FEAT: דגם יסודי לינארי-מורכב לנתונים מאורגנים גדולים מאוד

תקציר מקורי באנגליתarXiv:2603.16513v4 Announce Type: replace Abstract: Structured data is widely used in domains such as healthcare, finance, and scientific data management. Recent studies on structured data foundation models (SFMs) aim to support data analysis and mining tasks over such data, but still face scalability and generalization challenges when applied to real-world enterprise databases. First, many SFMs rely on full self-attention, which introduces an O(N^2) computational bottleneck and limits the number of tuples that can be processed jointly. Second, directly replacing attention with linear-complexity sequence models may conflict with the permutation-invariant nature of structured data, introducing artificial order bias and degrading representation quality. Moreover, models trained only on synth