I am a research scientist in the Fundamental AI Research (FAIR) group at Meta in NYC and study foundational topics in machine learning and optimization, recently involving reinforcement learning, control, optimal transport, and geometry. My research is on learning systems that understand and interact with our world and focuses on integrating structural information and domain knowledge into these systems to represent non-trivial reasoning operations.
2014 - 2019
Ph.D. in Computer Science, Carnegie Mellon University
(0.00/0.00)
|
2011 - 2014
B.S. in Computer Science, Virginia Tech
(3.99/4.00)
|
2024
Visiting Lecturer, Cornell Tech, New York City |
2016 - 2019
Research Assistant, Carnegie Mellon University (with J. Zico Kolter on ML and optimization) |
2018
Research Intern, Intel Labs, Santa Clara (with Vladlen Koltun on computer vision) |
2017
Research Intern, Google DeepMind, London (with Nando de Freitas and Misha Denil on RL) |
2014 - 2016
Research Assistant, Carnegie Mellon University (with Mahadev Satyanarayanan on mobile systems) |
2014
Research Intern, Adobe Research, San Jose (with David Tompkins on distributed systems) |
2013 - 2014
Research Assistant, Virginia Tech (with Layne Watson and David Easterling on optimization) |
2012 - 2014
Research Assistant, Virginia Tech (with Jules White and Hamilton Turner on mobile systems) |
2012 - 2014
Research Assistant, Virginia Tech (with Binoy Ravindran and Alastair Murray on compilers) |
2013 - 2014
Software Intern, Snowplow (Scala development) |
2013
Software Intern, Qualcomm, San Diego (Python and C++ development) |
2012
Software Intern, Phoenix Integration, Virginia (C++, C#, and Java development) |
2011
Network Administrator Intern, Sunapsys, Virginia |
2022
|
2022
|
2019
|
2016 - 2019
NSF Graduate Research Fellowship
|
2011 - 2014
Nine undergraduate scholarships
Roanoke County Public Schools Engineering, Salem-Roanoke County Chamber of Commerce, Papa John's, Scottish Rite of Freemasonry, VT Intelligence Community Conter for Academic Excellence, VT Pamplin Leader, VT Benjamin F. Bock, VT Gay B. Shober, VT I. Luck Gravett |
[Google Scholar: 10k+ citations and an h-index of 40]
Selected publications I am a primary author on are highlighted.
1. |
Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model Ensembles
[abs] Buu Phan, Brandon Amos, Itai Gat, Marton Havasi, Matthew Muckley, and Karen Ullrich ICLR 2025 |
2. |
Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold
[abs] [code] Lazar Atanackovic, Xi Zhang, Brandon Amos, Mathieu Blanchette, Leo J Lee, Yoshua Bengio, Alexander Tong, and Kirill Neklyudov ICLR 2025 |
22. |
Cross-Domain Imitation Learning via Optimal Transport
[abs] [code] Arnaud Fickinger, Samuel Cohen, Stuart Russell, and Brandon Amos ICLR 2022 |
23. |
Matching Normalizing Flows and Probability Paths on Manifolds
[abs] Heli Ben-Hamu*, Samuel Cohen*, Joey Bose, Brandon Amos, Aditya Grover, Maximilian Nickel, Ricky T. Q. Chen, and Yaron Lipman ICML 2022 |
24. |
Semi-Discrete Normalizing Flows through Differentiable Tessellation
[abs] Ricky T. Q. Chen, Brandon Amos, and Maximilian Nickel NeurIPS 2022 |
25. |
Theseus: A Library for Differentiable Nonlinear Optimization
