| Towards revealing the mystery behind chain of thought: a theoretical perspective G Feng, B Zhang, Y Gu, H Ye, D He, L Wang Advances in Neural Information Processing Systems 36, 70757-70798, 2023 | 211 | 2023 |
| Guided diffusion model for adversarial purification from random noise Q Wu, H Ye, Y Gu arXiv preprint arXiv:2206.10875, 2022 | 43 | 2022 |
| Denoising masked autoencoders help robust classification QL Wu, H Ye, Y Gu, H Zhang, L Wang, D He arXiv preprint arXiv:2210.06983, 2022 | 24 | 2022 |
| How numerical precision affects mathematical reasoning capabilities of llms G Feng, K Yang, Y Gu, X Ai, S Luo, J Sun, D He, Z Li, L Wang arXiv preprint arXiv:2410.13857, 2024 | 8 | 2024 |
| Denoising masked autoencoders are certifiable robust vision learners Q Wu, H Ye, Y Gu, H Zhang, L Wang, D He arXiv preprint arXiv:2210.06983, 2022 | 8 | 2022 |
| Flats: Principled out-of-distribution detection with feature-based likelihood ratio score H Lin, Y Gu arXiv preprint arXiv:2310.05083, 2023 | 6 | 2023 |
| Towards Differentiable Multilevel Optimization: A Gradient-Based Approach Y Gu, X Chen arXiv preprint arXiv:2410.11312, 2024 | | 2024 |
| Representation of General Continuous Anti-symmetric Function H Ye, R Li, Y Gu, Y Lu, D He, L Wang arXiv preprint arXiv:2402.15167, 2024 | | 2024 |
