Hello! I am a CS Ph.D. Student at University of California San Diego (UCSD). I am fortunate to be advised by Lianhui Qin. I obtained my Bachelor of Science degree from the Paul G. Allen School of Computer Science at the University of Washington (UW), Seattle. During my undergraduate time, I was fortunate to work closely with Luke Zettlemoyer and Terra Blevins, who provided invaluable mentorship and guidance in my early research endeavors.
I am interested in securing a summer research internship in the industry. If you know of any relevant openings or could provide an introduction, I would deeply appreciate your support.
News
- [2026.02] New preprint: LaDi-RL — diversity-preserving RL via latent diffusion reasoning.
- [2026.01] LaDiR accepted to ICLR 2026.
- [2026.01] New preprint: TSRBench — multi-task multi-modal time series reasoning benchmark.
- [2025.11] New preprint: PAN — a world model for general, interactable, long-horizon simulation.
- [2025.06] Started as a Student Researcher at Google DeepMind, working on latent reasoning for vision-language models.
- [2025.02] GFlowVLM accepted to CVPR 2025.
- [2025.05] Flow of Reasoning accepted to ICML 2025.
- [2024.09] FinBen accepted to NeurIPS 2024 Datasets and Benchmarks Track.
- [2024.05] Started as a Research Intern at Honda Research Institute, working on GFlowNets for VLM reasoning.
- [2024.01] Translate to Disambiguate accepted to EACL 2024 as an Oral presentation.
Research Interests
- RL Post-Training: Diversity and exploration in reinforcement learning for large model post-training
- Latent Reasoning: Developing latent reasoning paradigms for language and vision-language models
- Embodied Coding Agent: Building intelligent agents that solve practical real-world tasks
Experience
Google DeepMind | Jun 2025 – Sep 2025
Position: Student Researcher
Topic: Latent Reasoning for Vision Language Models
Host: Yinpeng Chen
Honda Research Institute, USA | May 2024 – Sep 2024
Position: Research Intern
Topic: GFlowNets Post-Training for Reasoning in Vision-Language Models
Hosts: Kwonjoon Lee and Enna Sachdeva
Feel free to reach out to me for collaborations, discussions, or even a casual chat about research!