SuperMap is a living spatial memory for embodied AI — it perceives the world, remembers its evolution, and supports reasoning and action.

A highly robust and accurate LiDAR-only, LiDAR-inertial odometry

Imitation learning algorithms with Co-training for Mobile ALOHA: ACT, Diffusion Policy, VINN

Implementation for Model Predictive Adversarial Imitation Learning 2 (MPAIL2)

Sim-to-real and CDM inference code for ManipAsInSim project.

JoyAI-VL-Interaction: An Open Real-time Video-Language Interaction System

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

Official code for "μ0: A Scalable 3D Interaction-Trace World Model"

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

ROS2 TensorRT Hardware-Accelerated Stereo Depth Estimation with FastFoundationStereo

A PyTorch Implementation of CA-SUM from "Summarizing Videos using Concentrated Attention and Considering the Uniqueness and Diversity of the Video Frames", Proc. ACM ICMR 2022

gap — graph as policy: compile language instructions into typed, verified robot skill graphs and execute them on simulators or real robots

Official PyTorch Implementation of Paper "The Surprising Effectiveness of Video Diffusion Models for Hand Motion Reconstruction"

Lock/unlock your Mac with your iPhone, Apple Watch, or any other Bluetooth LE devices

[RSS 2026] FreeOcc: Training-Free Embodied Open-Vocabulary Occupancy Prediction

Official repository for "VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training"

Code for paper titled, "Learning to Predict Task Progress by Self-Supervised Video Alignment" by Gerard Donahue and Ehsan Elhamifar, published at CVPR 2024.

Google Research

A Codex skill for choosing reproducible research baselines.

[ECCV 2026] WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion

Create stunning demos for free. Open-source, no subscriptions, no watermarks, and free for commercial use. An alternative to Screen Studio.

X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining

Maximum Entropy and Maximum Causal Entropy Inverse Reinforcement Learning Implementation in Python

iPhUMI is a handheld data collection interface for training visuomotor robot manipulation policies and a hardware interface for behavior prompting.

Official Repo for Qwen-RobotNav

[RSS 2026] Ordered Action Tokenization