作者位次 #3/8ICLR 2026Poster· Computer Vision / Image and Video Generation
CASteer: Cross-Attention Steering for Controllable Concept Erasure
Tatiana Gaintseva · Andreea-Maria Oncescu · Chengcheng Ma · Ziquan Liu · Martin Benning · Gregory Slabaugh · Jiankang Deng · Ismail Elezi