most citedKV-Efficient VLA: A Method to Speed up Vision Language Models with RNN-Gated Chunked KV Cache

1 citations · 1 across the 1 of their papers we have counts for

collaborators

1 paper

cs.CV2025★ 1 cited

KV-Efficient VLA: A Method to Speed up Vision Language Models with RNN-Gated Chunked KV Cache

Wanshun Xu, Long Zhuang, Lianlei Shan

Vision-Language-Action (VLA) models offer a unified framework for robotic perception and control, but their ability to scale to real-world, long-horizon tasks is limited by the hig…