Image-to-Text
Transformers
Safetensors
openvla
custom_code
ReVLA-Fractal / README.md
Sombit's picture
Update README.md
a0a884d verified
metadata
library_name: transformers
license: mit
datasets:
  - lerobot-raw/fractal20220817_data_raw
base_model:
  - openvla/openvla-7b

This is the ReVLA model, finetuned on the Fractal Dataset

ReVLA: Reverting Visual Domain Limitation of Robotic Foundation Models, accepted at ICRA 2025

Arxiv

Acknowledgements: INSAIT, Sofia University “St. Kliment Ohridski”. Partially funded by the Ministry of Education and Science of Bulgaria’s support for INSAIT as part of the Bulgarian National Roadmap for Research Infrastructure. This project was further supported with computational resources provided by Google Cloud Platform (GCP)