[SIGGRAPH Asia 2025 (ACM TOG)] AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views

[ICLR 2025 Spotlight] MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility

Ray tracing and hybrid rasterization of Gaussian particles

Calculate signed distance fields for arbitrary meshes

A lightweight suite of motion imitation methods for training controllers.

RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning

VLA-RFT: Vision-Language-Action Models with Reinforcement Fine-Tuning

Dexbotic: Open-Source Vision-Language-Action Toolbox

Official code of RDT 2

A general-purpose machine learning architecture designed for robot training

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

dng / dcp camera profiles and LUTs to match film simulation profiles for fujifilm x-series cameras

Open-Source To Self-Driving.

A ROS/ROS2 Multi-robot Simulator for Autonomous Vehicles

This is the code repository for the AI project template. The idea of this template is to have a code framework prepared for any AI/ML/MLOps/LLMOps project

The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…

SAM 3D Objects

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy

OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.

[CoRL 2025] Neural Robot Dynamics

Software stack for loco-manipulation experiments across multiple humanoid platforms, with primary support for the Unitree G1. This repository provides whole-body control policies, a teleoperation s…

[NeurIPS 2025] Official implementation for "Flow Matching-Based Autonomous Driving Planning with Advanced Interactive Behavior Modeling"

🎁 A collection of utilities for LeRobot.

[NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation

MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone