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

    Mariia Drozdova Describes Anytime Iterative Solver

    PhD student at University of Geneva posts results from modified denoising model.

    MD
    1 Source, 27d ago, first seen 27d ago

    TLDR

    Mariia Drozdova posted a thread describing changes to a denoising model. She added a persistent memory state and removed timestep conditioning. The post states this produces an anytime iterative solver. Drozdova reported the model has under 250k parameters and reaches 99.9 percent accuracy on Sudoku-Extreme plus 98.3 percent on Maze-Unique. The tweet links to an arXiv paper and includes a side-by-side video animation of the two tasks.

    Combined views

    37.1K

    1 Source, first seen 27d ago

    Combined views

    37.1K

    1 Source, first seen 27d ago

    522 likes
    522 likes
    10 comments
    467 saves
    60 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    10 comments
    467 saves
    60 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

    @MariiaD_ML1/7) What happens when we add a persistent memory state and remove timestep conditioning from a denoising model? We obtain an anytime iterative solver! With less than 250k-params, we obtain a 99.9% accuracy on Sudoku-Extreme and 98.3% on Maze-Unique. https://arxiv.org/abs/2609.01449

    1 Source

    @MariiaD_ML1/7) What happens when we add a persistent memory state and remove timestep conditioning from a denoising model? We obtain an anytime iterative solver! With less than 250k-params, we obtain a 99.9% accuracy on Sudoku-Extreme and 98.3% on Maze-Unique. https://arxiv.org/abs/2609.01449