Stars
Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
Wan: Open and Advanced Large-Scale Video Generative Models
Sparse Video Generation Model for Embodied Navigation conditioned on loose language guidance, 100% real world verification
[CVPR 25] Vid2Sim: Realistic and Interactive Simulation from Video for Urban Navigation
[RSS'25] This repository is the implementation of "NaVILA: Legged Robot Vision-Language-Action Model for Navigation"
Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI
Complete Claude Code configuration collection - agents, skills, hooks, commands, rules, MCPs. Battle-tested configs from an Anthropic hackathon winner.
Training VLM agents with multi-turn reinforcement learning
[CVPR2025] CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos
Thinking in 360°: Humanoid Visual Search in the Wild
Learning Dexterous Manipulation Skills from Imperfect Simulations
[NeurIPS'25] Generalizable Reasoning through Compositional Energy Minimization
This repository contains the implementation of all methods evaluated in the paper "Learning a Thousand Tasks in a Day". We provide model architectures, training scripts, and deployment examples.
Curate, Annotate, and Manage Your Data in LightlyStudio.
A toolbox for target-less LiDAR-camera calibration [ROS1/ROS2]
Easy to use and hardware independent Python hand-eye calibration library.
Differentiable Iso-Surface Extraction Package (DISO)
A novel 4D reconstruction method that directly generates high-quality, animation-ready 4D mesh asset (.GLB file) from a single monocular video.
[ICCV 2025] Official code for AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation
[CVPR 2025 Highlight] Official implementation of "Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characters"
A collection of paper/projects that trains flow matching model/policies via RL.
A Modular Toolkit for Robot Kinematic Optimization
[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL
[NeurIPS 2025, Spotlight] Rectified Point Flow: Generic Point Cloud Pose Estimation