MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
Summary
Introduces MulTaBench, a benchmark of 40 datasets for multimodal tabular learning with text and image modalities, demonstrating that task-specific embedding tuning improves performance over frozen pretrained embeddings, particularly when modalities provide complementary predictive signals.
View Cached Full Text
Cached at: 05/14/26, 08:17 AM
Paper page - MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
Source: https://huggingface.co/papers/2605.10616
Abstract
Multimodal tabular learning benchmarks reveal that task-specific embedding tuning improves performance over frozen pretrained embeddings, particularly when modalities provide complementary predictive signals.
Tabular Foundation Modelshave 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 embeddingsto process them. On establishedMultimodal Tabular Learningbenchmarks, 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 introduceMulTaBench, a benchmark of 40 datasets, split equally between image-tabular and text-tabular tasks. We focus onpredictive taskswhere the modalities providecomplementary predictive signal, and where generic embeddings lose critical information, necessitatingTarget-Aware Representationsthat 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.MulTaBenchconstitutes 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 incorporatejoint modelingandtarget-aware representations, paving the way for the development of novel MultimodalTabular Foundation Models.
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2605\.10616
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2605.10616 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2605.10616 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2605.10616 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
MuteBench: Modality Unavailability Tolerance Evaluation for Incomplete Multimodal Fusion
MuteBench is a benchmark for evaluating multimodal fusion models under modality missing and within-modality missing conditions across clinical datasets. It provides insights into architecture robustness and suggests that diffusion-based imputation can help.
WildTableBench: Benchmarking Multimodal Foundation Models on Table Understanding In the Wild
WildTableBench introduces the first question-answering benchmark for real-world table images, revealing that existing multimodal foundation models struggle significantly with structural perception and numerical reasoning, with only one model exceeding 50% accuracy.
TabEmbed: Benchmarking and Learning Generalist Embeddings for Tabular Understanding
This paper introduces TabEmbed, a generalist embedding model for tabular data that unifies classification and retrieval tasks, along with TabBench, a new benchmark for evaluating tabular understanding.
Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models
Introduces Blind-Spots-Bench, a benchmark designed to expose persistent failures in modern multimodal AI models on tasks that are trivial for humans. Evaluates a range of models, revealing performance gaps and that no single model dominates across all task types.
M$^3$R-Bench: A Unified Benchmark for Evidence-Grounded Multimodal Metaphor Understanding
This paper introduces M3R-Bench, a unified evidence-grounded benchmark for multimodal metaphor understanding with 1,000 image-text instances, and proposes M3R-Reasoner, an 8B-parameter model combining curriculum-based reasoning supervision and reinforcement learning that outperforms larger proprietary models.