Poster · Sydney
CrossSteer:Cross-Modal Safety Steering for Audio-Language Models
- When
- Tue 8 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 1
- Authors
- Houde Dong, Weifei Jin, Yuxin Cao, Wei Song, Derui Wang, Jie Hao
- Organisations
- Beijing University of Posts and Telecommunications, Duke University, National University of Singapore, CSIRO
- QRS classification
- Language models, Safety, fairness and privacy, Speech and audio