Poster · Sydney
Punctuation-aware Hybrid Trainable Sparse Attention for Large Language Models
- 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
- Junxiang Qiu, Shuo Wang, Zhengsu Chen, Hengheng Zhang, Jinda Lu, Changcheng Li, Xinting Hu, Qi Tian
- Organisations
- University of Science and Technology of China, Huawei, Nanyang Technological University
- QRS classification
- Attention and transformers, Language models