Improving alignment of dialogue agents via targeted human judgements
Paper·Amelia Glaese, Nat McAleese, Maja Trebacz, John Aslanides…·9/22/2022
Research LabManaged by Attendemia
Deep Mind AI🇬🇧
Google DeepMind is a premier AI research laboratory, formed by merging Google Brain and DeepMind, dedicated to developing safe, advanced artificial intelligence to solve complex scientific challenges. Founded in 2010 and acquired by Google in 2014, it is famous for breakthroughs like AlphaGo, AlphaFold, and general-purpose algorithms.
Sign in to followFollowers: 232
Timeline
Page 2Source ↗
A Generalist Agent
Paper·Scott Reed, Konrad Zolna, Emilio Parisotto, Sergio Gomez …·5/12/2022
Flamingo: a Visual Language Model for Few-Shot Learning
Paper·Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine…·4/28/2022
Training Compute-Optimal Large Language Models
Paper·Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch, Elena…·3/29/2022
Magnetic control of tokamak plasmas through deep reinforcement learning
Paper·Jonas Degrave, Federico Felici, Jonas Buchli, Martin Neun…·2/16/2022
Improving language models by retrieving from trillions of tokens
Paper·Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann, Trevo…·12/8/2021
Scaling Language Models: Methods, Analysis & Insights from Training Gopher
Paper·Jack W. Rae, Sebastian Borgeaud, Trevor Cai, Katie Millic…·12/8/2021
Protein complex prediction with AlphaFold-Multimer
Paper·Richard Evans, Michael O'Neill, Alexander Pritzel, Natash…·10/4/2021
Highly accurate protein structure prediction for the human proteome
Paper·Kathryn Tunyasuvunakool, Jonas Adler, Zackary Wu, Tim Gre…·7/22/2021
Highly accurate protein structure prediction with AlphaFold
Paper·John Jumper, Richard Evans, Alexander Pritzel, Tim Green,…·7/15/2021
Perceiver: General Perception with Iterative Attention
Paper·Andrew Jaegle, Felix Gimeno, Andrew Brock, Oriol Vinyals,…·3/4/2021
Mastering Atari, Go, chess and shogi by planning with a learned model
Paper·Julian Schrittwieser, Ioannis Antonoglou, Thomas Hubert, …·12/23/2020
Agent57: Outperforming the Atari Human Benchmark
Paper·Adrià Puigdomènech Badia, Bilal Piot, Steven Kapturowski,…·3/31/2020
Grandmaster level in StarCraft II using multi-agent reinforcement learning
Paper·Oriol Vinyals, Igor Babuschkin, Wojciech M. Czarnecki, Mi…·10/30/2019
Continuous control with deep reinforcement learning
Paper·Timothy P. Lillicrap, Jonathan J. Hunt, Alexander Pritzel…·7/5/2019
Human-level performance in 3D multiplayer games with population-based reinforcement learning
Paper·Max Jaderberg, Wojciech M. Czarnecki, Iain Dunning, Luke …·5/31/2019
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
Paper·David Silver, Thomas Hubert, Julian Schrittwieser, Ioanni…·12/7/2018
Large Scale GAN Training for High Fidelity Natural Image Synthesis
Paper·Andrew Brock, Jeff Donahue, Karen Simonyan·9/28/2018
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Paper·Lasse Espeholt, Hubert Soyer, Remi Munos, Karen Simonyan,…·2/9/2018
Neural Discrete Representation Learning
Paper·Aaron van den Oord, Oriol Vinyals, Koray Kavukcuoglu·11/2/2017