Yilang Liu — Robotics Ph.D. Candidate at Yale University

Hi! I'm a Ph.D. candidate in Mechanical Engineering at Yale University, advised by Prof. Ian Abraham.

I develop robot learning systems that combine sampling-based control, visual policies, and coding agents for locomotion and dexterous manipulation. My work spans vision-language-action models, simulation-to-real transfer, and autonomous exploration.

I'm on the job market for full-time positions and expect to graduate in 2027. Please see my CV. If you think I'd be a good fit for your team, please reach out!

News

Sep 2026Introducing EmbodiedSWE: coding agents for long-horizon dexterous robotics.
Sep 2026Our Sampling-Guided Policy Search paper is available on arXiv.
Sep 2026SDPG accepted to CoRL 2026.

May 2026Our ergodic coverage paper accepted to RSS 2026.
Jan 2026Sample-Based Hybrid Mode Control accepted to ICRA 2026.
Sep 2025D.Va accepted to NeurIPS 2025 as a Spotlight.

Selected Publications

Zeyu Shen*, Haoxiang You*, Yilang Liu*, Zhicheng Zheng, Lihan Zha, Kashu Yamazaki, Mingtong Zhang, Suning Huang, Jiankai Sun, Qianzhong Chen, Lucy He, Haoran Chang, Dhruv Shah, Mac Schwager, Katerina Fragkiadaki, Peter Henderson, Ian Abraham, Canwen Xu. "EmbodiedSWE: Coding Agents for Long-Horizon Dexterous Robotics." Under review, 2026 (* equal contribution). Project pageCoding agents solve long-horizon robotics tasks and generate demonstrations for vision-language-action policies.

Yilang Liu, Haoxiang You, Qian Wang, Daniel Rakita, Ian Abraham. "Accelerating Visual Policy Learning with Sampling-Based Model Predictive Control." Under review, 2026. arXiv:2609.20575Sampling-guided visual policy learning enables zero-shot locomotion on a real quadruped.

Haoxiang You*, Yilang Liu*, Davis Zong, Qian Wang, Teeratham Vitchutripop, Qi Wang, Daniel Rakita, Ian Abraham. "Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient." CoRL 2026. arXiv:2605.26478Visual reinforcement learning reduces GPU memory use and transfers zero-shot to a real quadruped.

Christian Hughes, Yilang Liu, Yanis Lahrach, Julia Engdahl, Houston Warren, Darrick Lee, Fabio Ramos, Travis Miles, Ian Abraham. "Asymptotically Optimal Ergodic Coverage on Generalized Motion Fields." RSS 2026. arXiv:2605.13442Flow-aware trajectory planning enables robotic coverage in environments with changing motion fields.

Yilang Liu, Haoxiang You, Ian Abraham. "Sample-Based Hybrid Mode Control: Asymptotically Optimal Switching of Algorithmic and Non-Differentiable Control Modes." ICRA 2026. arXiv:2510.19074Sampling-based control switches between locomotion modes to execute agile quadruped skills.

Haoxiang You, Yilang Liu, Ian Abraham. "Accelerating Visual-Policy Learning through Parallel Differentiable Simulation." NeurIPS 2025 (Spotlight). arXiv:2505.10646Parallel differentiable simulation accelerates visual policy learning without differentiating through rendering.

Yilang Liu, Amir Barati Farimani. "An Energy-Saving Snake Locomotion Gait Policy Obtained Using Deep Reinforcement Learning." Journal of Mechanisms and Robotics, 2023. arXiv:2103.04511Model-based reinforcement learning discovers energy-efficient locomotion for a simulated snake robot.

Experience

Dexmate Inc.

Oct 2025 – Jan 2026

Robotics Intern · Santa Clara, CA

Education

Yale University

Expected May 2027

Ph.D. in Mechanical Engineering · Candidate
Carnegie Mellon University

May 2022

M.S. in Mechanical Engineering · Research Program
University of Cincinnati & Chongqing University

Apr 2020

Dual-degree program

B.S. in Mechanical Engineering, cum laude — University of Cincinnati
B.E. in Mechanical Design, Manufacture and Automation — Chongqing University