MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference
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.
Authors
- Kunxi Li (ORCID: https://orcid.org/0009-0006-4433-2236)
- Zhonghua Jiang
- Chen Lv (ORCID: https://orcid.org/0000-0001-6897-4512)
- Fan Wu (ORCID: https://orcid.org/0000-0003-2836-700X)
- Zelin Shen (ORCID: https://orcid.org/0009-0003-9623-7546)
- Fei Wu (ORCID: https://orcid.org/0009-0009-6632-4490)
- Shengyu Zhang (ORCID: https://orcid.org/0000-0001-7480-398X)
- ZhaodeWang ZhaodeWang
Publication Details
- Published
- 2025-01-01
- DOI
- https://doi.org/10.18653/v1/2025.acl-long.652
- Primary Topic
- Speech Recognition and Synthesis
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China