AI Research 技术调研

标签: co-training

此标签下有4条笔记。

  • 2026年7月16日

    DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset

    • robot-manipulation
    • teleoperation-dataset
    • franka-panda
    • in-the-wild
    • diffusion-policy
    • co-training
    • cross-lab
    • rlds
    • generalization
  • 2026年7月16日

    Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation

    • mobile-manipulation
    • bimanual
    • whole-body-teleoperation
    • imitation-learning
    • co-training
    • aloha
    • act
    • low-cost-hardware
    • corl-2024
    • 成功
    • 尝试
  • 2026年7月16日

    Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better

    • vla
    • knowledge-insulation
    • stop-gradient
    • flow-matching
    • fast-tokenizer
    • co-training
    • paligemma
    • action-expert
    • catastrophic-forgetting
  • 2026年7月16日

    π0.5: a VLA Model with Open-World Generalization

    • vla
    • mobile-manipulation
    • co-training
    • cross-embodiment
    • flow-matching
    • fast-tokenizer
    • hierarchical-policy
    • open-world-generalization
    • paligemma

  • GitHub