CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models

NeurIPSSpotlight2025

Authors
Shristi Das Biswas, Arani Roy, Kaushik Roy
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

As Text-to-Image models continue to evolve, so does the risk of generating unsafe, copyrighted, or privacy-violating content…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

text-to-image diffusion privacy

Related NeurIPS papers

← All NeurIPS 2025 Spotlight papers · Browse the whole archive