VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning
贾 子怡, Zijian Cheng, Xinyue Zhang, Kun-Yang Yu, Zhi Zhou, Yu-Feng Li, Lan-Zhe Guo
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 \textit{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 21 representative models, including unimodal experts, specialized visual-tabular models, and general-purpose vision-language models (VLMs), 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: \url{https://anonymous.4open.science/r/VT-Bench-13C2}
BibTeX
@inproceedings{
jia2026vtbench,
title={{VT}-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning},
author={Ziyi Jia and Zi-Jian Cheng and Xinyue Zhang and Kun-Yang Yu and Zhi Zhou and Yu-Feng Li and Lan-Zhe Guo},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=4oZDo5v9zt}
}