SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics Paper • 2506.01844 • Published 1 day ago • 51
SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics Paper • 2506.01844 • Published 1 day ago • 51
view article Article Tiny Agents in Python: a MCP-powered agent in ~70 lines of code By celinah and 3 others • 12 days ago • 117
view article Article The Transformers Library: standardizing model definitions By lysandre and 3 others • 20 days ago • 109
view article Article LeRobot Community Datasets: The “ImageNet” of Robotics — When and How? By danaaubakirova and 6 others • 24 days ago • 55
70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float Paper • 2504.11651 • Published Apr 15 • 28
70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float Paper • 2504.11651 • Published Apr 15 • 28 • 5