zhrli

ailor

·

AI & ML interests

LLM Safety

Recent Activity

upvoted a paper 4 days ago

Focused Omni-Modal GUI Agents

upvoted a paper 5 months ago

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

updated a dataset 7 months ago

ailor/AdvBench-omni

View all activity

Organizations

upvoted a paper 4 days ago

Focused Omni-Modal GUI Agents

Paper • 2610.26203 • Published 10 days ago • 231

upvoted a paper 5 months ago

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

Paper • 2606.11817 • Published Jun 10 • 18

upvoted a paper 9 months ago

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

Paper • 2602.10161 • Published Feb 10 • 1

upvoted a paper about 1 year ago

Fine-tuning Done Right in Model Editing

Paper • 2509.22072 • Published Sep 26, 2025 • 28