Profiles2022-2026
Xin Liu
School of Information Science & Technology, ShanghaiTech University
13Papers
7Last author
9Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers13
- Keep the Best, Forget the Rest: Reliable Alignment with Order-Aware Preference OptimizationAuthor 4 of 6ICLR 2026
- Towards Achieving Optimal Strong Regret and Constraint Violation via Computationally Efficient Model-free RLAuthor 4 of 4ICML 2026
- Towards Safe and Optimal Online Bidding: A Modular Look-ahead Lyapunov FrameworkAuthor 9 of 9ICLR 2026
- Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy OptimizationAuthor 7 of 7NeurIPS 2025 · 9 citations
- On Stochastic Contextual Bandits with Knapsacks in Small Budget RegimeAuthor 2 of 2ICLR 2025
- Triple-Optimistic Learning for Stochastic Contextual Bandits with General ConstraintsAuthor 3 of 3ICML 2025
- Safe and Efficient: A Primal-Dual Method for Offline Convex CMDPs under Partial Data CoverageAuthor 4 of 4NeurIPS 2024 · 5 citations
- Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement LearningAuthor 4 of 4NeurIPS 2024 · 4 citations
- Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing NetworksAuthor 2 of 4NeurIPS 2023 · 13 citations
- Online Nonstochastic Control with Adversarial and Static ConstraintsAuthor 1 of 3ICML 2023 · 6 citations
- Neural Constrained Combinatorial BanditsAuthor 3 of 4INFOCOM 2023 · 5 citations
- Online Convex Optimization with Hard Constraints: Towards the Best of Two Worlds and BeyondAuthor 2 of 4NeurIPS 2022 · 76 citations
- A Provably-Efficient Model-Free Algorithm for Infinite-Horizon Average-Reward Constrained Markov Decision ProcessesAuthor 2 of 3AAAI 2022 · 31 citations
