Embodied AI Researcher at Unitree Robotics
I work on the continued pre-training of vision-language models (VLM), vision-language-action models (VLA), and world-action models (WAM), with a focus on embodied intelligence and general-purpose robots.
I obtained my M.Eng. from the College of Control Science and Engineering at Zhejiang University in 2023 and my B.Eng. in Automation from Harbin Institute of Technology in 2019. My current research primarily focuses on Embodied AI. I am also interested in deep stereo matching, feed-forward 3D reconstruction, and video world models.
General-Purpose Humanoid Robot Foundation Model 🔥
UnifoLM-WLA-1.0 is Unitree Robotics' comprehensively upgraded, next-generation general-purpose humanoid robot foundation model with 6B parameters. Trained on approximately 2,500 hours of high-quality real-robot data, a single model coordinates 64 tasks spanning desktop manipulation and whole-body manipulation.
Project pageA Vision-Language-Action Model for General-Purpose Manipulation
UnifoLM-VLA-0 is a Vision–Language–Action (VLA) large model in the UnifoLM series, designed for general-purpose humanoid robot manipulation.
Project page
2026The International Journal of Robotics Research (IJRR), 2026 🔥
We present the first photo-realistic LiDAR-Inertial-Camera Gaussian Splatting SLAM that jointly addresses visual quality, geometric accuracy, and real-time performance.
2022
