| Stability analysis and generalization bounds of adversarial training J Xiao, Y Fan, R Sun, J Wang, ZQ Luo Advances in Neural Information Processing Systems 35, 15446-15459, 2022 | 61 | 2022 |
| 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 120 (552), 2154-2164, 2025 | 57 | 2025 |
| Preserving diversity in supervised fine-tuning of large language models Z Li, C Chen, T Xu, Z Qin, J Xiao, ZQ Luo, R Sun The Thirteenth International Conference on Learning Representations, 2025 | 38 | 2025 |
| Adversarial rademacher complexity of deep neural networks J Xiao, Y Fan, R Sun, ZQ Luo arXiv preprint arXiv:2211.14966, 2022 | 31 | 2022 |
| Magnetic preference optimization: Achieving last-iterate convergence for language model alignment M Wang, C Ma, Q Chen, L Meng, Y Han, J Xiao, Z Zhang, J Huo, WJ Su, ... The Thirteenth International Conference on Learning Representations, 2024 | 22 | 2024 |
| Entropic distribution matching for supervised fine-tuning of LLMs: Less overfitting and better diversity Z Li, C Chen, T Xu, Z Qin, J Xiao, R Sun, ZQ Luo NeurIPS 2024 FITML, 2024 | 22 | 2024 |
| Understanding adversarial robustness against on-manifold adversarial examples J Xiao, L Yang, Y Fan, J Wang, ZQ Luo Pattern Recognition 159, 111071, 2022 | 21 | 2022 |
| Fine-Tuning Attention Modules Only: Enhancing Weight Disentanglement in Task Arithmetic R Jin, B Hou, J Xiao, WJ Su, L Shen The Thirteenth International Conference on Learning Representations, 2025 | 20* | 2025 |
| Pac-bayesian spectrally-normalized bounds for adversarially robust generalization J Xiao, R Sun, ZQ Luo Advances in Neural Information Processing Systems 36, 36305-36323, 2023 | 16 | 2023 |
| Statistical impossibility and possibility of aligning llms with human preferences: From condorcet paradox to nash equilibrium K Liu, Q Long, Z Shi, WJ Su, J Xiao arXiv preprint arXiv:2503.10990, 2025 | 15 | 2025 |
| Restoring calibration for aligned large language models: A calibration-aware fine-tuning approach J Xiao, B Hou, Z Wang, R Jin, Q Long, WJ Su, L Shen The 42nd International Conference on Machine Learning, 68364-68390, 2025 | 13 | 2025 |
| Improving Adversarial Training for Multiple Perturbations through the Lens of Uniform Stability J Xiao, Z Qin, Y Fan, B Wu, J Wang, ZQ Luo ICML 2023 AdvML-Frontiers, 2023 | 12* | 2023 |
| Uniformly stable algorithms for adversarial training and beyond J Xiao, J Zhang, ZQ Luo, A Ozdaglar The 41st International Conference on Machine Learning, 54319-54340, 2024 | 10* | 2024 |
| Bridging the gap: Rademacher complexity in robust and standard generalization J Xiao, R Sun, Q Long, W Su The Thirty Seventh Annual Conference on Learning Theory, 5074-5075, 2024 | 9* | 2024 |
| Fundamental limits of game-theoretic llm alignment: Smith consistency and preference matching Z Shi, K Liu, Q Long, WJ Su, J Xiao arXiv preprint arXiv:2505.20627, 2025 | 7 | 2025 |
| Pac-bayesian adversarially robust generalization bounds for deep neural networks J Xiao, R Sun, ZQ Luo ICML 2023 AdvML-Frontiers, 2023 | 6 | 2023 |
| Theoretical Tensions in RLHF: Reconciling Empirical Success with Inconsistencies in Social Choice Theory J Xiao, Z Shi, K Liu, Q Long, WJ Su arXiv preprint arXiv:2506.12350, 2025 | 4 | 2025 |
| Entropic Distribution Matching in Supervised Fine-tuning of LLMs: Less Overfitting and Better Diversity.(2024) Z Li, C Chen, T Xu, Z Qin, J Xiao, R Sun, ZQ Luo URL https://arxiv. org/abs/2408.16673, 0 | 4 | |
| Understanding Adversarially Robust Generalization: A Learning Theory Perspective J Xiao The Chinese University of Hong Kong, Shenzhen, 2023 | | 2023 |
| A Fine-Grained Analysis of Pure Semantic Preference Alignment in Large Language Models R Jin, J Xiao, N Ruia, Q Long, WJ Su | | |
Zhi-Quan LuoProfessor, The Chinese University of Hong Kong, Shenzhen, ChinaVerified email at cuhk.edu.cn
