RoboInter-VLM

Papers using or citing this model 1

• RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulation 26 citations · 2026 · arXiv.org · arXiv

  Advances in large vision-language models (VLMs) have stimulated growing interest in vision-language-action (VLA) systems for robot manipulation. However, existing manipulation datasets remain costly to curate, highly...