Starred repositories
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
Official Implementation of the Paper: Lifting Motion to the 3D World via 2D Diffusion (CVPR 2025 Highlight)
Official implementation of paper: "RichControl: Structure- and Appearance-Rich Training-Free Spatial Control for Text-to-Image Generation"
[arXiv] PyTorch implementation of “Generalizable Neural Electromagnetic Inverse Scattering”
A Modular Toolkit for Robot Kinematic Optimization
[arXiv] PyTorch implementation of "The Less You Depend, The More You Learn: Synthesizing Novel Views from Sparse, Unposed Images without Any 3D Knowledge".
PyTorch code and models for VJEPA2 self-supervised learning from video.
official repo for AGNOSTOS, a cross-task manipulation benchmark, and X-ICM method, a cross-task in-context manipulation (VLA) method
Official PyTorch implementation for ICML 2025 paper: UP-VLA.
XLeRobot: Practical Dual-Arm Mobile Home Robot for $660
Imitation learning benchmark focusing on complex locomotion tasks using MuJoCo.
[CVPR 2025 Highlight] Real-time dense scene reconstruction with SLAM3R
RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning
[CVPR25 Oral (Top 3.3%)] Official code for paper "Reconstructing Humans with a Biomechanically Accurate Skeleton".
[CVPR 2025 Highlight] InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions
[3DV 2025 Best Paper] We present Object Images (Omages): An homage to the classic Geometry Images.
[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling
NVIDIA Isaac GR00T N1.6 - A Foundation Model for Generalist Robots.
Tactile Sensing • Simulation • Representation • Manipulation • RL/IL/VLA • Open Source
AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling
HumEnv is an SMPL humanoid environment enabling systematic model comparison and reproducibility