构建物理AI的数字孪生平台，支持自定义世界模型训练
Cosmos World Foundation Model Platform for Physical AI
- 提出通用世界基础模型，可微调为特定物理AI的数字孪生
- 提供视频数据流水线、预训练模型和视频分词器工具链
- 开源模型权重与代码，助力科研与产业落地
物理AI需先在数字环境中训练。这需要一个政策模型的数字孪生和一个世界模型的数字孪生。本文提出Cosmos世界基础模型平台，帮助开发者为其物理AI系统构建定制化世界模型。我们将世界基础模型定位为可微调为下游应用定制世界模型的通用型世界模型。平台涵盖视频采集处理流程、预训练世界基础模型、预训练模型的后训练示例以及视频分词器。为助力解决社会关键问题，我们开源了Cosmos项目，所有模型以宽松许可协议开放，可通过https://github.com/nvidia-cosmos/cosmos-predict1获取。
原文摘要 · Abstract (English)
Physical AI needs to be trained digitally first. It needs a digital twin of itself, the policy model, and a digital twin of the world, the world model. In this paper, we present the Cosmos World Foundation Model Platform to help developers build customized world models for their Physical AI setups. We position a world foundation model as a general-purpose world model that can be fine-tuned into customized world models for downstream applications. Our platform covers a video curation pipeline, pre-trained world foundation models, examples of post-training of pre-trained world foundation models, and video tokenizers. To help Physical AI builders solve the most critical problems of our society, we make Cosmos open-source and our models open-weight with permissive licenses available via https://github.com/nvidia-cosmos/cosmos-predict1.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。