Poster · Sydney
Sparse Layers are Critical to Scaling Looped Language Models
- When
- Thu 10 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 5
- Authors
- Ryan Lee, Jacob Biloki, Edward J Hu, Jonathan May
- Organisations
- University of Southern California, Apple, Mila, Université de Montréal
- QRS classification
- Attention and transformers, Language models