pith. sign in

Efficient Inference of Vision Instruction-Following Models with Elastic Cache , booktitle =

Liu, Zuyan, Liu, Benlin, Wang, Jiahui, Dong, Yuhao, Chen, Guangyi, Rao, Yongming · DOI 10.1007/978-3-031-72643-9_4

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
open at publisher browse 1 citing papers

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Make Your LVLM KV Cache More Lightweight

cs.CV · 2026-05-01 · unverdicted · novelty 5.0

LightKV compresses vision-token KV cache in LVLMs to 55% size via prompt-guided cross-modality aggregation, halving cache memory, cutting compute 40%, and maintaining performance on benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Make Your LVLM KV Cache More Lightweight cs.CV · 2026-05-01 · unverdicted · none · ref 61

    LightKV compresses vision-token KV cache in LVLMs to 55% size via prompt-guided cross-modality aggregation, halving cache memory, cutting compute 40%, and maintaining performance on benchmarks.