I am a senior undergraduate at Department of Electronic Engineering, Tsinghua University.
I am currently visiting UC Berkeley and Berkeley AI Research (BAIR), working with Haoran Geng and advised by Prof. Jitendra Malik and Prof. Pieter Abbeel. Previously, I had the privilege to work as an undergraduate research intern under the supervision of Prof. Yue Wang.

My interests focus on Robot Learning and Embodied Intelligence, with a focus on how robots can acquire and use world knowledge to act reliably in open-ended environments, and how this process can become a data flywheel for scalable robotic systems.

• Leveraging Human World Knowledge for Scalable Robotic Perception: How to make use of multiple sources of data such as human demonstrations, foundation models, Internet data, and synthetic data? How to leverage these abundant, low-cost data into universal perceptual priors for scalable robotic systems?
• Robotic Action and Interaction: How to understand the modality of action, thus unifying low-level control with high-level reasoning? How can we model the semantics, dependencies, and affordances of robotic actions to seek robust and generalizable robotic behavior?
• Reinforcement Learning for Embodied Knowledge Acquisition: How can we scale RL to turn it into an engine for autonomous robotic data collection, forming a self-improving data flywheel that continually strengthens generalizability of robotic perception and control?

I am seeking a Ph.D. position starting from Fall 2026! Feel free to drop me an email if you are interested in my research or have any questions!