SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics Paper โข 2506.01844 โข Published Jun 2 โข 147
view article Article SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data +7 Jun 3 โข 299
MolmoAct Collection All models for the MolmoAct (Multimodal Open Language Model for Action) release. โข 10 items โข Updated 4 days ago โข 32
SmolDocling datasets Collection Datasets used to train SmolDocling โข 6 items โข Updated Jul 31 โข 31