# Unlocking the Power of Medical Tabular Data via Semantic-Aware Multimodal Pre-training

arXiv: https://arxiv.org/abs/2608.10522 · HTML: https://mlsanity.com/paper/2608.10522/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Medical vision-language models](https://mlsanity.com/mllm/medical-vision-language-models/)

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [AdaBins: Depth Estimation using Adaptive Bins](https://mlsanity.com/paper/2011.14141/) (2020)
- [SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training](https://mlsanity.com/paper/2106.01342/) (2021)
- [SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption](https://mlsanity.com/paper/2106.15147/) (2021)
- [Best of Both Worlds: Multimodal Contrastive Learning with Tabular and Imaging Data](https://mlsanity.com/paper/2303.14080/) (2023)
- [TIP: Tabular-Image Pre-training for Multimodal Classification with Incomplete Data](https://mlsanity.com/paper/2407.07582/) (2024)
- [Derm1M: A Million-scale Vision-Language Dataset Aligned with Clinical Ontology Knowledge for Dermatology](https://mlsanity.com/paper/2503.14911/) (2025)
- [MAKE: Multi-Aspect Knowledge-Enhanced Vision-Language Pretraining for Zero-shot Dermatological Assessment](https://mlsanity.com/paper/2505.09372/) (2025)
- [Unleashing the Power of Image-Tabular Self-Supervised Learning via Breaking Cross-Tabular Barriers](https://mlsanity.com/paper/2512.14026/) (2025)
- [A Vision-Language Foundation Model for Zero-shot Clinical Collaboration and Automated Concept Discovery in Dermatology](https://mlsanity.com/paper/2602.10624/) (2026)
- [Multi-Aspect Knowledge-Enhanced Medical Vision-Language Pretraining with Multi-Agent Data Generation](https://mlsanity.com/paper/2512.03445/) (2025)

## Abstract (arXiv)

While vision-language models dominate medical representation learning, unstructured text lacks the dense, quantitative diagnostic phenotypes inherent in structured clinical tables. However, existing multimodal pre-training methods underutilize this potential due to semantic-agnostic designs that treat tabular inputs as flat vectors and employ unstable continuous regression objectives. To overcome this, we propose a novel semantic-aware framework explicitly modeling the intrinsic two-dimensional structure of tabular data. First, addressing the inter-feature hierarchy of varying diagnostic importance, we introduce Importance-Aware Adaptive Masking to construct a label-free curriculum prioritizing salient features. Second, addressing the intra-feature continuity-discreteness duality, we propose a Soft-Label Discretized Module that replaces unstable numerical regression with stable distribution matching, thereby mathematically preserving ordinal relationships. Extensive experiments across large-scale dermatology (SLICE-3D, HOP) and ophthalmology (EyePACS) datasets establish a new state-of-the-art (SOTA), demonstrating exceptional robustness and cross-domain generalizability.