About Me
I am currently a second-year M.S. student (with thesis) in Computer Science at University of Illinois Urbana-Champaign (UIUC). I am a member of iDEA-iSAIL Lab, advised by Prof. Jingrui He. Prior to this, I earned my B.S. with highest honors in Computer Engineering at UIUC. I have been fortunate to work with Prof. Mengdi Wang at Princeton University, and Prof. James Zou at Stanford University. Currently, I am a student researcher at Google DeepMind. I also held research internships at Amazon and Microsoft Research before.
My research lies in the intersection of machine learning and natural language processing, with a specific focus on LLMs Reasoning. My research interests include but not limit to:
- Agentic AI: single/multi-agent systems, tool integrated LLMs.
- LLM Post-Training: RLHF, reward modeling.
- Data-Centric Learning: structure/multimodal data representation learning, effecient data selection and pruning.
- Scientific Foundation Models: AI for X (social science, weather forecasting, agriculture, clinic discovery, etc.).
I’m always happy to connect! Feel free to email me if you’d like to discuss my research interests or potential collaborations. Let’s cook up something cool together! 👨🏻🍳
📢 News
[10/2025] Check TaTToo, a special tool-grounded thinking PRM for test time scaling in tabular reasoning.
[10/2025] Small model, Big mind 🧠. Check our new analytic study on Agentic RL.
[10/2025] Check RAG Over Tables, a coarse-to-fine hierarchical Graph-Table-RAG framework with a new benchmark.
[09/2025] Two papers accepted at NeurIPS 2025, including Transformer Copilot (spotlight paper, top 3%) and ReasonFlux-PRM.
[08/2025] Start my internship as a student researcher at Google DeepMind GenAI team.
[05/2025] Start my internship as an applied scientist at Amazon.
[05/2025] One paper accepted at ACL 2025: STEM-PoM, a benchmark on math-symbol reasoning.
📄 Selected Publications (Full List)
(* denotes Equal Contribution)
 Preprint | Demystifying Reinforcement Learning in Agentic Reasoning |
 FoRLM@NeurIPS 2025 | TaTToo: Tool-Grounded Thinking PRM for Test-Time Scaling in Tabular Reasoning |
 Preprint | RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking |
 NeurIPS 2025 (Spotlight) | Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning |
 NeurIPS 2025 | ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs |
 ACL 2025 | STEM-PoM: Evaluating Language Models Math-Symbol Reasoning in Document Parsing |
 NeurIPS 2024 | PageRank Bandits for Link Prediction |
 EMNLP 2024 | PromptIntern: Saving Inference Costs by Internalizing Recurrent Prompt during LLM Fine-tuning |
 EMNLP 2024 | TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning |
💼 Selected Experience
Princeton AI Lab Research Assistant, 2025 Research Topic: Process Reward Model, LLM Agents |  |
Google DeepMind Student Researcher (part-time), 2025 Research Topic: Agentic RL, GUI Agent, AI for Science |  |
Amazon Applied Scientist Intern, 2025 Research Topic: Reward Modeling, Speculative Decoding |  |
Microsoft Research Research Intern, 2023-2024 Research Topic: Stucture data representation learning, Code generation, Prompt Compression, Data Pruning |  |
✨ Honors & Awards
- NeurIPS 2025 Scholar Award, 2025
- Highest Honor Graduation at UIUC, 2024
- Microsoft Stars of Tomorrow Award, 2023
- O. Thomas and Martha S. Purl Scholarship, 2023
- Daniel W. and Carol A. Dobberpuhl Student Award, 2023
- Illinois Engineering Outstanding & Achievement Scholarship, 2023
- Professor N. Narayana Rao Scholarship, 2022
- Edmund J. James Scholarship, 2021
🌍 Academic Services
Conference Program Committee/Reviewer: ICLR 2026, AAAI 2026, NeurIPS 2025, ICML 2025, ARR Rolling Review (Oct 2024, Dec 2024, May 2025, July 2025, Oct 2025)
Journal Reviewer: IEEE Transactions on Knowledge and Data Engineering (TKDE), ACM Transactions on Knowledge Discovery from Data (TKDD), ACM Computing Surveys
Conference Student Volunteer: EMNLP’24, NeurIPS’24
Teaching Experience:
- Graduate Teaching Assistant: UIUC CS307 (Fall 2024), UIUC CS128 (Spring 2025)
- Course Assistant/Grader: UIUC CS/ECE374 (Head CA), ECE210, ECE310, ECE313
🧩 Miscellaneous
I’m a boarder through and through — 🏂 snowboarding is my favorite ride (my setup: Burton Custom X Flying V for all-mountain ride, and YES BASIC for freestyle and park ride). You’ll also find me carving pavement on a skateboard or chasing waves on a surfboard. Maybe one day I’ll earn my spot as an X-Gamer . Some of my riding pictures below:
I am also a fan of 📸 Conceptual Photography and 🎨 Visual Aesthetics.
🌍 Visitors around the world