Poster · Sydney
Flux Attention: Context-Aware Hybrid Attention for Efficient LLMs Inference
- 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
- Quantong Qiu, Zhiyi Hong, Yi Yang, Haitian Wang, Kebin Liu, Qingqing Dang, Juntao Li, Min zhang
- Organisations
- Soochow University, Baidu, Harbin Institute of Technology
- QRS classification
- Attention and transformers, Language models, Efficient and distributed ML systems