具身智能DREAM2FLOW
Our recent work using object-centered spatial information for better generalization 🦾
Stanford 研究 Dream2Flow 提出用 3D object flow 连接视频生成与机器人控制，以提升开放世界机器人操作的泛化能力
Fei-Fei Li @drfeifei19 分钟阅读英文
阅读原文
TL;DR: Stanford 研究 Dream2Flow 提出用 3D object flow 连接视频生成与机器人控制，以提升开放世界机器人操作的泛化能力
以下为 Fei-Fei Li @drfeifei 原文（英文）
Our recent work using object-centered spatial information for better generalization 🦾
Wenlong Huang@wenlong_huang
What representation enables open-world robot manipulation from generated videos?
Introducing Dream2Flow, our recent work that bridges video generation and robot control with 3D object flow.
dream2flow.github.io@Stanford#ICRA2026
1/N Your browser does not support the video tag.🔗 View on Twitter
🔗 View Quoted Tweet
💬10🔄57❤️348👀52313📊57 ⚡ Powered by xgo.ing