Profiles2024-2026
Jiongxiao Wang
University of Wisconsin-Madison
3Papers
0Last author
7Unique co-authors
3First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers3
- Reinforcement Learning for Self-Improving Agent with Skill LibraryAuthor 1 of 9ACL 2026 · 52 citations
- BackdoorAlign: Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety AlignmentAuthor 1 of 10NeurIPS 2024 · 47 citations
- RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language ModelsAuthor 1 of 5ACL 2024
