Skip to content
NeurIPS 2026 planner

Poster · Sydney

ADKV: A Low-Overhead Adaptive Delta Quantization for KV Cache in LLM Inference

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
Honghao Jia, Zhenxing Li, Jialiang Guo, Jiacheng Gan
Organisations
University of Science and Technology of China, Harbin Engineering University, Tianjin University
QRS classification
Language models, Efficient and distributed ML systems

Open in scheduleOfficial page