Work

MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference

Year: 2025

Type: conference-paper

Abstract: Kunxi Li, Zhonghua Jiang, Zhouzhou Shen, ZhaodeWang ZhaodeWang, Chengfei Lv, Shengyu Zhang, Fan Wu, Fei Wu. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Source: Annual Meeting of the Association for Computational Linguistics (ACL)

DOI: 10.18653/v1/2025.acl-long.652

Authors: Kunxi Li, Zhonghua Jiang, Zhouzhou Shen, ZhaodeWang ZhaodeWang, Chengfei Lv, Shengyu Zhang, Fan Wu, Fei Wu

Institutions: Zhejiang University, Southeast University, Southeast University, Shanghai Jiao Tong University

Language: English

Topic: Multimodal Machine Learning Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funders: National Natural Science Foundation of China, Key Research and Development Program of Zhejiang Province

Award: G1101031052

OpenAlex ID: W4412945256

FWCI: 1.592

Cites:

Cited by: 2

Related to: 10