[abs] [code] Luis Pineda, Taosha Fan, Maurizio Monge, Shobha Venkataraman, Paloma Sodhi, Ricky Chen, Joseph Ortiz, Daniel DeTone, Austin Wang, Stuart Anderson, Jing Dong, Brandon Amos, and Mustafa Mukadam NeurIPS 2022 |
26. |
Nocturne: a driving benchmark for multi-agent learning
[abs] [code] Eugene Vinitsky, Nathan Lichtlé, Xiaomeng Yang, Brandon Amos, and Jakob Foerster NeurIPS Datasets and Benchmarks Track 2022 |
40. |
The Differentiable Cross-Entropy Method
[abs] [code] [slides] Brandon Amos and Denis Yarats ICML 2020 |
41. |
Objective Mismatch in Model-based Reinforcement Learning
[abs] Nathan Lambert, Brandon Amos, Omry Yadan, and Roberto Calandra L4DC 2020 |
42. |
QNSTOP: Quasi-Newton Algorithm for Stochastic Optimization
[abs] [code] Brandon Amos, David Easterling, Layne T. Watson, William Thacker, Brent Castle, and Michael Trosset ACM TOMS 2020 |
43. |
Neural Potts Model
[abs] Tom Sercu, Robert Verkuil, Joshua Meier, Brandon Amos, Zeming Lin, Caroline Chen, Jason Liu, Yann LeCun, and Alexander Rives MLCB 2020 |
44. |
Deep Riemannian Manifold Learning
[abs] Aaron Lou, Maximilian Nickel, and Brandon Amos NeurIPS Geo4dl Workshop 2020 |
45. |
Differentiable Optimization-Based Modeling for Machine Learning
[abs] [code] Brandon Amos Ph.D. Thesis 2019 |
46. |
Differentiable Convex Optimization Layers
[abs] [code] Akshay Agrawal*, Brandon Amos*, Shane Barratt*, Stephen Boyd*, Steven Diamond*, and J. Zico Kolter* NeurIPS 2019 |
47. |
The Limited Multi-Label Projection Layer
[abs] [code] Brandon Amos, Vladlen Koltun, and J. Zico Kolter arXiv 2019 |
48. |
Generalized Inner Loop Meta-Learning
[abs] [code] Edward Grefenstette, Brandon Amos, Denis Yarats, Phu Mon Htut, Artem Molchanov, Franziska Meier, Douwe Kiela, Kyunghyun Cho, and Soumith Chintala arXiv 2019 |
49. |
Learning Awareness Models
[abs] Brandon Amos, Laurent Dinh, Serkan Cabi, Thomas Rothörl, Sergio Gómez Colmenarejo, Alistair Muldal, Tom Erez, Yuval Tassa, Nando de Freitas, and Misha Denil ICLR 2018 |
50. |
Differentiable MPC for End-to-end Planning and Control
[abs] [code] Brandon Amos, Ivan Dario Jimenez Rodriguez, Jacob Sacks, Byron Boots, and J. Zico Kolter NeurIPS 2018 |
51. |
Depth-Limited Solving for Imperfect-Information Games
[abs] Noam Brown, Tuomas Sandholm, and Brandon Amos NeurIPS 2018 |
52. |
Enabling Live Video Analytics with a Scalable and Privacy-Aware Framework
[abs] Junjue Wang, Brandon Amos, Anupam Das, Padmanabhan Pillai, Norman Sadeh, and Mahadev Satyanarayanan ACM TOMM 2018 |
60. |
OpenFace: A general-purpose face recognition library with mobile applications
[abs] [code] Brandon Amos, Bartosz Ludwiczuk, and Mahadev Satyanarayanan CMU 2016 |
61. |
Collapsed Variational Inference for Sum-Product Networks
[abs] Han Zhao, Tameem Adel, Geoff Gordon, and Brandon Amos ICML 2016 |
62. |
Quantifying the impact of edge computing on mobile applications
[abs] Wenlu Hu, Ying Gao, Kiryong Ha, Junjue Wang, Brandon Amos, Zhuo Chen, Padmanabhan Pillai, and Mahadev Satyanarayanan ACM SIGOPS 2016 |
63. |
Privacy mediators: helping IoT cross the chasm
[abs] Nigel Davies, Nina Taft, Mahadev Satyanarayanan, Sarah Clinch, and Brandon Amos HotMobile 2016 |
37.5k+ GitHub stars across all repositories.
