Starred repositories
PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation
Sourccey Desktop and Kiosk application
Open Source Hardware Repository for the Sourccey Robot
Convert Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, and PDF to clean Markdown. Built in Rust, with Node.js and Python bindings.
MANO hand models in MJCF format for MuJoCo simulation.
A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.
[ECCV 2026] Group3D: MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection
Improving and Evaluating Hand-Object Interaction Detection
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
STL files and lerobot integration code for modified so101 arms
XLeRobot: Practical Dual-Arm Mobile Home Robot for $660
Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding (ECCV 2026)
A library of agent skills for CAD, CAE and CAM
Transform 3D modeling from complex menus to simple conversations. Create and modify CAD models using plain English descriptions.
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
A tutorial and a set of tools to compute depth-from-stereo with Project Aria Gen2 devices. This includes stereo image rectification as well as disparity estimation
[IEEE TPAMI 2026] Simulating the Real World: Survey & Resources, which contains our survey "Simulating the Real World: A Unified Survey of Multimodal Generative Models" (IEEE TPAMI, 2026) and Aweso…
Seamlessly extend any image in any direction with AI. Open-source web app powered by Gemini via OpenRouter, with Poisson-blended seams and best-of-3 variant picker.
Official implementation of "WorldKV: Efficient World Memory with World Retrieval and Compression"
Stemdeck is an modern stem extraction platform for musicians,producers and hobbyists, designed to isolate vocals, drums, bass, piano and guitar for practice, transcription, remixing, and creative a…
Simulation platform for general-purpose robotics & embodied AI learning.
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning