DM05-libero

DM05-libero is the LIBERO fine-tuned checkpoint of DM0.5, Dexmal's open-world Vision-Language-Action foundation model for embodied intelligence. DM0.5 uses a Gemma3 4B vision-language backbone with a 680M Action Expert to generate continuous robot actions, and is designed for natural-language manipulation, zero-shot generalization, efficient downstream fine-tuning, long-horizon historical context, robust policy behavior, and transfer across robot embodiments.

LIBERO Results

Method	Spatial	Object	Goal	Long	Average
DM0.5	99.0	99.8	99.6	97.4	99.0

How to Use

This model is intended to be used with the OpenDM LIBERO workflow. See the OpenDM README and LIBERO guide for installation, checkpoint download, inference service startup, and benchmark evaluation commands.

Citation

@misc{dm05,
    title  = {{DM0.5}: An Open-World Foundation Model for General-Purpose Embodied Intelligence},
    author = {{Dexmal Team}},
    month  = {July},
    year   = {2026},
    url    = {https://www.dexmal.com/blog/dm0.5/index_en.html}
}