Topic: lab:deep-mind-ai

← Back to home

1. Highly accurate protein structure prediction for the human proteome

   Paper • Jul 22, 2021 • Nature • Kathryn Tunyasuvunakool, Jonas Adler, Zackary Wu, Tim Green, Michal Zielinski, Augustin Žídek, Alex Bridgland, Andrew Cowie, Clemens Meyer, Agata Laydon, Sameer Velankar, Gerard J. Kleywegt, Alex Bateman, Richard Evans, Alexander Pritzel, Michael Figurnov, Olaf Ronneberger, Russ Bates, Simon A. A. Kohl, Anna Potapenko, Andrew J. Ballard, Bernardino Romera-Paredes, Stanislav Nikolov, Rishub Jain, Ellen Clancy, David Reiman, Stig Petersen, Andrew W. Senior, Koray Kavukcuoglu, Ewan Birney, Pushmeet Kohli, John Jumper, Demis Hassabis

   The sequence of the human genome has been available for two decades, but the structures of the proteins it encodes have largely remained unknown, limiting our understanding of human health and dise...

2. Highly accurate protein structure prediction with AlphaFold

   Paper • Jul 15, 2021 • Nature • John Jumper, Richard Evans, Alexander Pritzel, Tim Green, Demis Hassabis

   Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. We provide the first computational method that can regularly predict ...

3. Design of highly affine and specific protein binders with AlphaProteo

   Paper • Sep 5, 2024 • bioRxiv • Google DeepMind

   Designing novel proteins that bind tightly and specifically to disease-relevant targets is a fundamental challenge in drug discovery and synthetic biology. We introduce AlphaProteo, an integrated m...

4. Open X-Embodiment: Robotic Learning Datasets and RT-X Models

   Paper • Oct 13, 2023 • arXiv • Open X-Embodiment Collaboration (Google DeepMind & Academic Partners)

   Large, diverse datasets have catalyzed breakthroughs in natural language and computer vision, yet robotics has struggled to build generalist models due to the fragmented nature of hardware platform...

5. Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset

   Paper • May 22, 2017 • arXiv • Joao Carreira, Andrew Zisserman

   Video action recognition is a crucial challenge in computer vision, but progress has been hindered by the lack of large-scale, comprehensive datasets comparable to ImageNet. We introduce the Kineti...

6. Matching Networks for One Shot Learning

   Paper • Jun 13, 2016 • arXiv • Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Koray Kavukcuoglu, Daan Wierstra

   Deep learning algorithms typically require vast amounts of data to achieve high performance, contrasting sharply with human ability to learn new concepts from a single example. We introduce Matchin...

7. Pointer Networks

   Paper • Jun 9, 2015 • arXiv • Oriol Vinyals, Meire Fortunato, Navdeep Jaitly

   We introduce a new neural architecture to learn the conditional probability of an output sequence with elements that are discrete tokens corresponding to positions in an input sequence. Such proble...

8. Human-level performance in 3D multiplayer games with population-based reinforcement learning

   Paper • May 31, 2019 • Science • Max Jaderberg, Wojciech M. Czarnecki, Iain Dunning, Luke Marris, Guy Lever, Antonio Garcia Castaneda, Charles Beattie, Neil C. Rabinowitz, Ari S. Morcos, Avraham Ruderman, Nicolas Sonnerat, Tim Green, Louise Deason, Joel Z. Leibo, David Silver, Demis Hassabis, Koray Kavukcuoglu, Thore Graepel

   Multiplayer video games represent a significant frontier for AI research, requiring real-time, high-dimensional sensory processing, spatial navigation, and team-based coordination. We report an AI ...

9. Mastering the game of Stratego with model-free multiagent reinforcement learning

   Paper • Dec 1, 2022 • Science • Julien Perolat, Bart De Vylder, Daniel Hennes, Eugene Tarassov, Florian Strub, Vincent de Boer, Paul Muller, Jerome T. Connor, Neil Burch, Thomas Anthony, Stephen McAleer, Romuald Elie, Sarah H. Cen, Zhe Wang, Audrunas Gruslys, Aleksander Malyshev, Mina Khan, Sherjil Ozair, Finbarr Timbers, Toby Pohlen, Tom Eccles, Mark Rowland, Marc Lanctot, Jean-Baptiste Lespiau, Bilal Piot, Shayegan Omidshafiei, Edward Lockhart, Laurent Sifre, Nathalie Beauguerlange, Remi Munos, David Silver, Satinder Singh, Demis Hassabis, Karl Tuyls

   Imperfect information games, where players have hidden information, represent a significant challenge for artificial intelligence. Stratego is a complex, imperfect-information board game with an en...

10. Scaling deep learning for materials discovery

    Paper • Nov 29, 2023 • Nature • Amil Merchant, Simon Batzner, Samuel S. Schoenholz, Muratahan Aykol, Gowoon Cheon, Ekin Dogus Cubuk

    The discovery of novel functional materials is essential for technological progress in batteries, solar cells, and computation, but traditionally relies on expensive, trial-and-error experimentatio...

