most citedUnderstanding How University Guidelines Address Privacy and Security Issues of Generative AI in Academic Settings

4 citations · 4 across the 4 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

You Can't Have It Both Ways: Concept Entanglement Limits Diffusion Model Unlearning

Yian Wang, Ali Ebrahimpour-Boroojeny, Hari Sundaram +1

Concept unlearning in text-to-image diffusion models aims to suppress a target concept (e.g., \texttt{horse}) while preserving related but distinct content (e.g., \texttt{donkey}),…