A MuJoCo to OpenUSD Data Converter

[NeurIPS 2025 Spotlight] MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning

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

[NeurIPS 2025] InternScenes: A Large-scale Interactive Indoor Scene Dataset with Realistic Layouts.

Official Implementation of the paper "HSM: Hierarchical Scene Motifs for Multi-Scale Indoor Scene Generation"

Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors

LL3M writes Python code that generates 3D assets in Blender.

Official code for "LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models" (CVPR 2025)

[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.

PhysX: Physical-Grounded 3D Asset Generation (NeurIPS 2025, Spotlight)

Code for "Diffusion Model Alignment Using Direct Preference Optimization"

3D Object Reconstruction project is a workflow that takes a set of stereo images and camera info and outputs a textured mesh (i.e., .OBJ file). The purpose is to translate physical items into the d…

Official repo for GraspGen: A Diffusion-based Framework for 6-DOF Grasping

🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!

Command line tools to convert SDFormat to USD and viceversa

Infinite Photorealistic Worlds using Procedural Generation

Speed up model training by fixing data loading.

A lightweight, powerful framework for multi-agent workflows

[arXiv 2023] Set-of-Mark Prompting for GPT-4V and LMMs

A library of long-horizon Task-and-Motion-Planning (TAMP) problems in kitchen and household scenes, as well as planners to solve them

CVPR 2024: Language Guided Generation of 3D Embodied AI Environments.

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

A procedural Blender pipeline for photorealistic training image generation

A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

Kickstart your MLOps initiative with a flexible, robust, and productive Python package.

SynCity: Training-Free Generation of 3D Worlds