arXiv cs.CL· Alan Arazi, Eilam Shapira, Shoham Grunblat, Mor Ventura, Elad Hoffer, Gioia Blayer, David Holzm\"uller, Lennart Purucker, Ga\"el Varoquaux, Frank Hutter, Roi Reichart·· 12 小时前AI 评分32
MulTaBench：面向文本与图像的多模态表格学习基准发布
MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
AI 导读
研究者推出 MulTaBench，一个包含 40 个数据集的基准，图像-表格与文本-表格任务各占一半，聚焦模态间提供互补预测信号的场景。实验显示，按任务调优嵌入向量（目标感知表示）带来的性能提升可跨文本与图像模态、多种表格学习器、编码器规模和嵌入维度泛化。该基准是迄今规模最大的图像-表格评测工作，覆盖医疗与电商等高影响力领域，已被 NeurIPS 2026 接收为 Spotlight。
正文 · 原文
Authors:Alan Arazi, Eilam Shapira, Shoham Grunblat, Mor Ventura, Elad Hoffer, Gioia Blayer, David Holzmüller, Lennart Purucker, Gaël Varoquaux, Frank Hutter, Roi Reichart
Abstract:Tabular Foundation Models have recently established the state of the art in supervised tabular learning, by leveraging pretraining to learn generalizable representations of numerical and categorical structured data. However, they lack native support for unstructured modalities such as text and image, and rely on frozen, pretrained embeddings to process them. On established Multimodal Tabular Learning benchmarks, we show that tuning the embeddings to the task improves performance. Existing benchmarks, however, often focus on the mere co-occurrence of modalities; this leads to high variance across datasets and masks the benefits of task-specific tuning. To address this gap, we introduce MulTaBench, a benchmark of 40 datasets, split equally between image-tabular and text-tabular tasks. We focus on predictive tasks where the modalities provide complementary predictive signal, and where generic embeddings lose critical information, necessitating Target-Aware Representations that are aligned with the task. Our experimental results demonstrate that the gains from target-aware representation tuning generalize across both text and image modalities, several tabular learners, encoder scales, and embedding dimensions. MulTaBench constitutes the largest image-tabular benchmarking effort to date, spanning high-impact domains such as healthcare and e-commerce. It is designed to enable the research of novel architectures which incorporate joint modeling and target-aware representations, paving the way for the development of novel Multimodal Tabular Foundation Models.
| Comments: | Accepted to NeurIPS 2026 (Spotlight) |
| Subjects: | Machine Learning (cs.LG); Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2605.10616 [cs.LG] |
| (or arXiv:2605.10616v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.10616 arXiv-issued DOI via DataCite |
Submission history
From: Alan Arazi [view email]
[v1]
Mon, 11 May 2026 14:12:05 UTC (3,490 KB)
[v2]
Sun, 27 Sep 2026 19:05:57 UTC (3,514 KB)
[v3]
Fri, 30 Oct 2026 20:45:53 UTC (3,523 KB)
来源：arXiv cs.CL · arxiv.org