Poster · Sydney
Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
- 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
- Yanke Zhou, Yiduo Li, Hanlin Tang, Maohua Li, Kan Liu, Tao Lan, Lin Qu, Yuan Yao, Xiaoxing Ma
- Organisations
- Nanjing University, Meituan, University of Rochester, Alibaba
- QRS classification
- Attention and transformers, Language models