| A unified pruning framework for vision transformers H Yu, J Wu Science China Information Sciences 66 (7), 179101, 2023 | 63 | 2023 |
| Training vision transformers with only 2040 images YH Cao, H Yu, J Wu European Conference on Computer Vision, 220-237, 2022 | 59 | 2022 |
| Mixup without hesitation H Yu, H Wang, J Wu Image and Graphics: 11th International Conference, ICIG 2021, Haikou, China …, 2021 | 34 | 2021 |
| Compressing transformers: features are low-rank, but weights are not! H Yu, J Wu Proceedings of the AAAI Conference on Artificial Intelligence 37 (9), 11007 …, 2023 | 33 | 2023 |
| Fast k-means clustering with Anderson acceleration J Zhang, Y Yao, Y Peng, H Yu, B Deng arXiv preprint arXiv:1805.10638, 2018 | 10 | 2018 |
| Effectively Compress KV Heads for LLM H Yu, Z Yang, S Li, Y Li, J Wu arXiv preprint arXiv:2406.07056, 2024 | 8 | 2024 |
| Reviving undersampling for long-tailed learning H Yu, Y Du, J Wu Pattern Recognition 161, 111200, 2025 | 2 | 2025 |
| Treasures in Discarded Weights for LLM Quantization H Yu, Y Zhou, B Chen, Z Yang, S Li, Y Li, J Wu | | 2025 |
| Quantization without Tears M Fu, H Yu, J Shao, J Zhou, K Zhu, J Wu arXiv preprint arXiv:2411.13918, 2024 | | 2024 |
| Unified Low-rank Compression Framework for Click-through Rate Prediction H Yu, M Fu, J Ding, Y Zhou, J Wu Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and …, 2024 | | 2024 |
Jianxin Wu (吴建鑫)Nanjing UniversityVerified email at nju.edu.cn