Search papers, labs, and topics across Lattice.
EXAONE Tabular is a novel compact foundation model designed for classification and regression tasks that leverages in-context learning without requiring dataset-specific gradient updates. By employing a unique architecture that interleaves feature-axis and item-axis attention, EXAONE Tabular achieves superior predictive performance while maintaining high efficiency, outperforming traditional methods and larger models. Its results on multiple benchmarks, including a first-place ranking on TabArena and competitive performance on BCCO and TALENT, highlight its potential as a state-of-the-art solution for tabular data tasks.
EXAONE Tabular outperforms tuned ensembles and larger models, achieving top rankings in multiple benchmarks while drastically reducing inference costs.
EXAONE Tabular is a compact tabular foundation model family for classification and regression via in-context learning, producing predictions without dataset-specific gradient updates. Pretrained exclusively on a synthetic structural-causal-model (SCM) prior, its central contribution is an architecture-centered redesign of tabular in-context learning. Rather than compressing features into a fixed row embedding before a separate row-level learner, EXAONE Tabular interleaves feature-axis attention within each item with support-conditioned item-axis attention within each feature at every Transformer layer, mediated by item-summary and feature-summary tokens. Across four public benchmarks, EXAONE Tabular combines strong predictive performance with high efficiency. On TabArena, its 20.81M-parameter classification model ranks first overall, surpassing tuned ensembles and 4-hour AutoML pipelines, while regression reaches the performance regime of the 1.64B-parameter TabFM at roughly 1/11 the inference cost. On BCCO and TALENT, EXAONE Tabular ranks second in classification and first in regression. On ScoringBench, it achieves the best mean rank for both point-estimation and predictive-distribution quality, leading the $R^2$, RMSE, and CRPS evaluations. Together, these results establish EXAONE Tabular as a state-of-the-art compact tabular foundation model family, combining strong predictive performance across classification, point regression, and probabilistic regression with an efficient model design.
