Rom
wrom
AI & ML interests
LLM Security
Recent Activity
upvoted a paper 27 days ago
Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software authored
a paper
29 days ago
Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models upvoted a paper 29 days ago
Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models Organizations
