| Towards the generalization of contrastive self-supervised learning W Huang*, M Yi*, X Zhao* International Conference on Learning Representations (ICLR-2023), 2021 | 94 | 2021 |
| Improved OOD Generalization via Adversarial Training and Pre-training M Yi, L Hou, J Sun, L Shang, X Jiang, Q Liu, ZM Ma International Conference on Machine Learning (ICML-2021), 2021 | 68 | 2021 |
| Out-of-distribution Generalization with Causal Invariant Transformations R Wang*, M Yi*, Z Chen, S Zhu Conference on Computer Vision and Pattern Recognition (CVPR-2022), 2022 | 56 | 2022 |
| Stabilize deep ResNet with a sharp scaling factor H Zhang, D Yu, M Yi, W Chen, TY Liu Machine Learning 111 (9), 3359-3392, 2022 | 29* | 2022 |
| Positively scale-invariant flatness of relu neural networks M Yi, Q Meng, W Chen, Z Ma, TY Liu arXiv preprint arXiv:1903.02237, 2019 | 24 | 2019 |
| Reweighting Augmented Samples by Minimizing the Maximal Expected Loss M Yi, L Hou, L Shang, X Jiang, Q Liu, ZM Ma International Conference on Learning Representations (ICLR-2021), 2021 | 21 | 2021 |
| SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models S Xue, M Yi, W Luo, S Zhang, J Sun, Z Li, ZM Ma Conference on Neural Information Processing Systems (NeurIPS-2023), 2023 | 11 | 2023 |
| On the generalization of diffusion model M Yi, J Sun, Z Li arXiv preprint arXiv:2305.14712, 2023 | 10 | 2023 |
| Breaking Correlation Shift via Conditional Invariant Regularizer M Yi, R Wang, J Sun, Z Li, ZM Ma International Conference on Learning Representations (ICLR-2023), 2023 | 8* | 2023 |
| BN-invariant sharpness regularizes the training model to better generalization M Yi, H Zhang, W Chen, ZM Ma, TY Liu International Joint Conference on Artificial Intelligence (IJCAI-2019), 2019 | 5 | 2019 |
| Accelerating Training of Batch Normalization: A Manifold Perspective M Yi Uncertainty in Artificial Intelligence (UAI-2022), 2021 | 4 | 2021 |
| Characterization of Excess Risk for Locally Strongly Convex Population Risk M Yi*, R Wang*, ZM Ma Conference on Neural Information Processing Systems (NeurIPS-2022), 2020 | 3* | 2020 |
| Improving Deep Learning by Regularized Scale-Free MSE of Representations X Luo, M Yi, Y Wang International Conference on Neural Information Processing (ICONIP-19), 2019 | 1 | 2019 |
| Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model M Yi*, A Li*, Y Xin*, Z Li Conference on Neural Information Processing Systems (NeurIPS-2024), 2024 | | 2024 |
| Enhancing Text-to-Image Editing via Hybrid Mask-Informed Fusion A Li*, M Yi*, Z Li arXiv preprint arXiv:2405.15313, 2024 | | 2024 |
| Towards Understanding the Riemannian SGD and SVRG Flows on Wasserstein Probabilistic Space M Yi, B Wang arXiv preprint arXiv:2401.13530, 2024 | | 2024 |
Wei Chen (陈薇)Institute of Computing Technology, Chinese Academy of SciencesVerified email at ict.ac.cn
