VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning

Ziyi Jia, Zi-Jian Cheng, Xinyue Zhang, Kun-Yang Yu, Zhi Zhou, Yu-Feng Li, Lan-Zhe Guo
Proceedings of the 43rd International Conference on Machine Learning, PMLR 306:51712-51741, 2026.

Abstract

Multi-model learning has attracted great attention in visual-text tasks. However, visual-tabular data, which plays a pivotal role in high-stakes domains like healthcare and industry, remains underexplored. In this paper, we introduce VT-Bench, the first unified benchmark for standardizing vision-tabular discriminative prediction and generative reasoning tasks. VT-Bench aggregates 14 datasets across 9 domains (medical-centric, while covering pets, media, and transportation) with over 756K samples. We evaluate 23 representative models, including unimodal experts, specialized visual-tabular models, general-purpose vision-language models (VLMs), and tool-augmented methods, highlighting substantial challenges of visual-tabular learning. We believe VT-Bench will stimulate the community to build more powerful multi-modal vision-tabular foundation models. Benchmark: https://github.com/LAMDA-NeSy/VT-Bench

Cite this Paper


BibTeX
@InProceedings{pmlr-v306-jia26a, title = {{VT}-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning}, author = {Jia, Ziyi and Cheng, Zi-Jian and Zhang, Xinyue and Yu, Kun-Yang and Zhou, Zhi and Li, Yu-Feng and Guo, Lan-Zhe}, booktitle = {Proceedings of the 43rd International Conference on Machine Learning}, pages = {51712--51741}, year = {2026}, editor = {Zhang, Tong and Dudik, Miroslav and Jaggi, Martin and Agarwal, Alekh and Li, Sharon and Schuurmans, Dale and Zhu, Jerry and Berkenkamp, Felix and Dong, Hanze and Bietti, Alberto}, volume = {306}, series = {Proceedings of Machine Learning Research}, month = {06--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v306/main/assets/jia26a/jia26a.pdf}, url = {https://proceedings.mlr.press/v306/jia26a.html}, abstract = {Multi-model learning has attracted great attention in visual-text tasks. However, visual-tabular data, which plays a pivotal role in high-stakes domains like healthcare and industry, remains underexplored. In this paper, we introduce VT-Bench, the first unified benchmark for standardizing vision-tabular discriminative prediction and generative reasoning tasks. VT-Bench aggregates 14 datasets across 9 domains (medical-centric, while covering pets, media, and transportation) with over 756K samples. We evaluate 23 representative models, including unimodal experts, specialized visual-tabular models, general-purpose vision-language models (VLMs), and tool-augmented methods, highlighting substantial challenges of visual-tabular learning. We believe VT-Bench will stimulate the community to build more powerful multi-modal vision-tabular foundation models. Benchmark: https://github.com/LAMDA-NeSy/VT-Bench} }
Endnote
%0 Conference Paper %T VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning %A Ziyi Jia %A Zi-Jian Cheng %A Xinyue Zhang %A Kun-Yang Yu %A Zhi Zhou %A Yu-Feng Li %A Lan-Zhe Guo %B Proceedings of the 43rd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2026 %E Tong Zhang %E Miroslav Dudik %E Martin Jaggi %E Alekh Agarwal %E Sharon Li %E Dale Schuurmans %E Jerry Zhu %E Felix Berkenkamp %E Hanze Dong %E Alberto Bietti %F pmlr-v306-jia26a %I PMLR %P 51712--51741 %U https://proceedings.mlr.press/v306/jia26a.html %V 306 %X Multi-model learning has attracted great attention in visual-text tasks. However, visual-tabular data, which plays a pivotal role in high-stakes domains like healthcare and industry, remains underexplored. In this paper, we introduce VT-Bench, the first unified benchmark for standardizing vision-tabular discriminative prediction and generative reasoning tasks. VT-Bench aggregates 14 datasets across 9 domains (medical-centric, while covering pets, media, and transportation) with over 756K samples. We evaluate 23 representative models, including unimodal experts, specialized visual-tabular models, general-purpose vision-language models (VLMs), and tool-augmented methods, highlighting substantial challenges of visual-tabular learning. We believe VT-Bench will stimulate the community to build more powerful multi-modal vision-tabular foundation models. Benchmark: https://github.com/LAMDA-NeSy/VT-Bench
APA
Jia, Z., Cheng, Z., Zhang, X., Yu, K., Zhou, Z., Li, Y. & Guo, L.. (2026). VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning. Proceedings of the 43rd International Conference on Machine Learning, in Proceedings of Machine Learning Research 306:51712-51741 Available from https://proceedings.mlr.press/v306/jia26a.html.

Related Material