Stanford Tabular and Relational (STAR) Project

Stanford Tabular and Relational (STAR) Project

Foundation models for tabular and relational data.

Advancing foundation models for structured data, from a single table to the many linked tables of a relational database.

Explore the research Models & datasets ↗

Latest

Aug 2026 · Paper

RT-PluRel is the #1 system on RelArena-α

RelArena-α, the new open and reproducible benchmark for relational learning from Prior Labs, ranks our Relational Transformer pretrained on PluRel synthetic data first in end-to-end predictive performance.

Open Resources

Models, datasets, and code.

🤗 Hugging Face · stanford-starmodels & datasets GitHub · stanford-staropen-source code

Models

Model	Description	Params
rt-j	Context-efficient relational foundation model pretrained on THE JOIN.	85M	open ↗
rt-plurel	Relational Transformer pretrained on PluRel synthetic databases, for in-context prediction; the #1 system on RelArena-α. Original 22M PluRel-paper checkpoints preserved under `paper/`.	85M	open ↗
rt-v1	Original Relational Transformer checkpoints from the ICLR 2026 paper, including per-dataset held-out pretraining and continued-pretraining variants.	22M	open ↗

Datasets

Dataset	Description	Databases
the-join	The largest open relational corpus for pretraining, spanning academic, e-commerce, finance, sports, biomedical, government, and text2sql domains, with forecasting and autocomplete tasks.	639	open ↗
relbench	The original RelBench v1 databases and tasks, in the self-describing manifest format.	7	open ↗
relbench-v2-extra	Additional real-world databases introduced with RelBench v2.	3	open ↗
plurel	Synthetic relational databases generated by PluRel for scaling-law pretraining.	2,000	open ↗
redelex	Databases from the CTU Prague Relational Learning Repository, ported via redelex.	71	open ↗
tgb	Temporal Graph Benchmark datasets exported to the RelBench format, with official splits and negatives.	12	open ↗
dbinfer	The 4DBInfer benchmark databases in RelBench format, with their original labels.	7	open ↗

Talks

Talks and presentations.

Talk: Zero-Shot Predictive Models for Relational Databases

Zero-Shot Predictive Models for Relational Databases Mark Žnidar · YC ML Meetup at Startup School

Talk: PluRel, Synthetic Data unlocks Scaling Laws for Relational Foundation Models

PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models Vignesh Kothapalli · Temporal Graph Learning Reading Group

Talk: Relational Transformer, Toward Zero-Shot Foundation Models for Relational Data

Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data Rishabh Ranjan · Temporal Graph Learning Reading Group

Keynote by Jure Leskovec on relational foundation models at ACM RecSys

Relational Foundation Models Jure Leskovec · ACM RecSys 2025 keynote

Talk: Large Language Models are Good Relational Learners

Large Language Models are Good Relational Learners Fang Wu & Vijay Prakash Dwivedi · Temporal Graph Learning Reading Group

Talk: RelBench, A Benchmark for Deep Learning on Relational Databases

RelBench: A Benchmark for Deep Learning on Relational Databases Rishabh Ranjan · Temporal Graph Learning Reading Group

People

Built at Stanford, with collaborators across academia and industry.

Faculty

Jure LeskovecProfessor of Computer Science · Stanford

Carlos GuestrinProfessor of Computer Science · Stanford

Core team

Rishabh RanjanPhD Student

Vignesh KothapalliPhD Student

Charilaos KanatsoulisResearch Associate

Other contributors

Adrian Hayler · Alan Arazi · Alejandro Dobles · Fang Wu · Federico López · Fengyu Li · Frank Hutter · Haiming Tang · Harshvardhan Agarwal · Jan Eric Lenssen · Jiaqi Han · Jiaxuan You · Joe Meyer · Johannes Hoffart · Joshua Robinson · Justin Gu · Kexin Huang · Klemens Flöge · Lennart Purucker · Mahmoud Mohammadi · Mark Znidar · Martin Jurkovic · Matthias Fey · Noah Hollmann · Parth Shroff · Pranshu Chaturvedi · Rex Ying · Rishi Puri · Roshan Upendra · Shenyang Huang · Sri Jaladi · Tianlang Chen · Tom Palczewski · Valter Hudovernik · Vijay Prakash Dwivedi · Weihua Hu · Xinwei He · Yangyi Shen · Yiwen Yuan · Zecheng Zhang

Partner institutions