Model Card for InternVLA-M1

Description:

InternVLA-M1 is an open-source, end-to-end vision–language–action (VLA) framework for building and researching generalist robot policies. The checkpoints in this repository were pretrained on the system2 dataset.

• 🌐 Homepage: InternVLA-M1 Project Page
• 💻 Codebase: InternVLA-M1 GitHub Repo

Citation

@misc{internvla2024,
  title  = {InternVLA-M1: Latent Spatial Grounding for Instruction-Following Robotic Manipulation},
  author = {InternVLA-M1 Contributors},
  year   = {2025},
  booktitle={arXiv},
}