Latent Adversarial Regularization for Offline Preference Optimization.

Yinglun Xu

Enyi Jiang Yibo Jacky Zhang Yinglun Xu Andreas Haupt Nancy M. Amato Sanmi Koyejo Latent Adversarial Regularization for Offline Preference Optimization. 2026 January abs/2601.22083 CoRR https://doi.org/10.48550/arXiv.2601.22083 db/journals/corr/corr2601.html#abs-2601-22083 streams/journals/corr

Yinglun Xu Gagandeep Singh 0001 Universal Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning. 2025 2025 Trans. Mach. Learn. Res. https://openreview.net/forum?id=MX0aDKu8lY db/journals/tmlr/tmlr2025.html#XuS25 streams/journals/tmlr

Yinglun Xu Tarun Suresh Rohan Gumaste David Zhu Ruirui Li 0002 Zhengyang Wang Haoming Jiang Xianfeng Tang Qingyu Yin Monica Xiao Cheng Qi Zeng 0001 Chao Zhang 0014 Gagandeep Singh 0001 Two-Step Offline Preference-Based Reinforcement Learning on Explicitly Constrained Policies. 2025 2025 Trans. Mach. Learn. Res. https://openreview.net/forum?id=LxPg5GJuY3 db/journals/tmlr/tmlr2025.html#XuSGZLWJTYCZZS25 streams/journals/tmlr

Anjiang Wei Tarun Suresh Huanmi Tan Yinglun Xu Gagandeep Singh 0001 Ke Wang 0022 Alex Aiken Improving Assembly Code Performance with Large Language Models via Reinforcement Learning. 2025 May abs/2505.11480 CoRR https://doi.org/10.48550/arXiv.2505.11480 db/journals/corr/corr2505.html#abs-2505-11480 streams/journals/corr

Yinglun Xu Hangoo Kang Tarun Suresh Yuxuan Wan Gagandeep Singh 0001 Learning a Pessimistic Reward Model in RLHF. 2025 May abs/2505.20556 CoRR https://doi.org/10.48550/arXiv.2505.20556 db/journals/corr/corr2505.html#abs-2505-20556 streams/journals/corr

Yinglun Xu Gagandeep Singh 0001 Efficient Two-Phase Offline Deep Reinforcement Learning from Preference Feedback. 2024 abs/2401.00330 CoRR https://doi.org/10.48550/arXiv.2401.00330 db/journals/corr/corr2401.html#abs-2401-00330

Yinglun Xu Rohan Gumaste Gagandeep Singh 0001 Reward Poisoning Attack Against Offline Reinforcement Learning. 2024 abs/2402.09695 CoRR https://doi.org/10.48550/arXiv.2402.09695 db/journals/corr/corr2402.html#abs-2402-09695

Yinglun Xu David Zhu Rohan Gumaste Gagandeep Singh 0001 Optimal Reward Labeling: Bridging Offline Preference and Reward-Based Reinforcement Learning. 2024 abs/2406.10445 CoRR https://doi.org/10.48550/arXiv.2406.10445 db/journals/corr/corr2406.html#abs-2406-10445

Yinglun Xu Zhiwei Wang Gagandeep Singh 0001 Robust Thompson Sampling Algorithms Against Reward Poisoning Attacks. 2024 abs/2410.19705 CoRR https://doi.org/10.48550/arXiv.2410.19705 db/journals/corr/corr2410.html#abs-2410-19705 streams/journals/corr

Yinglun Xu Qi Zeng 0001 Gagandeep Singh 0001 Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning. 2023 2023 Trans. Mach. Learn. Res. https://openreview.net/forum?id=25G63lDHV2 db/journals/tmlr/tmlr2023.html#Xu0023

Yinglun Xu Gagandeep Singh 0001 Black-Box Targeted Reward Poisoning Attack Against Online Deep Reinforcement Learning. 2023 abs/2305.10681 CoRR https://doi.org/10.48550/arXiv.2305.10681 db/journals/corr/corr2305.html#abs-2305-10681

Yinglun Xu Bhuvesh Kumar Jacob D. Abernethy On the Robustness of Epoch-Greedy in Multi-Agent Contextual Bandit Mechanisms. 2023 abs/2307.07675 CoRR https://doi.org/10.48550/arXiv.2307.07675 db/journals/corr/corr2307.html#abs-2307-07675

Yinglun Xu Qi Zeng 0001 Gagandeep Singh 0001 Efficient Reward Poisoning Attacks on Online Deep Reinforcement Learning. 2022 abs/2205.14842 CoRR https://doi.org/10.48550/arXiv.2205.14842 db/journals/corr/corr2205.html#abs-2205-14842

Yinglun Xu Bhuvesh Kumar Jacob D. Abernethy Observation-Free Attacks on Stochastic Bandits. 22550-22561 2021 NeurIPS https://proceedings.neurips.cc/paper/2021/hash/be315e7f05e9f13629031915fe87ad44-Abstract.html conf/nips/2021 db/conf/nips/neurips2021.html#XuKA21 Jacob D. Abernethy Alex Aiken Nancy M. Amato Monica Xiao Cheng Rohan Gumaste Andreas Haupt Enyi Jiang Haoming Jiang Hangoo Kang Oluwasanmi KoyejoSanmi Koyejo Bhuvesh Kumar Ruirui Li 0002 Gagandeep Singh 0001 Tarun Suresh Huanmi Tan Xianfeng Tang Yuxuan Wan Ke Wang 0022 Zhengyang Wang Zhiwei Wang Anjiang Wei Qingyu Yin Qi Zeng 0001 Chao Zhang 0014 Yibo Jacky Zhang David Zhu