Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
Publications:
- GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks
- Key-Point-Driven Data Synthesis with its Enhancement on Mathematical Reasoning
- DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models
- Competition-level Problems Are Effective LLM Evaluators
- S3Eval: A Synthetic, Scalable, Systematic Evaluation Suite for Large Language Models
- S3HQA: A Three-Stage Approach for Multi-hop Text-Table Hybrid Question Answering
- ADFA: Attention-Augmented Differentiable Top-k Feature Adaptation for Unsupervised Medical Anomaly Detection
- Spatial and Planar Consistency for Semi-Supervised Volumetric Medical Image Segmentation
Awards:
- UCSD Jacobs School of Engineering Fellowship, 2025
- USTB Principal Medal (10 out of all undergraduate graduates, highest honor of undergraduate student), 2023
- Beijing Outstanding Graduate Awards (top 1% in Academics), 2023
- National Scholarship (Top 0.2% nationwide), 2022
- National Scholarship (Top 0.2% nationwide), 2021
- National Scholarship (Top 0.2% nationwide), 2020
Research Experience
Worked as a research intern at TikTok, collaborating with Dr. Qian Liu. Previously spent time at Microsoft Research Asia, working with Dr. Xiao Liu, Dr. Yeyun Gong, and Dr. Weizhu Chen.
Education
PhD student at UC San Diego, advised by Prof. Jingbo Shang
Background
Research interests include evaluating and enhancing the reasoning capabilities of large language models, particularly in code, math, and agent tasks; exploring data-centric methods to improve learning efficiency and adaptability.