Transformers are great for sequences, but most business-critical predictions (e.g. product sales, customer churn, ad CTR, in-hospital mortality) rely on highly-structured relational data where signal is scattered across rows, columns, linked tables and time. Excited to finally

🚀 Announcing RelBench V2, a major update to our benchmark for foundation models on relational data! With V2, we are significantly expanding the benchmark’s scope to catalyze further research in Relational Deep Learning (RDL) and Relational Foundation Models (RFMs). Key

Relational Transformer has been accepted to ICLR 2026!!🎉 See you in Brazil 🇧🇷

New research from Stanford University, Kumo, and SAP, co-authored by Jure Leskovec, advances how relational foundation models learn from data. Paper: arxiv.org/pdf/2602.04029 Code and data: github.com/snap-stanford/…

Relational Foundation Models face a scaling problem: diverse training datasets are rarely public due to privacy constraints 🔒. 🚀 We are excited to introduce "PluRel": a framework that synthesizes diverse multi-table relational databases from scratch, unlocking scaling laws for

Synthetic data is critical for foundation models, even more so in relational and tabular domains where public data is scarce. Our new work shows how synthetic pretraining unlocks a whole new axis to scale up relational foundation models (RFMs)! This was a super fun collaboration