WindowKV: Task-adaptive group-wise KV cache window selection for efficient LLM inference
- 4 September 2026
- journal article
- Published by Elsevier in Expert Systems with Applications
- Vol. 333
Abstract
No abstract availableAll Related Versions
Funding Information
- National Natural Science Foundation of China (62376027)
This publication has 4 references indexed in Scilit:
- A collaborative reasoning framework for large language models in long-context Q&AExpert Systems with Applications, 2025
- Task-driven attention attack: An enhanced adversarial framework for long textExpert Systems with Applications, 2025
- ♫ MuSiQue: Multihop Questions via Single-hop Question CompositionTransactions of the Association for Computational Linguistics, 2022
- Eye movements in reading and information processing: 20 years of research.Psychological Bulletin, 1998