Skip to content
NeurIPS 2026 planner

Poster · Sydney

KV Cache Compression via Attention Output Distortion Minimization

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
Yi Wang, Yixuan Cao, Qiang Ding, Zelin Gao, Ping Luo
Organisations
Chinese Academy of Sciences
QRS classification
Attention and transformers, Efficient and distributed ML systems

Open in scheduleOfficial page