• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI

    Vikash Kumar on Manipulation Needs Embodied Action

    Vikash Kumar replies to Scobleizer on navigation versus manipulation in robotics.

    AK
    EX
    DA
    4 Sources, 27d ago, first seen 27d ago

    TLDR

    Vikash Kumar, a robotics researcher and CEO of MyoLab.ai, replied to Scobleizer in an AI discussion. He stated that navigation is definite yet the frontier in manipulation requires embodied action. Semantic LRFW labels remain easy to acquire during navigation but prove quite non trivial otherwise. The comment identifies manipulation as the harder domain for acquiring those labels compared with navigation tasks.

    Combined views

    5.9K

    4 Sources, first seen 27d ago

    Combined views

    5.9K

    4 Sources, first seen 27d ago

    27 likes
    27 likes
    3 comments
    14 saves
    22 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    3 comments
    14 saves
    22 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    4 Sources

    @HuggingPapersSolarWM: Open Data & Scalable Training for Long-Horizon Video World Models A fully open framework for interactive video world models, unifying 1.43M clips across 14 datasets and 4 backbones, enabling real-time rollouts for minutes to hours after training on just 5-second clips.
    @ericxingThe #1 model outside US and China, but 360-open. Meaningful AI progress depends on the ability to examine, build upon, and improve the technology, not simply access it through an API or weights.
    @Vikashplus@Scobleizer Def for navigation. The robotics frontier in manipulation needs embodied action. Semantic LRFW labels, easy to acquire in navigation, are quite non trivial otherwise
    @_akhaliqRT @HuggingPapers: SolarWM: Open Data & Scalable Training for Long-Horizon Video World Models A fully open framework for interactive video…

    4 Sources

    @HuggingPapersSolarWM: Open Data & Scalable Training for Long-Horizon Video World Models A fully open framework for interactive video world models, unifying 1.43M clips across 14 datasets and 4 backbones, enabling real-time rollouts for minutes to hours after training on just 5-second clips.
    @ericxingThe #1 model outside US and China, but 360-open. Meaningful AI progress depends on the ability to examine, build upon, and improve the technology, not simply access it through an API or weights.
    @Vikashplus@Scobleizer Def for navigation. The robotics frontier in manipulation needs embodied action. Semantic LRFW labels, easy to acquire in navigation, are quite non trivial otherwise
    @_akhaliqRT @HuggingPapers: SolarWM: Open Data & Scalable Training for Long-Horizon Video World Models A fully open framework for interactive video…