Bridging the Gap: Enabling Soft Actor-Critic for High Performance Legged Locomotion

The official implementation of the DARPA SubT winning LiDAR mapping and odometry solution.

Ultra-Fusion: A Resilient Tightly-Coupled Multi-Sensor Fusion SLAM Framework under Sensor Degradation and Spatiotemporal Perturbation

[NeurIPS 2025] Sekai: A Video Dataset towards World Exploration

LiDAR SLAM = FAST-LIO + Scan Context

[RAL 2023] A globally consistent LiDAR map optimization module

Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots

[CVPR 2025] A unified framework for Scene Coordinate Regression-based visual localization

A MLLM-based agentic system converts a single room image into executable Blender code for 3D room reconstruction.

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

A lightweight, open-source OpenClaw version built into your Claude Code.

[ICCV 2023] OccNet: Scene as Occupancy

[ICCV 2025] ACE-G is an architecture and pre-training scheme to improve generalization for scene coordinate regression-based visual relocalization.

[CVPR2026 Oral, Award Candidate] Monocular Open Vocabulary Occupancy Prediction for Indoor Scenes

[ECCV 2024] ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 60-95% fewer tokens, same answers. Library, proxy, MCP server.

[CVPR 2023] DKM: Dense Kernelized Feature Matching for Geometry Estimation

[CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.

[CVPR 2026 Highlight] MV-RoMa: From Pairwise Matching into Multi-View Track Reconstruction

Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".

A tool to run docker containers with overlays and convenient options for things like GUIs etc.

Telekinesis Agentic Skill Library: build AI-powered Computer Vision, Robotics and Physical AI applications.

Mosaico - The data platform for Physical AI

GLUEMAP: Global Structure-from-Motion Meets Feedforward Reconstruction

Official repository for TerraSky3D dataset with co-registered aerial and ground scenes (CVPRW 2026).

Leveraging system development and robot deployment for aerial autonomous navigation.