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

    EXAONE Tabular ranked first on TabArena for classification by Elo score, a user reports

    A user describes LG AI Research’s classification and regression models as having about 21 million parameters each. The released weights are limited to non-commercial research and education, the user says, while the inference code permits commercial use.

    PP
    1 Source, 19d ago, first seen 19d ago

    TLDR

    A September 11, 2026 post reports that LG AI Research’s EXAONE Tabular ranked first for classification and second for regression on TabArena by Elo score, and that its technical report was available. According to the user, the model handles missing values without requiring them to be filled in first and uses missingness information to represent features. It also uses built-in feature selection for tables that exceed its feature limit. The user notes that commercial use is permitted for the inference code, but the released weights are restricted to non-commercial research and education.

    Combined views

    1.2K

    1 Source, first seen 19d ago

    Combined views

    1.2K

    1 Source, first seen 19d ago

    15 likes
    15 likes
    2 comments
    18 saves
    6 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    2 comments
    18 saves
    6 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

    @pandeyparulIf you’re following the tabular foundation models(TFMs) space, it’s worth checking the TabArena leaderboard from time to time. One recent addition was EXAONE Tabular from LG AI Research which currently ranks first for classification and second for regression on Elo scores . Its technical report is out now and is worth a read. • It is a compact model. Both classification and regression models contain about 21 million parameters each. (For comparison, TabFM from Google Research has around 1.6B parameters) • Handles missing values directly, without requiring imputation, and uses missingness information when building feature representations. • Uses built-in feature selection for tables that exceed its feature limit. • It handles more classes than its native capacity through ECOC (Error Correcting Output Codes) • As for license, the released weights are limited to non-commercial research and education. The inference code permits commercial use though. https://github.com/LGAI-Research/EXAONE-Tabular/blob/main/EXAONE_Tabular_v1.0_Technical_Report.pdf

    1 Source

    @pandeyparulIf you’re following the tabular foundation models(TFMs) space, it’s worth checking the TabArena leaderboard from time to time. One recent addition was EXAONE Tabular from LG AI Research which currently ranks first for classification and second for regression on Elo scores . Its technical report is out now and is worth a read. • It is a compact model. Both classification and regression models contain about 21 million parameters each. (For comparison, TabFM from Google Research has around 1.6B parameters) • Handles missing values directly, without requiring imputation, and uses missingness information when building feature representations. • Uses built-in feature selection for tables that exceed its feature limit. • It handles more classes than its native capacity through ECOC (Error Correcting Output Codes) • As for license, the released weights are limited to non-commercial research and education. The inference code permits commercial use though. https://github.com/LGAI-Research/EXAONE-Tabular/blob/main/EXAONE_Tabular_v1.0_Technical_Report.pdf