An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

AHN: Artificial Hippocampus Networks for Efficient Long-Context Modeling

HunyuanVideo: A Systematic Framework For Large Video Generation Model

HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation

Automatic Video Generation from Scientific Papers

[IROS 2025 Award Finalist] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems

Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets

A Gym for Agentic LLMs

[EMNLP-2025] R1-Zero on ANY TASK

Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environment…

A RL env with procedurally generated symbolic reasoning data

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

A tiny little JSON parsing library

Simulation of spiking neural networks (SNNs) using PyTorch.

Brian is a free, open source simulator for spiking neural networks.

SpikingJelly is an open-source deep learning framework for Spiking Neural Network (SNN) based on PyTorch.

Brain-inspired Cognitive Intelligence Engine (BrainCog) is a brain-inspired spiking neural network based platform for Brain-inspired Artificial Intelligence and simulating brains at multiple scales…

🔥🔥🔥A collection of some awesome public SNN(Spiking Neural Network) projects.

Spiking neural network inference engine for 7-Series FPGAs

🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

The official UniVerse-1 code.

Open-source unified multimodal model

Ming - facilitating advanced multimodal understanding and generation capabilities built upon the Ling LLM.

TradingAgents: Multi-Agents LLM Financial Trading Framework

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning

GTP engine and self-play learning in Go