1. | 2024 facebookresearch/oni | 34 | Online LLM intrinsic rewards for NetHack |
2. | 2024 facebookresearch/advprompter | 144 | Fast Adaptive Adversarial Prompting for LLMs |
3. | 2024 facebookresearch/lagrangian-ot | 54 | Lagrangian Optimal Transport |
4. | 2024 lazaratan/meta-flow-matching | 48 | Meta Flow Matching |
5. | 2024 facebookresearch/soc-matching | 30 | Stochastic Optimal Control Matching |
6. | 2024 kuleshov/cornell-cs5785-2024-applied-ml | 476 | Slides for our applied ML course |
7. | 2023 facebookresearch/amortized-optimization-tutorial | 238 | Tutorial on amortized optimization |
8. | 2023 facebookresearch/taskmet | 19 | TaskMet: Task-Driven Metric Learning for Model Learning |
9. | 2023 facebookresearch/w2ot | 46 | Wasserstein-2 optimal transport in JAX |
10. | 2023 facebookresearch/LANCER | 36 | Landscape Surrogate Learning Decision Losses |
11. | 2022 facebookresearch/theseus | 1.9k | Differentiable non-linear optimization library |
12. | 2022 facebookresearch/meta-ot | 100 | Meta Optimal Transport |
13. | 2022 bamos/presentations | 144 | Source for my major presentations |
14. | 2022 facebookresearch/gwil | 24 | Gromov-Wasserstein Cross Domain Imitation Learning |
15. | 2022 facebookresearch/nocturne | 273 | A partially-observable multi-agent driving simulator |
16. | 2021 facebookresearch/rcpm | 67 | Riemannian Convex Potential Maps |
17. | 2021 facebookresearch/svg | 55 | Model-based stochastic value gradient |
18. | 2021 facebookresearch/mbrl-lib | 987 | Model-based reinforcement learning library |
19. | 2021 martius-lab/CombOptNet | 72 | Combinatorial OptNet |
20. | 2021 samcohen16/Aligning-Time-Series | 51 | Aligning time series on incomparable spaces |
21. | 2021 facebookresearch/neural_stpp | 101 | Neural Spatio-Temporal Point Processes |
22. | 2021 facebookresearch/neural-scs | 29 | Neural Fixed-Point Acceleration for SCS |
23. | 2021 rtqichen/torchdiffeq | 5.8k | PyTorch Differentiable ODE Solvers (differentiable event handling) |
24. | 2020 facebookresearch/dcem | 126 | The Differentiable Cross-Entropy Method |
25. | 2019 facebookresearch/higher | 1.6k | PyTorch higher-order gradient and optimization library |
26. | 2019 bamos/thesis | 332 | Ph.D. Thesis LaTeX source code |
27. | 2019 cvxgrp/cvxpylayers | 1.9k | Differentiable Convex Optimization Layers |
28. | 2019 locuslab/lml | 58 | The Limited Multi-Label Projection Layer |
29. | 2018 locuslab/mpc.pytorch | 925 | Differentiable PyTorch Model Predictive Control library |
30. | 2018 locuslab/differentiable-mpc | 266 | Differentiable MPC experiments |
31. | 2017 locuslab/icnn | 286 | Input Convex Neural Network experiments |
32. | 2017 locuslab/optnet | 523 | OptNet experiments |
33. | 2017 locuslab/qpth | 700 | Differentiable PyTorch QP solver |
34. | 2017 bamos/densenet.pytorch | 836 | PyTorch DenseNet implementation |
35. | 2017 bamos/block | 303 | Intelligent block matrix constructions |
36. | 2017 bamos/setGPU | 106 | Automatically use the least-loaded GPU |
37. | 2016 bamos/dcgan-completion.tensorflow | 1.3k | Image completion with GANs |
38. | 2015 cmusatyalab/openface | 15.2k | Face recognition with deep neural networks |
39. | 2015 bamos/girl | 70 | GitHub README link checker |
40. | 2015 bamos/conference-tracker | 72 | Minimal conference tracker |
41. | 2014 vtopt/qnstop | 10 | Fortran quasi-Newton stochastic optimization library |
42. | 2014 bamos/snowglobe | 27 | Haskell-driven, self-hosted web analytics with minimal configuration |
43. | 2014 bamos/zsh-history-analysis | 233 | Analyze and plot your zsh history |
44. | 2014 bamos/beamer-snippets | 110 | Beamer and TikZ snippets |
45. | 2013 bamos/latex-templates | 364 | LaTeX templates |
46. | 2013 cparse/cparse | 348 | C++ expression parser using Dijkstra's shunting-yard algorithm |
47. | 2013 bamos/cv | 408 | Source for this CV: Creates LaTeX/Markdown from YAML/BibTeX |
48. | 2013 bamos/parsec-benchmark | 104 | PARSEC benchmark support for Arch Linux |
49. | 2013 bamos/python-scripts | 197 | Short and fun Python scripts |
50. | 2013 bamos/reading-list | 186 | YAML reading list and notes system |
51. | 2012 bamos/dotfiles | 241 | Linux, xmonad, emacs, vim, zsh, tmux |
Slides for my major presentations are available here under a CC-BY license.
