发表机构
LG AI Research（LG AI研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
EXAONE Tabular 1.0 是一款紧凑表格基础模型系列，通过重新设计架构实现高效表格上下文学习，在多个公开基准测试中展现出优于同类模型的预测性能与推理效率。
AI 中文摘要
EXAONE Tabular 是一款用于分类和回归的紧凑表格基础模型系列，通过上下文学习生成预测结果，无需针对特定数据集进行梯度更新。该模型仅基于合成结构因果模型（SCM）先验进行预训练，其核心贡献是对表格上下文学习进行了以架构为中心的重新设计：与将特征压缩为固定行嵌入后再单独进行行级学习的方式不同，EXAONE Tabular 在每个 Transformer 层中，在每个条目内交错使用特征轴注意力，在每个特征内使用支持条件的条目轴注意力，由条目摘要和特征摘要令牌进行协调。在四个公开基准测试中，EXAONE Tabular 兼具强大的预测性能与高效性：在 TabArena 上，其参数规模为 2081 万的分类模型总体排名第一，超过了调优集成模型和耗时 4 小时的 AutoML 流水线，而回归性能达到了参数规模 16.4 亿的 TabFM 的水平，推理成本仅约为其 1/11；在 BCCO 和 TALENT 上，EXAONE Tabular 的分类排名第二、回归排名第一；在 ScoringBench 上，它在点估计和预测分布质量两项指标上均取得了最佳平均排名，在 R²、RMSE 和 CRPS 评估中均处于领先地位。综合这些结果，EXAONE Tabular 被确立为最先进的紧凑表格基础模型系列，在分类、点回归和概率回归任务中兼具强大的预测性能与高效的模型设计。
英文摘要
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.
Comments18 pages, 8 figures
