
Multi-UAV Multi-Target Cooperative Interception via Multi-Agent RL with Reward Shaping and LLM-Based Curriculum Learning
Open seminar pageJourney
-
2026.08 – now
Researcher, Shanghai Academy of AI for Science (SAIS)
Shanghai, China
-
2025.12 – 2026.07
Research Intern, Hunyuan, Tencent
Shenzhen, China
-
2025.01 – 2026.07
M.Sc. in Robotics
National University of Singapore, Singapore Temasek Laboratories @ NUS, Singapore
-
2023.11 – 2024.11
Research Intern, Peking University
Beijing, China
-
2023.05 – 2023.09
Research Intern, Westlake University
Hangzhou, China
-
2019.09 – 2023.07
B.Sc. in Computer Science and Technology
Xi'an Jiaotong-Liverpool University, Suzhou, China University of Liverpool, United Kingdom