| Scaling language models: Methods, analysis & insights from training gopher JW Rae, S Borgeaud, T Cai, K Millican, J Hoffmann, F Song, J Aslanides, ... arXiv preprint arXiv:2112.11446, 2021 | 348 | 2021 |
| Compressive transformers for long-range sequence modelling JW Rae, A Potapenko, SM Jayakumar, TP Lillicrap ICLR 2020, 2019 | 300 | 2019 |
| Stabilizing transformers for reinforcement learning E Parisotto, F Song, J Rae, R Pascanu, C Gulcehre, S Jayakumar, ... International conference on machine learning, 7487-7498, 2020 | 238 | 2020 |
| Adapting auxiliary losses using gradient similarity Y Du, WM Czarnecki, SM Jayakumar, M Farajtabar, R Pascanu, ... arXiv preprint arXiv:1812.02224, 2018 | 107 | 2018 |
| Memory-based parameter adaptation P Sprechmann, SM Jayakumar, JW Rae, A Pritzel, AP Badia, B Uria, ... ICLR 2018, 2018 | 91 | 2018 |
| Information asymmetry in KL-regularized RL A Galashov, SM Jayakumar, L Hasenclever, D Tirumala, J Schwarz, ... ICLR 2019, 2019 | 88 | 2019 |
| Distilling Policy Distillation WM Czarnecki, R Pascanu, S Osindero, SM Jayakumar, G Swirszcz, ... AISTATS 2019, 2019 | 87 | 2019 |
| Multiplicative interactions and where to find them SM Jayakumar, WM Czarnecki, J Menick, J Schwarz, J Rae, S Osindero, ... ICLR 2020, 2020 | 83 | 2020 |
| Been there, done that: Meta-learning with episodic recall S Ritter, JX Wang, Z Kurth-Nelson, SM Jayakumar, C Blundell, R Pascanu, ... ICML 2018, 2018 | 80 | 2018 |
| Mix&match-agent curricula for reinforcement learning WM Czarnecki, SM Jayakumar, M Jaderberg, L Hasenclever, YW Teh, ... ICML 2018, 2018 | 67 | 2018 |
| Meta-learning of sequential strategies PA Ortega, JX Wang, M Rowland, T Genewein, Z Kurth-Nelson, ... arXiv preprint arXiv:1905.03030, 2019 | 62 | 2019 |
| Top-kast: Top-k always sparse training S Jayakumar, R Pascanu, J Rae, S Osindero, E Elsen Advances in Neural Information Processing Systems 33, 20744-20754, 2020 | 51 | 2020 |
| Cyprien de Masson d’Autume JW Rae, S Borgeaud, T Cai, K Millican, J Hoffmann, F Song, J Aslanides, ... | 44 | 2021 |
| Powerpropagation: A sparsity inducing weight reparameterisation J Schwarz, S Jayakumar, R Pascanu, PE Latham, Y Teh Advances in neural information processing systems 34, 28889-28903, 2021 | 21 | 2021 |
| Low-pass recurrent neural networks-a memory architecture for longer-term correlation discovery T Stepleton, R Pascanu, W Dabney, SM Jayakumar, H Soyer, R Munos arXiv preprint arXiv:1805.04955, 2018 | 4 | 2018 |
| Reinforcement learning using agent curricula W Czarnecki, S Jayakumar US Patent 11,113,605, 2021 | 2 | 2021 |
| Perception-Prediction-Reaction Agents for Deep Reinforcement Learning A Stooke, V Dalibard, SM Jayakumar, WM Czarnecki, M Jaderberg Workshop on “Structure & Priors in Reinforcement Learning” at ICLR 2019, 2019 | 2 | 2019 |
| System and method for training a sparse neural network whilst maintaining sparsity SM Jayakumar, R Pascanu, JW Rae, S Osindero, EK Elsen US Patent App. 17/914,035, 2023 | | 2023 |
| Gated attention neural networks E Parisotto, H Song, JW Rae, SM Jayakumar, ME Jaderberg, R Pascanu, ... US Patent App. 17/763,984, 2022 | | 2022 |
| Selecting actions by reverting to previous learned action selection policies S Ritter, XJ Wang, S Jayakumar, R Pascanu, C Blundell, M Botvinick US Patent 11,423,300, 2022 | | 2022 |
Razvan PascanuResearch Scientist at Google DeepMindVerified email at google.com