11. Magnetic control of tokamak plasmas through deep reinforcement learning

    Paper • Feb 16, 2022 • Nature • Jonas Degrave, Federico Felici, Jonas Buchli, Martin Neunert, Brendan Tracey, Francesco Carpanese, Timo Ewalds, Roland Jung, Abbas Abdolmaleki, Demis Hassabis, Martin Riedmiller

    Nuclear fusion represents a clean, virtually limitless energy source, but sustaining the necessary plasma states inside a tokamak reactor requires complex, high-frequency magnetic control. Traditio...

12. Mastering the game of Go without human knowledge

    Paper • Oct 18, 2017 • Nature • David Silver, Julian Schrittwieser, Karen Simonyan, Ioannis Antonoglou, Aja Huang, Arthur Guez, Thomas Hubert, Lucas Baker, Matthew Lai, Adrian Bolton, Yutian Chen, Timothy Lillicrap, Fan Hui, Laurent Sifre, George van den Driessche, Thore Graepel, Demis Hassabis

    A long-standing goal of artificial intelligence is an algorithm that learns, tabula rasa, superhuman proficiency in challenging domains. We introduce AlphaGo Zero, an AI that achieves superhuman pe...

13. Protein complex prediction with AlphaFold-Multimer

    Paper • Oct 4, 2021 • bioRxiv • Richard Evans, Michael O'Neill, Alexander Pritzel, Natasha Antropova, Andrew Senior, Tim Green, Augustin Žídek, Russ Bates, Sam Blackwell, Jason Yim, Olaf Ronneberger, Sebastian Bodenstein, Michal Zielinski, Alex Bridgland, Anna Potapenko, Andrew Cowie, Kathryn Tunyasuvunakool, Rishub Jain, Ellen Clancy, Pushmeet Kohli, John Jumper, Demis Hassabis

    While AlphaFold 2 achieved unprecedented accuracy in predicting the structure of single protein chains, biological functions are primarily carried out by multi-protein complexes. We present AlphaFo...

14. Mastering Diverse Domains through World Models

    Paper • Jan 10, 2023 • arXiv • Danijar Hafner, Jurgis Pasukonis, Jimmy Ba, Timothy Lillicrap

    General intelligence requires solving tasks across diverse domains without human intervention. We present DreamerV3, a general and scalable reinforcement learning algorithm that masters a wide rang...

15. RT-1: Robotics Transformer for Real-World Control at Scale

    Paper • Dec 13, 2022 • arXiv • Anthony Brohan, Noah Brown, Justice Carbajal, Yevgen Chebotar, Joseph Dabis, Chelsea Finn, Keerthana Gopalakrishnan, Karol Hausman, Alex Herzog, Jasmine Hsu, Julian Ibarz, Brian Ichter, Alex Irpan, Tomas Jackson, Google DeepMind

    By transferring knowledge from large, diverse, task-agnostic datasets, modern machine learning models can solve specific downstream tasks either zero-shot or with small task-specific datasets. We i...

16. Agent57: Outperforming the Atari Human Benchmark

    Paper • Mar 31, 2020 • arXiv • Adrià Puigdomènech Badia, Bilal Piot, Steven Kapturowski, Pablo Sprechmann, Alex Vitvitskyi, Daniel Guo, Charles Blundell

    Atari 2600 games have been a long-standing benchmark in the reinforcement learning community. While previous algorithms have achieved superhuman performance on average, they consistently fail on a ...

17. Improving language models by retrieving from trillions of tokens

    Paper • Dec 8, 2021 • arXiv • Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevor Cai, Eliza Rutherford, Katie Millican, George van den Driessche, Jean-Baptiste Lespiau, Bogdan Damoc, Aidan Clark, Diego de Las Casas, Aurelia Guy, Jacob Menick, Roman Ring, Tom Hennigan, Saffron Huang, Loren Maggiore, Chris Jones, Albin Cassirer, Andy Brock, Michela Paganini, Geoffrey Irving, Oriol Vinyals, Simon Osindero, Karen Simonyan, Jack W. Rae, Erich Elsen, Laurent Sifre

    We enhance auto-regressive language models by conditioning on document chunks retrieved from a large corpus, based on local similarity with preceding tokens. With a 2 trillion token database, our R...

18. Large Scale GAN Training for High Fidelity Natural Image Synthesis

    Paper • Sep 28, 2018 • arXiv • Andrew Brock, Jeff Donahue, Karen Simonyan

    Despite recent progress in generative image modeling, successfully generating high-resolution, diverse samples from complex datasets such as ImageNet remains an elusive goal. To this end, we train ...

19. Scaling Instructable Agents Across Many Simulated Worlds

    Paper • Apr 15, 2024 • arXiv • SIMA Team, Google DeepMind

    We introduce the Scalable Instructable Multiworld Agent (SIMA), an AI agent capable of following natural-language instructions to carry out tasks in a wide variety of 3D virtual environments and vi...

20. Discovering faster matrix multiplication algorithms with reinforcement learning

    Paper • Oct 5, 2022 • Nature • Alhussein Fawzi, Matej Balog, Aja Huang, Thomas Hubert, Pushmeet Kohli

    Matrix multiplication is a fundamental computational task, heavily utilized in neural networks, scientific computing, and graphics. Despite its ubiquity, finding optimal algorithms for matrix multi...