Valter Hudovernik (@vhudovernik) 's Twitter Profile
Valter Hudovernik

@vhudovernik

ID: 2872558690

calendar_today11-11-2014 17:03:14

6 Tweet

14 Takipçi

56 Takip Edilen

rishabh ranjan (@_rishabhranjan_) 's Twitter Profile Photo

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

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
Jure Leskovec (@jure) 's Twitter Profile Photo

🚀 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

🚀 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
Kumo (@kumo_ai_team) 's Twitter Profile Photo

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/…

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/…
Vignesh Kothapalli (@kvignesh1420) 's Twitter Profile Photo

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

rishabh ranjan (@_rishabhranjan_) 's Twitter Profile Photo

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

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