Yilun Du


Email: yilundu@mit.edu
Github: Github


I am a first year graduate student at MIT coadvised by Leslie Kaelbling, Tomas Lozano-Perez and Joshua Tenenbaum. Iā€™m interested in attempting to build intelligent robotic agents that can perceive and interact with the world around them.

In the past, I was a research collaborator at FAIR, a fellow at OpenAI and received gold medals at the International Biology Olympiad.


  1. Unsupervised Discovery of 3D Physical Objects from Video
    Yilun Du, Kevin Smith, Tomer Ulman, Joshua Tenenbaum, Jiajun Wu
  2. A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects
    Anthony Simeonov, Yilun Du, Beomjoon Kim, Francois Hogan, Joshua Tenenbaum, Pulkit Agrawal, Alberto Rodriguez CORL 2020
  3. Compositional Visual Generation with Energy Based Models
    Yilun Du, Shuang Li, Igor Mordatch
    NeurIPS 2020 (Spotlight)
  4. Energy-based models for atomic-resolution protein conformations
    Yilun Du, Joshua Meier, Jerry Ma, Rob Fergus, Alexander Rives
    ICLR 2020 (Spotlight)
    Machine Learning in Computional Biology Workshop (Oral / Travel Award)
  5. Observational Overfitting in Reinforcement Learning
    Xingyou Song, Yiding Jiang, Yilun Du, Behnam Neyshabur
    ICLR 2020
    NeurIPS 2019 Workshop on Optimization Frontiers of Reinforcement Learning
  6. Implicit Generation and Generalization with Energy Based Models
    Yilun Du, Igor Mordatch
    NeurIPS 2019 (Spotlight)
    NeurIPS 2018 Workshop on Bayesian Deep Learning
  7. Model Based Planning with Energy Based Planning
    Yilun Du, Toru Lin, Igor Mordatch
    CORL 2019
    ICML 2019 Workshop on Generative Modeling and Model-Based Reasoning for Robotics and AI (Oral)
  8. An Empirical Study on Hyperparameters and their Interdependence for RL Generalization
    Xingyou Song, Yilun Du, Jacob Jackson
    ICML 2019 Workshop on Understanding and Improving Generalization in Deep Learning
  9. Learning Physics Priors for Deep Reinforcement Learing
    Yilun Du, and Karthik Narasimhan
    ICML 2019
    SPiRL Workshop ICLR 2019
  10. Neural MMO: A massively multiplayer game environment for intelligent agents
    Joseph Suarez, Yilun Du, Philip Isola, Igor Mordatch
    Code AAMAS 2020
  11. Learning to Exploit Stability for 3D Scene Parsing
    Yilun Du, Zhijian Liu, Hector Basevi, Ales Leonardis, William T. Freeman, Joshua B. Tenenbaum, Jiajun Wu
    NeurIPS 2018
  12. Interpreting Dynamic Scenes by a Physics Engine and Bottom-Up Visual Cues
    Ilker Yildirim*, Jiajun Wu*, Yilun Du, Joshua B. Tenenbaum
    ECCV 2016 Workshop on Action and Anticipation for Visual Learning