JR
Jack Rae
cs.LGstat.MLcs.CLcs.AIcs.NEcs.CVcs.CYcs.DBcs.DSDeep Learning
On Valency
published · living versionsW_45caf8hg·v1 · currentpublished
Model-Free Episodic Control
with Charles Blundell, Benigno Uria, Alexander Pritzel, Yazhe Li +4
1 version
Preprints & journals
25 papers in the corpus · 2016–2024Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context2403.05530v5 · Gemini Team Google: Petko Georgiev, Ving Ian Lei, Ryan Burnell et al.2024 · 302 citationsarXiv
Gemini: A Family of Highly Capable Multimodal Models2312.11805v5 · Gemini Team Google: Rohan Anil, Sebastian Borgeaud, Jean-Baptiste Alayrac et al.2023 · 988 citationsarXiv
GPT-4 Technical Report2303.08774v6 · OpenAI, Josh Achiam, Steven Adler et al.2023 · 2,393 citationsarXiv
Training Compute-Optimal Large Language Models2203.15556v1 · Jordan Hoffmann, Sebastian Borgeaud, Arthur Mensch et al.2022 · 925 citationsarXiv
Unified Scaling Laws for Routed Language Models2202.01169v2 · Aidan Clark, Diego de las Casas, Aurelia Guy et al.2022 · 40 citationsarXiv
Improving language models by retrieving from trillions of tokens2112.04426v3 · Sebastian Borgeaud, Arthur Mensch, Jordan Hoffmann et al.2021 · 382 citationsarXiv
Scaling Language Models: Methods, Analysis & Insights from Training Gopher2112.11446v2 · Jack W. Rae, Sebastian Borgeaud, Trevor Cai et al.2021 · 234 citationsarXiv
Top-KAST: Top-K Always Sparse Training2106.03517v1 · Siddhant M. Jayakumar, Razvan Pascanu, Jack W. Rae et al.2021 · 38 citationsAdvances in Neural Information Processing Systems, 33, 20744-20754
Use of deep learning to develop continuous-risk models for adverse event prediction from electronic health records.33953393 · Tomašev, Nenad, Harris, Natalie, Baur, Sebastien et al.2021 · 110 citationsNature protocols. 2021;16(6):2765-2787
Do Transformers Need Deep Long-Range Memory2007.03356v1 · Jack W. Rae, Ali Razavi2020 · 26 citationsarXiv
Compressive Transformers for Long-Range Sequence Modelling1911.05507v1 · Jack W. Rae, Anna Potapenko, Siddhant M. Jayakumar et al.2019 · 205 citationsarXiv
Reducing Sentiment Bias in Language Models via Counterfactual Evaluation1911.03064v3 · Po-Sen Huang, Huan Zhang, Ray Jiang et al.2019 · 137 citationsarXiv
Stabilizing Transformers for Reinforcement Learning1910.06764v1 · Emilio Parisotto, H. Francis Song, Jack W. Rae et al.2019 · 236 citationsarXiv
Meta-Learning Deep Energy-Based Memory Models1910.02720v2 · Sergey Bartunov, Jack W Rae, Simon Osindero et al.2019 · 23 citationsarXiv
V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control1909.12238v1 · H. Francis Song, Abbas Abdolmaleki, Jost Tobias Springenberg et al.2019 · 56 citationsarXiv
A clinically applicable approach to continuous prediction of future acute kidney injury.31367026 · Tomašev, Nenad, Glorot, Xavier, Rae, Jack W et al.2019 · 1,080 citationsNature. 2019;572(7767):116-119
Meta-Learning Neural Bloom Filters1906.04304v1 · Jack W Rae, Sergey Bartunov, Timothy P Lillicrap2019 · 16 citationsarXiv
Training language GANs from Scratch1905.09922v2 · Cyprien de Masson d'Autume, Mihaela Rosca, Jack Rae et al.2019 · 36 citationsarXiv
Neural Arithmetic Logic Units1808.00508v1 · Andrew Trask, Felix Hill, Scott Reed et al.2018 · 153 citationsarXiv
Relational recurrent neural networks1806.01822v2 · Adam Santoro, Ryan Faulkner, David Raposo et al.2018 · 153 citationsarXiv
Unsupervised Predictive Memory in a Goal-Directed Agent1803.10760v1 · Greg Wayne, Chia-Chun Hung, David Amos et al.2018 · 138 citationsarXiv
Fast Parametric Learning with Activation Memorization1803.10049v1 · Jack W Rae, Chris Dyer, Peter Dayan et al.2018 · 26 citationsarXiv
Memory-based Parameter Adaptation1802.10542v1 · Pablo Sprechmann, Siddhant M. Jayakumar, Jack W. Rae et al.2018 · 54 citationsarXiv
Scaling Memory-Augmented Neural Networks with Sparse Reads and Writes1610.09027v1 · Jack W Rae, Jonathan J Hunt, Tim Harley et al.2016 · 77 citationsarXiv
Model-Free Episodic Control1606.04460v1 · Charles Blundell, Benigno Uria, Alexander Pritzel et al.2016 · 162 citationsarXivon Valency
Career total: 29 works. 25 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.