OpenHLM/OpenHLM-ckpts

OpenHLM: An Empirical Recipe for Whole-Body Humanoid Loco-Manipulation

This repository contains checkpoints for OpenHLM, a whole-body native vision-language-action (VLA) model that maps language and camera pixels directly to all of the humanoid robot's degrees of freedom.

• Project Page: https://openhlm-project.github.io/
• Paper: OpenHLM: An Empirical Recipe for Whole-Body Humanoid Loco-Manipulation

Citation

@article{openhlm2026,
  title={OpenHLM: An Empirical Recipe for Whole-Body Humanoid Loco-Manipulation},
  author={Anonymous},
  journal={arXiv preprint arXiv:2606.22174},
  year={2026}
}