No Data? No Problem: Robust Vision-Tabular Learning with Missing Values

ArXi:2512.19602v2 Announce Type: replace Large-scale medical biobanks provide imaging data complemented by extensive tabular information, such as clinical measurements or graphics. However, this abundance of tabular attributes does not reflect real-world datasets, where only a subset of attributes may be available. This discrepancy calls for methods that remain robust to missing values at inference. To address this challenge, we propose RoVTL (Robust Vision-Tabular Learning), a framework designed to handle any level of tabular data availability, from 0% to 100