Tu Trinh
tu-trinh-scale
ยท
AI & ML interests
None yet
Recent Activity
authored a paper about 18 hours ago
A StrongREJECT for Empty Jailbreaks authored a paper about 18 hours ago
Refusal-Trained LLMs Are Easily Jailbroken As Browser Agents authored a paper about 18 hours ago
Learning to Coordinate with Experts