zhrli's picture

zhrli

ailor

·

AI & ML interests

LLM Safety

Recent Activity

upvoted a paper about 23 hours ago

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

updated a dataset 3 months ago

ailor/AdvBench-omni

new activity 4 months ago

ailor/AdvBench-omni:[bot] Conversion to Parquet

View all activity

Organizations

None yet

upvoted a paper about 23 hours ago

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

Paper • 2606.11817 • Published 2 days ago • 17

upvoted a paper 4 months ago

Omni-Safety under Cross-Modality Conflict: Vulnerabilities, Dynamics Mechanisms and Efficient Alignment

Paper • 2602.10161 • Published Feb 10 • 1

upvoted a paper 9 months ago

Fine-tuning Done Right in Model Editing

Paper • 2509.22072 • Published Sep 26, 2025 • 28