TIME: TabPFN-Integrated Multimodal Engine for Robust Tabular-Image Learning

Tabular-image multimodal learning, which integrates structured tabular data with imaging data, holds great promise for a variety of tasks, especially in medical applications. Yet, two key challenges remain: (1) the lack of a standardized, pretrained representation for tabular data, as is commonly available in vision and language domains; and (2) the difficulty of handling missing values in the tabular modality, which are common in real-world medical datasets. To address these issues, we propose the T abPFN-Integrated M ultimodal E ngine ( TIME), a novel multimodal framework that builds on the recently introduced tabular foundation model, TabPFN. TIME leverages TabPFN as a frozen tabular encoder to generate robust, strong embeddings that are naturally resilient to missing data, and combines them with image features from pretrained vision backbones. Extensive experiments demonstrate that TIME consistently outperforms competitive baselines across both complete and incomplete tabular inputs, underscoring its practical value in real-world mul-timodal learning scenarios. Keywords: Multimodal Learning, Tabular-Image, Pretrained Model, TabPFN 1. Introduction Multimodal learning has emerged as a powerful paradigm for integrating diverse data sources to enhance learning and decision-making across a wide range of domains [1]. Among the many forms of multimodal integration, tabular-image multimodal learning plays a uniquely important role, especially in clinical and biomedical applications [2, 3]. In such settings, structured tabular data such as laboratory test results often coexist with unstructured imaging data like X-rays.