| ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method for Aligning Large Language Models Z Li, T Xu, Y Zhang, Z Lin, Y Yu, R Sun, ZQ Luo International Conference on Machine Learning (ICML), 2024 | 187* | 2024 |
| Error bounds of imitating policies and environments T Xu, Z Li, Y Yu Advances in Neural Information Processing Systems (NeurIPS) 33, 15737-15749, 2020 | 140* | 2020 |
| Adam-mini: Use fewer learning rates to gain more Y Zhang, C Chen, Z Li, T Ding, C Wu, DP Kingma, Y Ye, ZQ Luo, R Sun International Conference on Learning Representations (ICLR), 2025 | 101* | 2025 |
| Why transformers need adam: A hessian perspective Y Zhang, C Chen, T Ding, Z Li, R Sun, ZQ Luo Neural Information Processing System (NeurIPS), 2024 | 98 | 2024 |
| Preserving diversity in supervised fine-tuning of large language models Z Li, C Chen, T Xu, Z Qin, J Xiao, ZQ Luo, R Sun International Conference on Learning Representations (ICLR), 2025 | 61* | 2025 |
| On the algorithmic bias of aligning large language models with rlhf: Preference collapse and matching regularization J Xiao, Z Li, X Xie, E Getzen, C Fang, Q Long, WJ Su Journal of the American Statistical Association, 1-21, 2025 | 57 | 2025 |
| Error bounds of imitating policies and environments for reinforcement learning T Xu, Z Li, Y Yu IEEE Transactions on Pattern Analysis and Machine Intelligence 44 (10), 6968 …, 2021 | 53 | 2021 |
| When is RL better than DPO in RLHF? A Representation and Optimization Perspective Z Li*, T Xu*, Y Yu Tiny Paper of International Conference on Learning Representations (ICLR), 2024 | 42* | 2024 |
| Treepo: Bridging the gap of policy optimization and efficacy and inference efficiency with heuristic tree-based modeling Y Li, Q Gu, Z Wen, Z Li, T Xing, S Guo, T Zheng, X Zhou, X Qu, W Zhou, ... arXiv preprint arXiv:2508.17445, 2025 | 26* | 2025 |
| Understanding and Mitigating Hallucination in Large Vision-Language Models via Modular Attribution and Intervention T Yang, Z Li, J Cao, C Xu International Conference on Learning Representations (ICLR), 2025 | 26* | 2025 |
| HyperDQN: A Randomized Exploration Method for Deep Reinforcement Learning Z Li, Y Li, Y Zhang, T Zhang, ZQ Luo International Conference on Learning Representations (ICLR), 2022 | 26 | 2022 |
| Imitation learning from imperfection: Theoretical justifications and algorithms Z Li*, T Xu*, Z Qin, Y Yu, ZQ Luo Neural Information Processing System (NeurIPS), 2023 | 25 | 2023 |
| Self-Guided Evolution Strategies with Historical Estimated Gradients FY Liu, ZN Li, C Qian International Joint Conferences on Artificial Intelligence (IJCAI), 2020 | 25 | 2020 |
| A survey on large language models for mathematical reasoning PY Wang, TS Liu, C Wang, Z Li, Y Wang, S Yan, C Jia, XH Liu, X Chen, ... ACM Computing Surveys, 2025 | 22 | 2025 |
| Understanding adversarial imitation learning in small sample regime: A stage-coupled analysis T Xu*, Z Li*, Y Yu, ZQ Luo arXiv preprint arXiv:2208.01899, 2022 | 21* | 2022 |
| Provably Efficient Adversarial Imitation Learning with Unknown Transitions T Xu*, Z Li*, Y Yu, ZQ Luo Conference on Uncertainty in Artificial Intelligence (UAI), 2023 | 19 | 2023 |
| Rethinking ValueDice - Does It Really Improve Performance? Z Li*, T Xu*, Y Yu, ZQ Luo Blog of International Conference on Learning Representations (ICLR), 2022 | 19 | 2022 |
| Seed-oss open-source models BDS Team | 15 | 2025 |
| Self-Evolving Critique Abilities in Large Language Models Z Tang*, Z Li*, Z Xiao*, T Ding, R Sun, B Wang, D Liu, F Huang, T Liu, ... Second Conference on Language Modeling, 2025 | 14* | 2025 |
| Advancing zero-shot text-to-speech intelligibility across diverse domains via preference alignment X Zhang, Y Wang, C Wang, Z Li, Z Chen, Z Wu Proceedings of the 63rd Annual Meeting of the Association for Computational …, 2025 | 12 | 2025 |
Tian XuNanjing UniversityVerified email at lamda.nju.edu.cn
