| Humanity's last exam L Phan, A Gatti, Z Han, N Li, J Hu, H Zhang, CBC Zhang, M Shaaban, ... arXiv preprint arXiv:2501.14249, 2025 | 301 | 2025 |
| Don’t waste your bits! squeeze activations and gradients for deep neural networks via tinyscript F Fu, Y Hu, Y He, J Jiang, Y Shao, C Zhang, B Cui International Conference on Machine Learning, 3304-3314, 2020 | 78 | 2020 |
| Revisiting scalarization in multi-task learning: A theoretical perspective Y Hu, R Xian, Q Wu, Q Fan, L Yin, H Zhao Advances in Neural Information Processing Systems 36, 48510-48533, 2023 | 66 | 2023 |
| Sok: Privacy-preserving data synthesis Y Hu, F Wu, Q Li, Y Long, GM Garrido, C Ge, B Ding, D Forsyth, B Li, ... 2024 IEEE Symposium on Security and Privacy (SP), 4696-4713, 2024 | 45 | 2024 |
| Localize-and-stitch: Efficient model merging via sparse task arithmetic Y He, Y Hu, Y Lin, T Zhang, H Zhao Transactions on Machine Learning Research (TMLR 2025), 2025 | 39 | 2025 |
| Towards understanding the data dependency of mixup-style training M Chidambaram, X Wang, Y Hu, C Wu, R Ge International Conference on Learning Representations (ICLR 2022 spotlight), 2022 | 27 | 2022 |
| Most influential subset selection: Challenges, promises, and beyond Y Hu, P Hu, H Zhao, J Ma Advances in Neural Information Processing Systems 37, 119778-119810, 2024 | 21 | 2024 |
| Actor-critic is implicitly biased towards high entropy optimal policies Y Hu, Z Ji, M Telgarsky International Conference on Learning Representations (ICLR 2022), 2022 | 21 | 2022 |
| Is Vertical Logistic Regression Privacy-Preserving? A Comprehensive Privacy Analysis and Beyond Y Hu, T Cai, J Shan, S Tang, C Cai, E Song, B Li, D Song arXiv preprint arXiv:2207.09087, 2022 | 14 | 2022 |
| Understanding the impact of adversarial robustness on accuracy disparity Y Hu, F Wu, H Zhang, H Zhao International Conference on Machine Learning, 13679-13709, 2023 | 12 | 2023 |
| HPL-ViT: A Unified Perception Framework for Heterogeneous Parallel LiDARs in V2V Y Liu, B Sun, Y Li, Y Hu, FY Wang IEEE International Conference on Robotics and Automation (ICRA 2024), 2024 | 8 | 2024 |
| A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning Y Hu, F Wu, H Ye, D Forsyth, J Zou, N Jiang, JW Ma, H Zhao NeurIPS 2025 Oral, 2025 | 5 | 2025 |
| MergeBench: A Benchmark for Merging Domain-Specialized LLMs Y He, S Zeng, Y Hu, R Yang, T Zhang, H Zhao NeurIPS 2025 Datasets and Benchmarks Track, 2025 | 5 | 2025 |
| Empirical Privacy Variance Y Hu, F Wu, R Xian, Y Liu, L Zakynthinou, P Kamath, C Zhang, D Forsyth International Conference on Machine Learning (ICML 2025), 2025 | 2 | 2025 |
| ACTG-ARL: Differentially Private Conditional Text Generation with RL-Boosted Control Y Hu, R McKenna, D Yu, S Wu, H Zhao, Z Xu, P Kairouz arXiv preprint arXiv:2510.18232, 2025 | 1 | 2025 |
| A Survey of Data Attribution: Methods, Applications, and Evaluation in the Era of Generative AI J Deng, Y Hu, P Hu, TW Li, S Liu, JT Wang, D Ley, Q Dai, B Huang, ... | | 2025 |
| Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining W Wang, J Deng, Y Hu, S Zhang, X Jiang, R Zhang, H Zhao, JW Ma NeurIPS 2025, 2025 | | 2025 |
| An Improved Autoregressive Evaluation Paradigm for Large Language Models J Zhang, R Pan, Y Hu, K SHUM, G Yao, X Liu, R Pi, H Dong, S Diao, Y Lin, ... ACM Transactions on Intelligent Systems and Technology, 2025 | | 2025 |
