开源世界模型的提升
计算机视觉与模式识别
2026-01-29 v1
摘要
我们提出LingBot-World，一个源自视频生成的开源世界模拟器。作为一级世界模型，LingBot-World具备以下特性。（1）在广泛环境中保持高保真度和稳健动力学，包括真实感、科学语境、卡通风格等。（2）在保持时间上下文一致性的同时支持分钟级视野，这也称为“长期记忆”。（3）支持实时交互，在以每秒16帧的速度生成帧时延小于1秒。我们提供公开的代码和模型，以努力缩小开源与闭源技术之间的鸿沟。我们相信我们的发布将使社区能够在内容创作、游戏和机器人学习等领域获得实际应用。
引用
@article{arxiv.2601.20540,
title = {Advancing Open-source World Models},
author = {Robbyant Team and Zelin Gao and Qiuyu Wang and Yanhong Zeng and Jiapeng Zhu and Ka Leong Cheng and Yixuan Li and Hanlin Wang and Yinghao Xu and Shuailei Ma and Yihang Chen and Jie Liu and Yansong Cheng and Yao Yao and Jiayi Zhu and Yihao Meng and Kecheng Zheng and Qingyan Bai and Jingye Chen and Zehong Shen and Yue Yu and Xing Zhu and Yujun Shen and Hao Ouyang},
journal= {arXiv preprint arXiv:2601.20540},
year = {2026}
}
备注
Project page: https://technology.robbyant.com/lingbot-world; Code: https://github.com/robbyant/lingbot-world