Highlights
- Pro
Stars
[CVPR 2025] Official implementation of "GenManip: LLM-driven Simulation for Generalizable Instruction-Following Manipulation"
The Isaac Sim Motion Generator provides a framework for motion generation using cuRobo, a CUDA-accelerated library. This tool allows users to perform forward kinematics, inverse kinematics, and mot…
Implementation for "Rectified Point Flow: Generic Point Cloud Pose Estimation"
Codebase for DexMachina: Functional Retargeting for Bimanual Dexterous Manipulation
MultiGripperGrasp Toolkit 2.0. Simulation Tools for the MultiGripperGrasp Dataset
This code corresponds to simulation environments used as part of the DexMimicGen project.
[CoRL 2024] Im2Flow2Act: Flow as the Cross-domain Manipulation Interface
This is a repository for GraspXL, which can generate objective-drive grasping motions for 500k+ objects with different dexterous hands.
Code for the paper "Planning with Diffusion for Flexible Behavior Synthesis"
A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.
Implementation for Describe Anything: Detailed Localized Image and Video Captioning
[CVPR 2025] 🎉 Official repository of "ManipTrans: Efficient Dexterous Bimanual Manipulation Transfer via Residual Learning"
GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data
Official Implementation for “CordViP: Correspondence-based Visuomotor Policy for Dexterous Manipulation in Real-World” (RSS 2025).
A comprehensive collection of process reward models.
[NeurIPS 2023] Jigsaw: Learning to Assemble Multiple Fractured Objects
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
Code for paper "PuzzleFusion++: Auto-agglomerative 3D Fracture Assembly by Denoise and Verify" [ICLR2025]
GARF: Learning Generalizable 3D Reassembly for Real-World Fractures
Official implementation of paper on Nature Machine Intelligence: "Preserving and Combining Knowledge in Robotic Lifelong Reinforcement Learning"
Official PyTorch implementation of One-Minute Video Generation with Test-Time Training
Official implementation of CVPR25 paper "Decompositional Neural Scene Reconstruction with Generative Diffusion Prior"
[CVPR 2025] UniK3D: Universal Camera Monocular 3D Estimation
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control
NVIDIA Isaac GR00T N1.5 is the world's first open foundation model for generalized humanoid robot reasoning and skills.