VLANeurIPS 20252025

ActionVLA: Action-Centric Vision-Language-Action Pre-training

Karl Pertsch, Moo Jin Kim, Chelsea Finn, Sergey LevineStanford University, UC Berkeley

摘要

We present ActionVLA, an action-centric pre-training approach for vision-language-action models. ActionVLA pre-trains on large-scale action-annotated video data, learning action representations that transfer effectively to diverse robot manipulation tasks with minimal fine-tuning data.

action-centricVLA pre-trainingaction representationvideo dataminimal fine-tuning

技术细节

仿真平台
测试机器人
FR3WidowX-250Kuka iiwa 7
模型骨架

Action Tokenizer + VLM Backbone

编码器

ViT-L/14 + Action Encoder

解码器

Action-Centric Transformer Decoder (8 layers)

相关公司(1)

京ICP备2026064258号-1