Poster · Sydney
Words Before Pixels: Selective Modality Routing for Vision-Language Model Unlearning
- When
- Tue 8 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 2
- Authors
- Laura Yao, Haochen Zhang, Jinhao Duan, Sijia Liu, Tianlong Chen
- Organisations
- University of North Carolina at Chapel Hill, Rice University, Michigan State University, MIT-IBM Watson AI Lab
- QRS classification
- Language models, Computer vision, Safety, fairness and privacy