Poster · Sydney
Cascaded Sparse Autoencoders LearnMulti-Level Visual Concepts in Multimodal LLMs
- When
- Wed 9 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 4
- Authors
- Yusong Zhao, Hengyi Wang, Tanuja Ganu, Akshay Nambi, Hao Wang
- Organisations
- University of Illinois Urbana-Champaign, Microsoft
- QRS classification
- Language models, Computer vision