| Toward understanding the feature learning process of self-supervised contrastive learning Z Wen, Y Li International Conference on Machine Learning, 11112-11122, 2021 | 103 | 2021 |
| Improving multi-modal learning with uni-modal teachers C Du, T Li, Y Liu, Z Wen, T Hua, Y Wang, H Zhao arXiv preprint arXiv:2106.11059, 2021 | 29 | 2021 |
| The mechanism of prediction head in non-contrastive self-supervised learning Z Wen, Y Li Advances in Neural Information Processing Systems 35, 24794-24809, 2022 | 27 | 2022 |
| What matters in the structured pruning of generative language models? M Santacroce, Z Wen, Y Shen, Y Li arXiv preprint arXiv:2302.03773, 2023 | 12 | 2023 |
| Transformers Provably Learn Feature-Position Correlations in Masked Image Modeling Y Huang, Z Wen, Y Chi, Y Liang arXiv preprint arXiv:2403.02233, 2024 | 1 | 2024 |
| Revisiting Disentanglement in Downstream Tasks: A Study on Its Necessity for Abstract Visual Reasoning R Nai, Z Wen, J Li, Y Li, Y Gao arXiv preprint arXiv:2403.00352, 2024 | | 2024 |
| On the Necessity of Disentangled Representations for Downstream Tasks R Nai, Z Wen, J Li, Y Li, Y Gao | | 2022 |
