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

    EMPIRIC aims to fill gaps in physics simulators with code

    Its developers say EMPIRIC solved all 25 runs across five simulated domains, compared with 14 to 16 for coding-agent baselines.

    AW
    YL
    2 Sources, ,

    TLDR

    EMPIRIC’s developers describe an agent that extends a physics engine with code for mechanisms the engine cannot model. They say it solved all 25 runs across five simulated domains, while coding-agent baselines solved 14 to 16. On a real robot, they say it learned wind and domino masses from two gusts.

    Combined views

    9.1K

    2 Sources, first seen 8h ago

    Combined views

    9.1K

    2 Sources, first seen 8h ago

    90 likes
    8h ago
    first seen 8h ago
    90 likes
    3 comments
    75 saves
    21 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Featured Source
    3 comments
    75 saves
    21 reposts

    2 Sources

    @yichao_liangAgentic real-to-sim is getting increasingly good at rebuilding scenes in a physics simulator. But looking at a scene does not reveal how glue cures, how water heats, or how a fan's wind pushes things. And what if the simulator cannot model these mechanisms at all? We present EMPIRIC, an agent that learns a residual world model: a physics engine extended with code for the missing mechanisms. It solves all 25 runs across five simulated domains, where coding-agent baselines solve 14 to 16, and on a real robot it learns wind and domino masses from two gusts. https://basisresearch.github.io/empiric/ [1/9]8h
    @adrian_wellerRT @yichao_liang: Agentic real-to-sim is getting increasingly good at rebuilding scenes in a physics simulator. But looking at a scene does…7h

    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

    2 Sources

    @yichao_liangAgentic real-to-sim is getting increasingly good at rebuilding scenes in a physics simulator. But looking at a scene does not reveal how glue cures, how water heats, or how a fan's wind pushes things. And what if the simulator cannot model these mechanisms at all? We present EMPIRIC, an agent that learns a residual world model: a physics engine extended with code for the missing mechanisms. It solves all 25 runs across five simulated domains, where coding-agent baselines solve 14 to 16, and on a real robot it learns wind and domino masses from two gusts. https://basisresearch.github.io/empiric/ [1/9]8h
    @adrian_wellerRT @yichao_liang: Agentic real-to-sim is getting increasingly good at rebuilding scenes in a physics simulator. But looking at a scene does…7h