Modelpublic

gen-robot/openvla-7b-rlvla-warmup

sourceHugging Facemitupdated 1y agoView on Hugging Face

1likes1.3kdownloads

Model Card

VLA-RL-Study: What Can RL Bring to VLA Generalization? An Empirical Study

![arXiv](http://arxiv.org/abs/2505.19789) ![Website](https://rlvla.github.io)

This is the warm-upped model, fine-tuned from official openvla/openvla-7b. The warm-up dataset consists of 140 trajectories collected by octo-small and the motion planner. For more details, please refer to the codebase and the paper.