AI Research 技术调研

标签: video-pretraining

此标签下有4条笔记。

  • 2026年7月16日

    Any-point Trajectory Modeling for Policy Learning

    • any-point-tracking
    • trajectory-model
    • video-pretraining
    • track-guided-policy
    • libero
    • cross-embodiment
    • imitation-learning
    • subgoal-representation
    • cotracker
  • 2026年7月16日

    Latent Action Pretraining from Videos (LAPA)

    • vla
    • latent-action
    • vq-vae
    • video-pretraining
    • unsupervised
    • cross-embodiment
    • openvla
    • iclr-2025
  • 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
  • 2026年7月16日

    Magma: A Foundation Model for Multimodal AI Agents

    • vla
    • foundation-model
    • ui-navigation
    • robot-manipulation
    • set-of-mark
    • trace-of-mark
    • cross-embodiment
    • video-pretraining
    • cvpr2025

  • GitHub