This repository provides a serving engine for OpenVLA and other Prismatic-VLM models. Our optimized implementation based on SGLang substantially outperforms the vanilla OpenVLA inference pipeline, ...
This repo provides a simplest version instruction to finetune OpenVLA-OFT on BEHAVIOR-1K Challenge dataset. You can also start with the original openvla-oft repo. This finetuning instruction is ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback