| CARVIEW |
MAX JADERBERG
I work at Isomorphic Labs, where we are reimagining the entire drug discovery process from first principles with AI. To learn more about our work, check out my TED talk on how AI is accelerating science, and this podcast about how we are approaching drug design with AI.
Selected Publications (full list)
Spatial Transformer Networks
M Jaderberg, K Simonyan, A Zisserman, K Kavukcuoglu
10715 citations | NIPS 2015 (Spotlight), 2015
Accurate structure prediction of biomolecular interactions with AlphaFold 3
J Abramson, J Adler, J Dunger, R Evans, T Green, A Pritzel, ...
10579 citations | Nature 630 (8016), 493-500, 2024
Grandmaster level in StarCraft II using multi-agent reinforcement learning
O Vinyals, I Babuschkin, WM Czarnecki, M Mathieu, A Dudzik, J Chung, ...
6616 citations | nature 575 (7782), 350-354, 2019
Value-decomposition networks for cooperative multi-agent learning
P Sunehag, G Lever, A Gruslys, WM Czarnecki, V Zambaldi, M Jaderberg, ...
2639 citations | arXiv preprint arXiv:1706.05296, 2017
Speeding up Convolutional Neural Networks with Low Rank Expansions
M Jaderberg, A Vedaldi, A Zisserman
1983 citations | BMVC 2014, 2014
Reinforcement learning with unsupervised auxiliary tasks
M Jaderberg, V Mnih, WM Czarnecki, T Schaul, JZ Leibo, D Silver, ...
1595 citations | ICLR 2017 (Oral), 2016
Reading Text in the Wild with Convolutional Neural Networks
M Jaderberg, K Simonyan, A Vedaldi, A Zisserman
1494 citations | IJCV May 2015, 2014
Feudal networks for hierarchical reinforcement learning
AS Vezhnevets, S Osindero, T Schaul, N Heess, M Jaderberg, D Silver, ...
1319 citations | ICML 2017, 2017
Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition
M Jaderberg, K Simonyan, A Vedaldi, A Zisserman
1319 citations | NIPS Deep Learning Workshop 2014, 2014
Population based training of neural networks
M Jaderberg, V Dalibard, S Osindero, WM Czarnecki, J Donahue, ...
1089 citations | arXiv preprint arXiv:1711.09846, 2017
Human-level performance in 3D multiplayer games with population-based reinforcement learning
M Jaderberg, WM Czarnecki, I Dunning, L Marris, G Lever, AG Castaneda, ...
997 citations | Science 364 (6443), 859-865, 2019
Stabilizing transformers for reinforcement learning
E Parisotto, F Song, J Rae, R Pascanu, C Gulcehre, S Jayakumar, ...
584 citations | International conference on machine learning, 7487-7498, 2020
Decoupled neural interfaces using synthetic gradients
M Jaderberg, WM Czarnecki, S Osindero, O Vinyals, A Graves, ...
485 citations | ICML 2017, 2016
Unsupervised Learning of 3D Structure from Images
DJ Rezende, SM Eslami, S Mohamed, P Battaglia, M Jaderberg, N Heess
476 citations | NIPS 2016, 2016
Sobolev Training for Neural Networks
WM Czarnecki, S Osindero, M Jaderberg, G Świrszcz, R Pascanu
374 citations | NIPS 2017, 2017
Grounded language learning in a simulated 3d world
KM Hermann, F Hill, S Green, F Wang, R Faulkner, H Soyer, D Szepesvari, ...
373 citations | arXiv preprint arXiv:1706.06551, 2017
Deep Structured Output Learning for Unconstrained Text Recognition
M Jaderberg, K Simonyan, A Vedaldi, A Zisserman
325 citations | ICLR 2015 (Oral), 2014
Open-ended learning in symmetric zero-sum games
D Balduzzi, M Garnelo, Y Bachrach, W Czarnecki, J Perolat, M Jaderberg, ...
246 citations | International Conference on Machine Learning, 434-443, 2019
Open-Ended Learning Leads to Generally Capable Agents
OEL Team, A Stooke, A Mahajan, C Barros, C Deck, J Bauer, J Sygnowski, ...
235 citations | arXiv preprint arXiv:2107.12808, 2021