Poster · Sydney
Token Filtering: Online Attention Pruning via KV Similarity for Efficient LLM Inference
- 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
- JUNGMIN LEE, Gwangeun Byeon, Yulhwa Kim, Seokin Hong
- Organisations
- Sungkyunkwan University
- QRS classification
- Attention and transformers, Language models, Efficient and distributed ML systems