Publications

Conference Papers

• LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations Anian Ruoss, Fabio Pardo, Harris Chan, Bonnie Li, Volodymyr Mnih, Tim Genewein. In International Conference on Machine Learning (ICML) 2025.
• STEVE-1: A Generative Model for Text-to-Behavior in Minecraft Shalev Lifshitz, Keiran Paster, Harris Chan, Jimmy Ba, Sheila McIlraith. In Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS) 2023 (Spotlight).
• Robotic Skill Acquisition via Instruction Augmentation with Vision-Language Models Ted Xiao, Harris Chan, Pierre Sermanet, Ayzaan Wahid, Anthony Brohan, Karol Hausman, Sergey Levine, Jonathan Tompson. In Robotics: Science and Systems (RSS) 2023.
• Large language models are human-level prompt engineers Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han*, Keiran Paster, Silviu Pitis, Harris Chan, Jimmy Ba. In International Conference on Learning Representations (ICLR) 2023.
• Inner monologue: Embodied reasoning through planning with language models. Wenlong Huang, Fei Xia, Ted Xiao*, Harris Chan, Jacky Liang, Pete Florence, Andy Zeng, Jonathan Tompson, Igor Mordatch, Yevgen Chebotar, Pierre Sermanet, Noah Brown, Tomas Jackson, Linda Luu, Sergey Levine, Karol Hausman, Brian Ichter. In Conference on Robot Learning (CoRL) (CoRL) 2022.
• Learning Domain Invariant Representations in Goal-conditioned Block MDPs. Beining Han, Chongyi Zheng, Harris Chan, Keiran Paster, Michael R. Zhang, Jimmy Ba. In Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS) 2021.
• Multichannel Generative Language Models. Harris Chan, Jamie Kiros, William Chan. In Findings of the 2020 Conference on Empirical Methods in Natural Language Processing (Findings of EMNLP) 2020.
• Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning. Silviu Pitis*, Harris Chan*, Stephen Zhao, Bradly Stadie, Jimmy Ba.
  In International Conference on Machine Learning (ICML) 2020.
• An Inductive Bias for Distances: Neural Nets that Respect the Triangle Inequality
  Silviu Pitis*, Harris Chan*, Kiarash Jamali, Jimmy Ba.
  In International Conference on Learning Representations (ICLR) 2020.
• Interplay Between Optimization and Generalization of Stochastic Gradient Descent with Covariance Noise
  Yeming Wen*, Kevin Luk*, Maxime Gazeau*, Guodong Zhang, Harris Chan, Jimmy Ba. In International Conference on Artificial Intelligence and Statistics (AISTATS) 2020.

Preprints or Submission

• ACTRCE: Augmenting Experience via Teacher’s Advice For Multi-Goal Reinforcement Learning
  Harris Chan*, Yuhuai Wu*, Jamie Kiros, Jimmy Ba.
  arXiv preprint arXiv:1902.04546, 2019.

Workshops

• Vision-Language Models as a Source of Rewards Kate Baumli, Satinder Singh, Feryal Behbahani, Harris Chan, Gheorghe Comanici, Sebastian Flennerhag, Maxime Gazeau, Kristian Holsheimer, Dan Horgan, Michael Laskin, Clare Lyle, Volodymyr Mnih, Alexander Neitz, Fabio Pardo, Jack Parker-Holder, John Quan, Tim Rocktäschel, Himanshu Sahni, Tom Schaul, Yannick Schroecker, Stephen Spencer, Richie Steigerwald, Luyu Wang, Lei Zhang In Agent Learning in Open-Endedness (ALOE) Workshop (ALOE) 2023 at NeurIPS 2023.
• A Generative Model for Text Control in Minecraft and A Generative Model for Text Control in Minecraft (Abridged Version) Shalev Lifshitz, Keiran Paster, Harris Chan, Jimmy Ba, Sheila A. McIlraith In Interactive Learning with Implicit Human Feedback (ILHF) 2023 and Workshop on Structured Probabilistic Inference & Generative Modeling at ICML 2023.
• Skill Acquisition via Instruction Augmentation with Vision-Language Models Ted Xiao, Harris Chan, Pierre Sermanet, Ayzaan Wahid, Anthony Brohan, Karol Hausman, Sergey Levine, Jonathan Tompson. In Foundation Models for Decision Making (FMDM) 2022.
• Large language models are human-level prompt engineers Yongchao Zhou, Andrei Ioan Muresanu, Ziwen Han*, Keiran Paster, Silviu Pitis, Harris Chan, Jimmy Ba In Foundation Models for Decision Making (FMDM) 2022.
• Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning Silviu Pitis*, Harris Chan*, Stephen Zhao, Bradly Stadie, Jimmy Ba. In Adaptive and Learning Agents Workshop. Workshop held at International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2020. (Oral, Best Paper Award). [Presentation]
• Multilingual KERMIT: It’s Not Easy Being Generative
  Harris Chan, Jamie Kiros, William Chan.
  In Perception as generative reasoning Workshop, workshop held at Neural Information Processing Systems (NeurIPS), 2019. And i 3rd Workshop on Neural Machine Translation and Generation (WNMT)*, workshop held at EMNLP-IJCNLP, 2019.
• Auto-regressive Graph Generation Modeling with Improved Evaluation Methods
  Chia-Cheng Liu*, Harris Chan*, Kevin Luk.
  In Graph Representation Learning Workshop. Workshop held at Neural Information Processing Systems (NeurIPS), 2019.
• ProtoGE: Prototype Goal Encodings for Multi-goal Reinforcement Learning
  Silviu Pitis*, Harris Chan*, Jimmy Ba.
  In 4th Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM), 2019.
• ACTRCE: Augmenting Experience via Teachers’ Advice
  Yuhuai Wu, Harris Chan, Sanja Fidler and Jimmy Ba.
  In 1st Workshop on Goal Specifications for Reinforcement Learning. Workshop held jointly at ICML, IJCAI, AAMAS 2018 (Oral)
• Investigating the impact of intrusion detection system performance on communication latency and power system stability
  Harris Chan, Eman Hammad, Deepa Kundur.
  In Proceedings of the Workshop on Communications, Computation and Control for Resilient Smart Energy Systems, 2016 (Oral)