The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"
关键参数与规格
关键参数与规格
参数
值
语言
Python
类别
Models
子类别
Vision models
星标数
2,216
分叉数
244
贡献者
2
创建日期
2025-12-17
更新日期
2026-10-15
1 天星标数
1
7 天星标数
10
排名
5,134
上次排名
3,848
排名变化
-1,286
7 天星标排名
3,982
上次 7 天星标排名
3,628
7 天星标排名变化
-354
总星标排名
5,845
上次总星标排名
5,841
总星标排名变化
-4
国家
USA
README 摘录
NitroGen NitroGen is an open foundation model for generalist gaming agents. This multi-game model takes pixel input and predicts gamepad actions. It is trained through behavior cloning on the largest video-action gameplay dataset, assembled exclusively from internet videos. It can be adapted via post-training to unseen games. IMPORTANT] NitroGen is a research project to enable training generalist agent from internet data, please refer to the paper for full details. The current model is a 500M parameter DiT
that can only see the last frame. Therefore it has no ability yet to plan over long horizons, play games end-to-end, self improve over time, or play completely unseen game. It is a fast-reacting system-1 sensory model Installation Prerequisites We **do not distribute game environments**, you must use your own copies of the games. This repository only supports running the agent on **Windows games**. You can serve the model from a Linux machine for inference, but
the game ultimately has to run on Windows. We have tested on Windows 11 with Python ≥ 3. Setup Install this repo: Download NitroGen checkpoint from HuggingFace: Getting Started First, start an inference server for the model: Then, run the agent on the game of your choice: The parameter must be the exact executable name of the game you want to play. You can find it by right-clicking on the game process in Windows Task Manager (Ctrl+Shift+Esc), and
selecting . The process name should be in the tab and end with . Paper and Citation If you find our work useful, please consider citing us! **Disclaimer**: This project is strictly for research purposes and is not an official NVIDIA product.
NitroGen is an open foundation model for generalist gaming agents. This multi-game model takes pixel input and predicts gamepad actions. It is trained through behavior cloning on the largest video-action gameplay dataset, assembled exclusively from internet videos. It can be adapted via post-training to unseen games.
[!IMPORTANT]
NitroGen is a research project to enable training generalist agent from internet data, please refer to the paper for full details. The current model is a 500M parameter DiT that can only see the last frame. Therefore it has no ability yet to plan over long horizons, play games end-to-end, self improve over time, or play completely unseen game. It is a fast-reacting system-1 sensory model
Installation
Prerequisites
We do not distribute game environments, you must use your own copies of the games. This repository only supports running the agent on Windows games. You can serve the model from a Linux machine for inference, but the game ultimately has to run on Windows. We have tested on Windows 11 with Python ≥ 3.12.
Setup
Install this repo:
git clone https://github.com/MineDojo/NitroGen.git
cd NitroGen
pip install -e .
The --process parameter must be the exact executable name of the game you want to play. You can find it by right-clicking on the game process in Windows Task Manager (Ctrl+Shift+Esc), and selecting Properties. The process name should be in the General tab and end with .exe.
Paper and Citation
If you find our work useful, please consider citing us!
@misc{magne2026nitrogen,
title={NitroGen: An Open Foundation Model for Generalist Gaming Agents},
author={Loïc Magne and Anas Awadalla and Guanzhi Wang and Yinzhen Xu and Joshua Belofsky and Fengyuan Hu and Joohwan Kim and Ludwig Schmidt and Georgia Gkioxari and Jan Kautz and Yisong Yue and Yejin Choi and Yuke Zhu and Linxi "Jim" Fan},
year={2026},
eprint={2601.02427},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2601.02427},
}
Disclaimer: This project is strictly for research purposes and is not an official NVIDIA product.
