AI Research 技术调研

标签: human-video-pretraining

此标签下有1条笔记。

  • 2026年7月16日

    Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos

    • latent-action
    • video-pretraining
    • vq-vae
    • autoregressive-transformer
    • action-chunking
    • cross-embodiment
    • human-video-pretraining
    • calvin
    • simpler
    • co-fine-tuning

  • GitHub