Tensors and Dynamic neural networks in Python with strong GPU acceleration

Visual localization made easy with hloc

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

A feature-rich command-line audio/video downloader

A unified inference and post-training framework for accelerated video generation.

Train transformer language models with reinforcement learning.

Zotero is a free, easy-to-use tool to help you collect, organize, annotate, cite, and share your research sources.

SSSegmentation: An Open Source Supervised Semantic Segmentation Toolbox Based on PyTorch.

A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.

The open source mesh processing system

Presentation Slides for Developers

KDE Plasma Desktop container designed for Kubernetes, supporting OpenGL EGL and GLX, Vulkan, and Wine/Proton for NVIDIA GPUs through WebRTC and HTML5, providing an open-source remote cloud/HPC grap…

MulimgViewer is a multi-image viewer that can open multiple images in one interface, which is convenient for image comparison and image stitching.

TensorFlow Graphics: Differentiable Graphics Layers for TensorFlow

A generative world for general-purpose robotics & embodied AI learning.

The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra

Native Multimodal Models are World Learners

Powerful, mature open-source cross-platform game engine for Python and C++, developed by Disney and CMU

Manipulation and analysis of geometric objects

verl: Volcano Engine Reinforcement Learning for LLMs

A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.

slime is an LLM post-training framework for RL Scaling.

Deepfakes Software For All

A fast reverse proxy to help you expose a local server behind a NAT or firewall to the internet.

OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling

Mitsuba 3: A Retargetable Forward and Inverse Renderer

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

A paper list for spatial reasoning

A pure Unix shell script implementing ACME client protocol