Awesome Robotics Manipulation · full_paper

OxyGen: Unified KV Cache Management for Vision-Language-Action Models under Multi-Task Parallelism

arXiv · 2026-03-15 · Low-Level Learning-Based Action Modelling / Input Modelling / 2D Vision Language Action Models with Efficiency / KV/Token Cache

VLA机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
OxyGen: Unified KV Cache Management for Vision-Language-Action Models under Multi-Task Parallelism figure
AlphaXiv 中文论文页面（可滚动查看）