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 July 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. Preprint.
• RSS 2026 Data-Centric WorkshopBest Paper Award
• RSS 2026 It’s The DemosMost 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 TCBest Paper Award 2024.

PDF Cite Video DOI

Publications

(2026). Training and Evaluating Diffusion Policies with Long Context Lengths. Preprint.

PDF Cite Project

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

PDF Cite Project