Poster · Sydney
LAPrune: Logits-Aligned Scoring Proxy for KV Pruning via Vector Quantization
- When
- Wed 9 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 3
- Authors
- Mingyang Yu, Rong-Cheng Tu, Yifu Ding, Hanqing Zhao, Yongcheng Jing, Xiao Luo, Dacheng Tao
- Organisations
- City University of Hong Kong, Nanyang Technological University, Beihang University, Wuhan University, University of Wisconsin-Madison
- QRS classification
- Language models, Efficient and distributed ML systems