Pitfalls of in-domain uncertainty estimation and ensembling in deep learning A Ashukha, A Lyzhov, D Molchanov, D Vetrov International Conference on Learning Representations (ICLR), 2020 | 376 | 2020 |
Inverse scaling: When bigger isn't better IR McKenzie, A Lyzhov, M Pieler, A Parrish, A Mueller, A Prabhu, ... Transactions on Machine Learning Research, 2023 | 84* | 2023 |
Greedy policy search: A simple baseline for learnable test-time augmentation A Lyzhov, Y Molchanova, A Ashukha, D Molchanov, D Vetrov Proceedings of the 36th Conference on Uncertainty in Artificial Intelligence …, 2020 | 84 | 2020 |
Inverse scaling prize: Second round winners I McKenzie, A Lyzhov, A Parrish, A Prabhu, A Mueller, N Kim, S Bowman, ... Fund for Alignment Research (FAR), 2022 | 16 | 2022 |
Normative disagreement as a challenge for cooperative AI J Stastny, M Riché, A Lyzhov, J Treutlein, A Dafoe, J Clifton Cooperative AI workshop at NeurIPS 2021, 2021 | 9 | 2021 |
Steering without side effects: Improving post-deployment control of language models AC Stickland, A Lyzhov, J Pfau, S Mahdi, SR Bowman arXiv preprint arXiv:2406.15518, 2024 | 7 | 2024 |
Cross-Pollinated Deep Ensembles A Lyzhov, D Voronkova, D Vetrov NeurIPS Europe meetup on Bayesian Deep Learning, https://github.com …, 2020 | | 2020 |