UTAustin-AIHealth

AI & ML interests

None defined yet.

Recent Activity

jyhong836  authored a paper about 1 month ago

Safe and Robust Watermark Injection with a Single OoD Image

jyhong836  authored a paper about 1 month ago

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning

jyhong836  authored a paper 7 months ago

MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models

View all activity

Team members 3