About Me
I am a first-year PhD student at UC San Diego, advised by Prof. Prithviraj Ammanabrolu and Prof. Hao Zhang. I received my B.E. in Computer Science and Technology from Tsinghua University. Previously, I was a research intern at XLANG Lab advised by Prof. Tao Yu, and interned at Qwen mentored by Binyuan Hui.
My research focuses on building multimodal digital agents that can perceive, reason, and execute long-horizon tasks across diverse interfaces. I work on:
- Foundation models for digital agents, e.g. [Aguvis], [OpenCUA] and [Mocha-Coder].
- Scaling digital agent data through large-scale synthetic data mined from the internet, e.g. [AgentTrek], [VideoAgentTrek], and [Jedi].
- Evaluating digital agents in the wild, e.g. [OSWorld-Verified], [Computer Agent Arena], and [CocoaBench].
- Open-source infrastructure that makes agent rollout and learning practical at scale, such as [NanoRollout].
Beyond my own projects, I have contributed to post-training open-source foundation models for agentic capabilities, including [Qwen3.5] and [Qwen3-Coder]. I mostly work on agentic RL infrastructure that enables agent rollouts in large-scale digital environments, and data cleaning and selection that makes agentic post-training effective.
News
-
[May. 2026] Checkout our new project [NanoRollout] and model [Mocha-Coder] for efficient digital agent rollouts at scale!
-
[March. 2025] I will join UC San Diego as a PhD student in
Fall 2025Winter 2026.
Selected Projects
Publications
-
TL;DR: VideoAgentTrek mines screen-recorded internet videos into labeled computer-use actions through inverse dynamics, creating web-scale supervision that improves agent pretraining without manual trajectory annotation.International Conference on Learning Representations (ICLR), 2026.
-
TL;DR: CocoaBench evaluates unified digital agents on long-horizon tasks that require composing vision, search, and coding, showing that current systems remain far from reliable in the wild.
-
TL;DR: Computer Agent Arena is an open-source platform for head-to-head CUA evaluation and a dynamic methodology that converts human preferences into structured feedback in realistic environments.International Conference on Learning Representations (ICLR), 2026.
-
TL;DR: OSWorld-Verified upgrades OSWorld with repaired tasks, more robust infrastructure, and public verified evaluation to provide more reliable signals for computer-use agent benchmarking.
-
TL;DR: OpenCUA releases an open framework for computer-use agents, including demonstration-capture infrastructure, AgentNet data, reasoning-augmented training pipelines, and competitive open-source CUA models.Neural Information Processing Systems (NeurIPS), 2025.
-
TL;DR: Aguvis builds a unified vision-based GUI agent that operates directly on screenshots with a standardized action space and structured reasoning, achieving strong cross-platform autonomous computer-use performance.International Conference on Machine Learning (ICML), 2025.
-
TL;DR: AgentTrek turns web tutorials into verified multimodal GUI agent trajectories, providing a scalable and low-cost alternative to human annotation for training stronger web agents.International Conference on Learning Representations (ICLR), 2025.
Powered by Jekyll and Minimal Light theme.