Adam Wei

Adam Wei

EECS Ph.D. Candidate

MIT

Biography

I am a third year Ph.D. student at MIT advised by Prof. Russ Tedrake. I am currently interning at Physical Intelligence.

My research focuses on two main directions: 1) understanding and improving how different data sources can be used in robot imitation learning; and 2) algorithmic improvements for generative modeling in robotics with a focus on learning from out-of-distribution or low-quality data. Prior to MIT, I worked on model-based control for contact-rich systems with Prof. Michael Posa.

I am grateful to be funded by the NSF Graduate Research Fellowship and the NSERC Postgraduate Scholarship (Doctoral).

CV (last updated September 2026)

Interests
  • Robotics
  • Imitation Learning
  • Generative Modeling
  • Controls
Education
  • EECS Ph.D. Candidate, 2023-Present

    MIT

  • B.Eng in Electrical Engineering, 2023

    University of Toronto

  • IB Diploma, 2019

    Colonel By Secondary School

Selected Publications

(2026). Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics. CoRL 2026.
• RSS 2026 Data-Centric Workshop — Best Paper Award
• RSS 2026 It’s The Demos — Most Useful Practical Information Award.

PDF Cite Project Poster Slides

(2025). Empirical Analysis of Sim-and-Real Cotraining Of Diffusion Policies For Planar Pushing from Pixels. IROS 2025.

PDF Cite Code Project Slides

(2024). Consensus Complementarity Control for Multicontact MPC. IEEE Transactions on Robotics.
• IEEE RAS TC — Best Paper Award 2024.

PDF Cite Video DOI

Publications

(2026). Training and Evaluating Diffusion Policies with Long Context Lengths. Preprint.
• HAND ERC — Fernando Family Best Paper Award 2026.

PDF Cite Project

(2025). How Well do Diffusion Policies Learn Kinematic Constraint Manifolds?. ICRA 2026.
• IROS 2025 RODGE Workshop — Best Poster Award.

PDF Cite Project