I am currently a Ph.D. candidate in Statistics at
The Pennsylvania State University
and am honored to be advised by
Prof. Lingzhou Xue.
I earned my master's degree from Penn State in 2025 and my bachelor's degree in Statistics from
Nankai University in 2023.
I was also fortunate to complete my undergraduate thesis under the supervision of
Prof. Changliang Zou.
I study how AI systems learn from feedback and experience, with a focus on self-improving agents and multimodal understanding.
Research Focus
Research directions & related papers
01 / SELF-IMPROVING AGENTS
Recursive Self-Improvement
Autonomous agents that evaluate their own work, retain useful experience, and improve their workflows across tasks.
I’ll be attending NeurIPS 2026 at the Atlanta satellite venue this December and would be happy to connect for a coffee chat—feel free to reach out. ☕
I completed my summer internship at Meta. I am grateful to my mentors Stephen Li and Yiyao Liu for their guidance on generative recommendation, and to Pengbo for involving me in the Model Development Agent project. ✨
Our paper has been accepted to ICML 2026. 🧑💻
I received a full travel award to attend MLSS NYC 2026 at Columbia University. See you in NYC this summer! 🗽
Our paper has been accepted to ICLR 2026. 🧑💻
Earlier updates 5 more
I started my internship at TikTok, focusing on multimodal understanding and exploring continual learning and agent-based automated error correction. ✨
I presented a poster at NeurIPS 2025 at the San Diego Convention Center. ☀️
I presented a poster at ICML 2025 at the Vancouver Convention Center. ☀️
I joined ByteDance Seed Infra in Seattle for a summer internship, working with
Cong Xie and
Zhi Zhang. 🧑💻
I’m thrilled to share that I’ve completed my five-month internship at Microsoft Research Asia (MSRA). I’m grateful to have worked with
Yan Lu and
Xiaoyi Zhang and honored to have received the Stars of Tomorrow award! 🧑💻
Memory for the harness optimizer: preserving why edits were made, what they were expected to fix, and what evaluation showed to support continued improvement across benchmarks and models.
2025-11-01 🎤 Co-organizer of the session “Low-Rank Adaptation for Efficient Fine-Tuning in Foundation Models” at the 2025 SIAM NNP Conference at Penn State.