Chinese contentReka 发布 Rho-1:全模态推理模型,延迟从 13.8 秒降到 7.0 秒
DeepMind 前员工做的单一模型,画图改视频控制机械臂全包,延迟砍半,不用再等十来秒了。
DeepMind 前员工做的单一模型,画图改视频控制机械臂全包,延迟砍半,不用再等十来秒了。
RIDM eliminates the need for expensive low-level action labeling in video training data, significantly reducing the barrier to building more realistic AI systems. Developers and robotics researchers can now leverage this open-source model to create more capable AI agents that bridge the simulation-to-reality gap, with immediate access to the weights on Hugging Face.