2024 - 2025 Aaron Havens (visiting FAIR from UIUC) |
2022 - 2024 Aram-Alexandre Pooladian (visiting FAIR from NYU) |
2022 - 2024 Carles Domingo-Enrich (visiting FAIR from NYU, now at MSR) |
2023 - 2024 Anselm Paulus (visiting FAIR from Max Planck Institute, Tübingen) |
2023 Matthew Retchin (Columbia MS thesis committee, now at Harvard) |
2022 - 2023 Sanae Lotfi (visiting FAIR from NYU) |
2022 - 2023 Dishank Bansal (AI resident at FAIR) |
2021 - 2022 Arnaud Fickinger (visiting FAIR from Berkeley) |
2020 - 2022 Aaron Lou (visiting FAIR from Cornell and Stanford, now scientist at OpenAI) |
2021 - 2022 Eugene Vinitsky (visiting FAIR from Berkeley, now professor at NYU) |
2021 - 2022 Samuel Cohen (visiting FAIR from UCL, now CEO at FairGen) |
2020 Ricky Chen (visiting FAIR from Toronto, now scientist at FAIR) |
2020 Paul Liang (visiting FAIR from CMU, now professor at MIT) |
2018 Phillip Wang (at CMU, now CEO at Gather) |
2025 AAAI Senior Program Committee |
2024 NeurIPS Area Chair |
2024 NeurIPS Datasets and Benchmarks Area Chair |
2024 AAAI Senior Program Committee |
2023 NeurIPS Area Chair |
2023 NeurIPS Datasets and Benchmarks Area Chair |
2023 AAAI Senior Program Committee |
2020 NeurIPS Learning Meets Combinatorial Optimization Workshop Organizer |
2020 CVPR Deep Declarative Networks Workshop Organizer |
2020 ECCV Deep Declarative Networks Tutorial Organizer |
2014 - 2015 CMU CSD MS Admissions |
AAAI Conference on Artificial Intelligence |
American Controls Conference (ACC) |
Artificial Intelligence and Statistics (AISTATS) |
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) |
IEEE Conference on Decision and Control (CDC) |
IEEE Control Systems Letters (L-CSS) |
IEEE International Conference on Computer Vision (ICCV) |
IEEE International Conference on Intelligent Robots and Systems (IROS) |
IEEE International Conference on Robotics and Automation (ICRA) |
International Conference on Learning Representations (ICLR) |
International Conference on Learning Representations (ICLR) Blog Posts |
International Conference on Machine Learning (ICML) |
International Conference on Machine Learning (ICML) SODS Workshop |
International Conference on the Constraint Programming, AI, and Operations Research (CPAIOR) |
Journal of Machine Learning Research (JMLR) |
Learning for Dynamics and Control (L4DC) |
Mathematical Programming Computation (MPC) |
Neural Information Processing Systems (NeurIPS) |
Neural Information Processing Systems (NeurIPS) Datasets and Benchmarks Track |
Neural Information Processing Systems (NeurIPS) Deep RL Workshop |
Neural Information Processing Systems (NeurIPS) DiffCVGP Workshop |
Neural Information Processing Systems (NeurIPS) OPT Workshop |
Optimization Letters |
Transactions on Machine Learning Research (TMLR) |
Uncertainty in Artificial Intelligence (UAI) |
Applied Machine Learning (Cornell Tech CS5785), Co-instructor | F2024 |
Graduate AI (CMU 15-780), TA | S2017 |
Distributed Systems (CMU 15-440/640), TA | S2016 |
Software Design and Data Structures (VT CS2114), TA | S2013 |
Programming | C, C++, Fortran, Haskell, Java, Lua, Make, Mathematica, Python, R, Scala |
Frameworks | JAX, NumPy, Pandas, PyTorch, SciPy, TensorFlow, Torch7 |
Toolbox | Linux, emacs, vim, evil, org, mu4e, xmonad, git, tmux, zsh |
Last updated on 2025-03-16