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

    Cosmos is building world foundation models for physical AI

    A Cosmos team member says the approach draws on data used to train world models for different tasks.

    ML
    1 Source, 8h ago, first seen 8h ago

    TLDR

    A Cosmos team member describes a world foundation model as one that learns shared knowledge of the physical world from data used for specialized world models, then adapts to different tasks and environments. They say Cosmos aims to help robots and other autonomous systems anticipate the consequences of actions and evaluate possible futures.

    Combined views

    12.7K

    1 Source, first seen 8h ago

    Combined views

    12.7K

    1 Source, first seen 8h ago

    96 likes
    96 likes
    13 comments
    11 saves
    14 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Featured Source
    13 comments
    11 saves
    14 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

    1 Source

    @liu_mingyuIn Cosmos, we build world foundation models for physical AI. The term “world foundation model,” coined by @JensenHuang, brings together two ideas: world models and foundation models. We build models to solve tasks. Because we live in the physical world, many tasks require knowledge of the world—its objects, environments, and physical behavior. Here, we use “world model” in a broad sense to describe a model that captures the knowledge of the world needed to solve a task, rather than adopting a specific definition from the robotics literature. Different tasks require different kinds of knowledge, so we build different world models, each using data suited to its purpose. Different tasks call for different world models, but those models all describe aspects of the same physical world. This shared basis makes it possible to bring together the diverse data used to train specialized world models and build a single model that learns across them. A world foundation model is, in this sense, a foundation model of world models: it learns shared knowledge of the physical world that can be adapted to many tasks and environments. This matters because we are entering the era of physical AI, where robots and other autonomous systems will perform useful tasks for us in the real world. These systems must operate in complex, varied, and constantly changing environments. World foundation models can help them anticipate the consequences of actions, evaluate possible futures, and make better decisions. That is the goal behind our work in Cosmos.