I'm Matthias Plappert. I've spent the last decade working on AI and robotics—most notably at OpenAI, where I helped teach a robot hand to solve a Rubik's Cube and computers to write code, and at GitHub, where I worked on Copilot.
Today I run dfdx labs, where I help companies apply ML to hard technical problems. On the side, I angel-invest in European deep tech startups. Currently, I'm particularly interested in the intersection of ML, power markets, and renewable energy.
You can also find me elsewhere on the Internet: Email, LinkedIn, Mastodon, and Google Scholar.
Publications
Journals
- OpenAI: M. Andrychowicz, B. Baker, M. Chociej, R. Jozefowicz, B. McGrew, J. Pachocki, A. Petron, M. Plappert, G. Powell, A. Ray, J. Schneider, S. Sidor, J. Tobin, P. Welinder, L. Weng, and W. Zaremba, Learning Dexterous In-Hand Manipulation, The International Journal of Robotics Research (IJRR), Vol. 39(1), pp. 3-20, January 2020 (pre-print August 2018) [pdf, pre-print, blog post, video 1, video 2, bib]
- M. Plappert, C. Mandery, and T. Asfour, Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks, Robotics and Autonomous Systems, Vol. 109, pp. 13-26, November 2018 [pdf, video, dataset, code, bib]
- M. Plappert, C. Mandery, and T. Asfour, The KIT Motion-Language Dataset, Big Data, Vol. 4, No. 4, pp. 236-252, December 2016 [pdf, dataset, code, bib]
Conferences
- M. Plappert, R. Houthooft, P. Dhariwal, S. Sidor, R.Y. Chen, X. Chen, T. Asfour, P. Abbeel, and M. Andrychowicz, Parameter Space Noise for Exploration, In the proceedings of the International Conference on Learning Representations (ICLR), Vancouver, Canada, April 2018 [pdf, blog post, code, bib]
- C. Mandery, M. Plappert, J. BorrĂ s, and T. Asfour, Dimensionality Reduction for Whole-Body Human Motion Recognition, 19th International Conference on Information Fusion (FUSION), pp. 355-362, July 2016 [pdf, bib]
Pre-Prints & Tech Reports
- K. Cobbe, V. Kosaraju, M. Bavarian, M. Chen, H. Jun, L. Kaiser, M. Plappert, J. Tworek, J. Hilton, R. Nakano, C. Hesse, and J. Schulman, Training Verifiers to Solve Math Word Problems, arXiv:2110.14168, October 2021 [pdf, blog post]
- M. Chen, J. Tworek, H. Jun, Q. Yuan, H. Ponde de Oliveira Pinto, J. Kaplan, H. Edwards, Y. Burda, N. Joseph, G. Brockman, A. Ray, R. Puri, G. Krueger, M. Petrov, H. Khlaaf, G. Sastry, P. Mishkin, B. Chan, S. Gray, N. Ryder, M. Pavlov, A. Power, L. Kaiser, M. Bavarian, C. Winter, P. Tillet, F. Such, D. Cummings, M. Plappert, F. Chantzis, E. Barnes, A. Herbert-Voss, W.H. Guss, A. Nichol, A. Paino, N. Tezak, J. Tang, I. Babuschkin, S. Balaji, S. Jain, W. Saunders, C. Hesse, A.N. Carr, J. Leike, J. Achiam, V. Misra, E. Morikawa, A. Radford, M. Knight, M. Brundage, M. Murati, K. Mayer, P. Welinder, B. McGrew, D. Amodei, S. McCandlish, I. Sutskever, and W. Zaremba, Evaluating Large Language Models Trained on Code, arXiv:2107.03374, July 2021 [pdf, blog post]
- OpenAI: M. Plappert, R. Sampedro, T. Xu, I. Akkaya, V. Kosaraju, P. Welinder, R. D'Sa, A. Petron, H. Ponde de Oliveira Pinto, A. Paino, H. Noh, L. Weng, Q. Yuan, C. Chu, and W. Zaremba, Asymmetric self-play for automatic goal discovery in robotic manipulation, arXiv:2101.04882, January 2021 [pdf, videos]
- L. Zhang, M. Plappert, and W. Zaremba, Predicting Sim-to-Real Transfer with Probabilistic Dynamics Models, arXiv:2009.12864, September 2020 [pdf]
- OpenAI: I. Akkaya, M. Andrychowicz, M. Chociej, M. Litwin, B. McGrew, A. Petron, A. Paino, M. Plappert, G. Powell, R. Ribas, J. Schneider, N. Tezak, J. Tworek, P. Welinder, L. Weng, Q. Yuan, W. Zaremba, and L. Zhang, Solving Rubik's Cube with a Robot Hand, arXiv:1910.07113, October 2019 [pdf, blog post, all videos, bib]
- M. Plappert, M. Andrychowicz, A. Ray, B. McGrew, B. Baker, G. Powell, J. Schneider, J. Tobin, M. Chociej, P. Welinder, V. Kumar, and W. Zaremba, Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research, arXiv:1802.09464, February 2018 [pdf, blog post, bib]
Theses
Talks
- Understanding LLMs — An Introduction to Modern Language Modeling, Knowunity AI Meetup, October 2023 [slides]
- OpenAI Robotics Symposium 2019, April 2019 [video]
- Learning Dexterity, NeurIPS 2018, Deep Reinforcement Learning Workshop, December 2018 [slides, poster]
- Learning Dexterity, karlsruhe.ai / Hack & Söhne, September 2018 [slides]
- Parameter Space Noise for Exploration, heidelberg.ai, May 2018 [slides]
In the News
- GitHub Copilot X: Bloomberg, Fast Company, TechCrunch, The Verge, VentureBeat, Handelsblatt, Heise
- Codex and GitHub Copilot: New York Times, WIRED Magazine, WIRED, Wikipedia, CNBC, The Verge, TechCrunch, VentureBeat, The Register
- Asymmetric self-play for automatic goal discovery in robotic manipulation: MIT Technology Review
- Solving Rubik's Cube with a Robot Hand: New York Times, BBC, Vox, MIT Technology Review, IEEE Spectrum, Washington Post, New York Post, Vice, Popular Mechanics, Synced, Fortune, ZDNet, The Verge, VentureBeat, TechCrunch, New Scientist
- Learning Dexterous In-Hand Manipulation: New York Times, WIRED, IEEE Spectrum, Science, MIT Technology Review, The Telegraph, Bloomberg, San Francisco Chronicle, The Register, Associated Press, Reuters, The Verge, Axios, TechCrunch, Engadget, Futurism, golem.de, Spektrum.de
- Ingredients for Robotics Research: IEEE Spectrum, MIT Technology Review, The Register, Newsweek, Futurism