NVIDIA Isaac GR00T N1.5 - A Foundation Model for Generalist Robots.

Skyfall-GS: Synthesizing Immersive 3D Urban Scenes from Satellite Imagery

A modular and open-ended toolkit for WebGPU, with advanced type inference and the ability to write shaders in TypeScript

React Native Godot - Embed Godot Engine in React Native apps

Nano vLLM

[arXiv 2025] Generative View Stitching

https://shop.tetheria.ai/

Native Multimodal Models are World Learners

Python port of part of the TypeAgent repo

Official implementation of NeurIPS 2025 paper "SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent"

LPIPS metric. pip install lpips

MiMo-Audio: Audio Language Models are Few-Shot Learners

Official Implementations for Paper - HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives

A Modular Framework for 3D Generation and Beyond [WIP]

Character Animation Diffusion with Any Topology

Import a 3D Model and automatically assign and export animations

Official repository for BrickGPT, the first approach for generating physically stable toy brick models from text prompts.

FlowR: Flowing from Sparse to Dense 3D Reconstructions (ICCV'25 Highlight)

code release for HouseCrafter (ICCV 2025 Highlight)

Fast and Universal 3D reconstruction model for versatile tasks

BuildArena, where LLM agents design, build, and test rockets, cars, and bridges in a physics simulator given a goal-directed sentence.

Suite of motion imitation methods for training motion controllers.

Turn your software into a business.

✨ WithAnyone is capable of generating high-quality, controllable, and ID consistent images

Code for "FlashWorld: High-quality 3D Scene Generation within Seconds"

React components for visualizing traces from AI agents

[CVPR 2025] HumanMM: Global Human Motion Recovery from Multi-shot Videos

An unified model for 4D human-scene reconstruction