Rom's picture

2 11

Rom

wrom

·

wr0om

AI & ML interests

LLM Security

Recent Activity

authored a paper about 16 hours ago

Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models

upvoted a paper about 20 hours ago

Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models

upvoted a paper 29 days ago

The Poisoned Apple Effect: Strategic Manipulation of Mediated Markets via Technology Expansion of AI Agents

View all activity

Organizations

wrom 's Spaces 2

silenced_biases

Sbb