Bayesian deep ensembles via the neural tangent kernel B He, B Lakshminarayanan, YW Teh Advances in neural information processing systems 33, 1010-1022, 2020 | 126 | 2020 |
Stable resnet S Hayou, E Clerico, B He, G Deligiannidis, A Doucet, J Rousseau International Conference on Artificial Intelligence and Statistics, 1324-1332, 2021 | 51 | 2021 |
The shaped transformer: Attention models in the infinite depth-and-width limit L Noci, C Li, M Li, B He, T Hofmann, CJ Maddison, D Roy Advances in Neural Information Processing Systems 36, 2024 | 21 | 2024 |
Deep transformers without shortcuts: Modifying self-attention for faithful signal propagation B He, J Martens, G Zhang, A Botev, A Brock, SL Smith, YW Teh arXiv preprint arXiv:2302.10322, 2023 | 21 | 2023 |
Exploring the gap between collapsed & whitened features in self-supervised learning B He, M Ozay International Conference on Machine Learning, 8613-8634, 2022 | 21 | 2022 |
Feature kernel distillation B He, M Ozay International Conference on Learning Representations, 2022 | 18 | 2022 |
Simplifying transformer blocks B He, T Hofmann arXiv preprint arXiv:2311.01906, 2023 | 16 | 2023 |
Uncertainr: Uncertainty quantification of end-to-end implicit neural representations for computed tomography F Vasconcelos, B He, N Singh, YW Teh arXiv preprint arXiv:2202.10847, 2022 | 16 | 2022 |
Efficient Bayesian inference of instantaneous reproduction numbers at fine spatial scales, with an application to mapping and nowcasting the Covid-19 epidemic in British local … YW Teh, B Elesedy, B He, M Hutchinson, S Zaidi, A Bhoopchand, ... Journal of the Royal Statistical Society Series A: Statistics in Society 185 …, 2022 | 13 | 2022 |
Effectiveness and resource requirements of test, trace and isolate strategies for COVID in the UK B He, S Zaidi, B Elesedy, M Hutchinson, A Paleyes, G Harling, ... Royal Society open science 8 (3), 201491, 2021 | 10* | 2021 |
Recurrent Distance Filtering for Graph Representation Learning Y Ding, A Orvieto, B He, T Hofmann Forty-first International Conference on Machine Learning, 2024 | 3* | 2024 |
Probabilistic fine-tuning of pruning masks and pac-bayes self-bounded learning S Hayou, B He, GK Dziugaite arXiv preprint arXiv:2110.11804, 2021 | 3 | 2021 |
Understanding and Minimising Outlier Features in Neural Network Training B He, L Noci, D Paliotta, I Schlag, T Hofmann arXiv preprint arXiv:2405.19279, 2024 | | 2024 |
Hallmarks of Optimization Trajectories in Neural Networks and LLMs: The Lengths, Bends, and Dead Ends SP Singh, B He, T Hofmann, B Schölkopf arXiv preprint arXiv:2403.07379, 2024 | | 2024 |
Authors’ Reply to the Discussion of ‘Efficient Bayesian Inference of Instantaneous Reproduction Numbers at Fine Spatial Scales, with an Application to Mapping and Nowcasting … YW Teh, B Elesedy, B He, M Hutchinson, S Zaidi, A Bhoopchand, ... Journal of the Royal Statistical Society Series A: Statistics in Society 185 …, 2022 | | 2022 |
On kernel and feature learning in neural networks B He University of Oxford, 2022 | | 2022 |
Hallmarks of Optimization Trajectories in Neural Networks and LLMs: Directional Exploration and Redundancy SP Singh, B He, T Hofmann, B Schölkopf ICML 2024 Workshop on Theoretical Foundations of Foundation Models, 0 | | |
Unveiling Grokking: Analyzing Feature Learning Dynamics During Training JS Baustiste, G Bachmann, B He, L Noci, T Hofmann High-dimensional Learning Dynamics 2024: The Emergence of Structure and …, 0 | | |