英伟达扩展 Cosmos 世界模型平台，推出训练工具与数据工厂蓝图
英伟达扩展了 Cosmos 平台，新增训练工具、仿真检查点以及 Cosmos Data Factory 蓝图，面向构建物理 AI 世界模型的开发者。英伟达表示，Data Factory 现提供五套云原生蓝图，可通过 GitHub、Microsoft Azure、Nebius 和 CoreWeave 使用；新的 Cosmos 3 Nano 变体支持在多视角、多传感器仿真中重复测试策略。英伟达还称，更新后的 Cosmos 3 NIM 微服务在经验证的配置下推理速度最高提升至 2 倍，并自称 Cosmos 平台在六个开放模型排行榜上进入前五——该排名未在所提供的材料中获独立验证。
英伟达将 Cosmos 定位为覆盖数据整理、模型训练和 NIM 部署的开放模块化平台，并称保时捷（预计可减少多达 90% 的重复实车测试）和 ANYbotics 等客户已在使用其 Data Factory 蓝图。
To help developers rapidly build world models, which help physical AI systems understand and simulate the real world, NVIDIA has expanded the Cosmos platform with new training tools, simulation checkpoints and Cosmos Data Factory blueprints.
Ranking top five on six different open models leaderboards, the NVIDIA Cosmos platform gives world model builders the frontier open models — as well as data, training and optimization tools and recipes — to scale training data, adapt models, test behavior and optimize for performance before deployment.
Build Better Training Data
Building world models begins with multimodal, multisensory data.
NVIDIA Cosmos Data Factory brings together the tools and skills for labeling, curating, augmenting and evaluating data at scale for training physical AI. Cosmos Curator, a GPU-accelerated solution for curating video training datasets, has now added support for multimodal multisensory inputs and processing blocks.
#NVIDIA#Cosmos Data Factory#Cosmos 3#Cosmos 3 Nano#Cosmos Curator#NIM#Porsche#Volkswagen Group#ANYbotics#Ultralytics#Microsoft Azure#Roboflow