Adam Lerer Senior Research Engineer DeepMind email: adam.lerer [at] gmail.com [Scholar] [Github] [Twitter]

I am a principal research engineer at Meta AI. I co-led the FAIR Diplomacy team that developed CICERO, a human-level AI for the game of Diplomacy. Previously, I developed state-of-the-art agents for Poker, Hanabi, and no-press Diplomacy.

I developed PyTorch-Big-Graph (PBG), a system for large-scale multi-relation graph embeddings used by dozens of teams at Facebook. PBG is released as an open source package and is in active use by other large organizations.

I am a member of the original PyTorch developer team, and previously a contributor to LuaTorch.

Recently, I have been collaborating with the Meta AI Protein team and with external collaborators on machine learning for biology applications.

Prior to Meta/FAIR, I was a member of the embedded software team at D. E. Shaw Research, where I helped to develop and validate algorithms and numerics for the Anton supercomputers, which use custom ASICs specialized for molecular dynamics simulations.

I graduated from MIT with a B.S. in Computer Science and Physics and an M. Eng in Computer Science.

Selected Publications

• Human-level play in the game of Diplomacy by combining language models with strategic reasoning.
  FAIR et al. (co-corresponding author)
  Science, 2022.
• Learning inverse folding from millions of predicted structures
  C. Hsu, R. Verkuil, J. Liu, Z. Lin, B. Hie, T. Sercu, A. Lerer*, A. Rives* (*Equal advising)
  International Conference on Machine Learning (ICML), 2022.
• No-Press Diplomacy from Scratch
  A. Bakhtin, D. Wu, A. Lerer, N. Brown
  Neural Information Processing Systems (NeurIPS), 2021
• CryoDRGN2: Ab initio neural reconstruction of 3D protein structures from real cryo-EM images.
  E. Zhong, A. Lerer, J. H. Davis, B. Berger
  International Conference on Computer Vision (ICCV), 2021.
• Human-Level Performance in No-Press Diplomacy via Equilibrum Search
  J. Gray*, A. Lerer*, A. Bakhtin, N. Brown (*Equal contribution)
  International Conference on Learning Representations (ICML), 2020
• The u-series: A separable decomposition for electrostatics computation with improved accuracy
  C. Predescu, A. Lerer, R. A. Lippert, B. Towles, J. P. Grossman, R.M. Dirks, D. Shaw
  Journal of Chemical Physics (JCP), 2020
• Improving Policies via Search in Cooperative Partially-Observable Games
  A. Lerer, H. Hu, J. Foerster, N. Brown
  AAAI Conference on Artificial Intelligence, 2020
• PyTorch-BigGraph: A Large-scale Graph Embedding System
  A. Lerer, L. Wu, J. Shen, T. Lacroix, L. Wehrstedt, A. Bose, A. Peysakhovich
  Proceedings of the Conference on Systems and Machine Learning (SysML), 2019
• Learning Existing Social Conventions via Observationally Augmented Self-Play
  A. Lerer*, A. Peysakhovich* (*Equal contribution)
  AAAI/ACM Conference on AI, Ethics, and Society, 2019
• Pytorch: An imperative style, high-performance deep learning library
  A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, ..., S. Chintala
  Neural Information Processing Systems (NeurIPS), 2019
• Deep Counterfactual Regret Minimization
  N. Brown*, A. Lerer*, S. Gross, T. Sandholm (*Equal contribution)
  International Conference on Machine Learning (ICML), 2018
• Maintaining cooperation in complex social dilemmas using deep reinforcement learning
  A. Lerer*, A. Peysakhovich* (*Equal contribution)
  arXiv, 2017
• Composable planning with attributes
  Amy Zhang*, A. Lerer*, S. Sukhbaatar, R. Fergus, A. Szlam (*Equal contribution)
  International Conference on Learning Representations (ICLR), 2018
• Learning physical intuition of block towers by example
  A. Lerer, S. Gross, R. Fergus
  International Conference on Machine Learning (ICML), 2016
• Anton 2: raising the bar for performance and programmability in a special-purpose molecular dynamics supercomputer
  D. E. Shaw, ..., A. Lerer, ...
  International Conference for High Performance Computing, Networking, Storage and Analysis (SC), 2014
• Open data kit; tools to build information services for developing regions
  C. Hartung, A. Lerer, Y. Anokwa, C. Tseng, W. Brunette, G. Borriello
  International Conference on Communication Technologies and Development (ICTD), 2010
• Tabulator: Exploring and Analyzing Linked Data on the Semantic Web
  T. Berners-Lee, Y. Chen, L. Chilton, D. Connolly, R. Dhanaraj, J. Hollenbach, A. Lerer, and D. Sheets
  Proceedings of the 3rd Int. Semantic Web User Interaction Conf., 2006