| Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, et al. Training a helpful and harmless assistant with reinforcement learning from human feedback Y Bai, A Jones, K Ndousse, A Askell, A Chen, N DasSarma arXiv preprint arXiv:2204.05862 1, 2022 | 947* | 2022 |
| Constitutional AI: Harmlessness from AI Feedback Y Bai, S Kadavath, S Kundu, A Askell, J Kernion, A Jones, A Chen, ... arXiv preprint arXiv:2212.08073, 2022 | 751 | 2022 |
| Deep Ensembles: A Loss Landscape Perspective S Fort, H Hu, B Lakshminarayanan arXiv preprint arXiv:1912.02757, 2019 | 617 | 2019 |
| Exploring the limits of out-of-distribution detection S Fort, J Ren, B Lakshminarayanan Advances in Neural Information Processing Systems 34, 7068-7081, 2021 | 304 | 2021 |
| Red teaming language models to reduce harms: Methods, scaling behaviors, and lessons learned D Ganguli, L Lovitt, J Kernion, A Askell, Y Bai, S Kadavath, B Mann, ... arXiv preprint arXiv:2209.07858, 2022 | 291 | 2022 |
| Predictability and surprise in large generative models D Ganguli, D Hernandez, L Lovitt, A Askell, Y Bai, A Chen, T Conerly, ... Proceedings of the 2022 ACM Conference on Fairness, Accountability, and …, 2022 | 221 | 2022 |
| Training independent subnetworks for robust prediction M Havasi, R Jenatton, S Fort, JZ Liu, J Snoek, B Lakshminarayanan, ... arXiv preprint arXiv:2010.06610, 2020 | 198 | 2020 |
| Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the neural tangent kernel S Fort, GK Dziugaite, M Paul, S Kharaghani, DM Roy, S Ganguli Advances in Neural Information Processing Systems 33, 5850-5861, 2020 | 160 | 2020 |
| A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detection J Ren, S Fort, J Liu, AG Roy, S Padhy, B Lakshminarayanan arXiv preprint arXiv:2106.09022, 2021 | 159 | 2021 |
| The Break-Even Point on Optimization Trajectories of Deep Neural Networks S Jastrzebski, M Szymczak, S Fort, D Arpit, J Tabor, K Cho, K Geras arXiv preprint arXiv:2002.09572, 2020 | 156 | 2020 |
| Language models (mostly) know what they know S Kadavath, T Conerly, A Askell, T Henighan, D Drain, E Perez, ... arXiv preprint arXiv:2207.05221, 2022 | 106 | 2022 |
| Gaussian Prototypical Networks for Few-Shot Learning on Omniglot S Fort arXiv preprint arXiv:1708.02735, 2017 | 98 | 2017 |
| Large Scale Structure of Neural Network Loss Landscapes S Fort, S Jastrzebski arXiv preprint arXiv:1906.04724, 2019 | 84 | 2019 |
| Stiffness: A new perspective on generalization in neural networks S Fort, PK Nowak, S Jastrzebski, S Narayanan arXiv preprint arXiv:1901.09491, 2019 | 82 | 2019 |
| Adaptive quantum state tomography with neural networks Y Quek, S Fort, HK Ng arXiv preprint arXiv:1812.06693, 2018 | 63 | 2018 |
| Measuring progress on scalable oversight for large language models SR Bowman, J Hyun, E Perez, E Chen, C Pettit, S Heiner, K Lukošiūtė, ... arXiv preprint arXiv:2211.03540, 2022 | 58 | 2022 |
| Discovery of gamma-ray pulsations from the transitional redback PSR J1227-4853 TJ Johnson, PS Ray, J Roy, CC Cheung, AK Harding, HJ Pletsch, S Fort, ... The Astrophysical Journal 806 (1), 91, 2015 | 58 | 2015 |
| The goldilocks zone: Towards better understanding of neural network loss landscapes S Fort, A Scherlis Proceedings of the AAAI Conference on Artificial Intelligence 33 (01), 3574-3581, 2019 | 44 | 2019 |
| Emergent properties of the local geometry of neural loss landscapes S Fort, S Ganguli arXiv preprint arXiv:1910.05929, 2019 | 42 | 2019 |
| Analyzing monotonic linear interpolation in neural network loss landscapes J Lucas, J Bae, MR Zhang, S Fort, R Zemel, R Grosse arXiv preprint arXiv:2104.11044, 2021 | 34* | 2021 |
Balaji LakshminarayananSenior Staff Research Scientist at Google DeepMind在 google.com 的电子邮件经过验证
