Stars
The Ralph Wiggum Technique—the AI development methodology that reduces software costs to less than a fast food worker's wage.
Running a big model on a small laptop
A generalized inverse kinematics solver that supports closed chains for parallel kinematics systems, dynamic reconfiguration, and arbitrary joint configuration based on damped least squares error m…
LeIsaac provides teleoperation functionality in IsaacLab using the SO101Leader (LeRobot), including data collection, data conversion, and subsequent policy training.
Open-Source Dual-Arm Mobile Robot with Motorized Lift
VR-based Teleoperation for Dexterous Manipulation - Control xArm + Inspire Hands with Vive Trackers and Quest Hand Tracking
Realtime & high-frequency control interfaces for various robot arms including bi-manual I2RT YAM, Franka Panda, with manual tele-operation control or autonomous policy control
An open-source, full-stack robotic neck for active perception
A fork of Supermodel, a Sega Model 3 emulator, with a focus on netplay features, replay, and training options for competitive play.
Unofficial implementation of "TableNet: Deep Learning model for end-to-end Table detection and Tabular data extraction from Scanned Document Images"
[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer
ICRA2025: OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding
Examples and guides for using the VLM Run API
[ICRA 2025] PyTorch Code for Local Policies Enable Zero-shot Long-Horizon Manipulation
[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors
RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
Combining ViT and GPT-2 for image captioning. Trained on MS-COCO. The model was implemented mostly from scratch.
Robot kinematics implemented in pytorch
Minimal, clean, single-file implementations of common robotics controllers in MuJoCo.