rishabh ranjan

Stanford CS PhD w @jure and @guestrin. Prev. CMU w @zacharylipton, IIT Delhi. I like neural networks.

[rishabh ranjan @_rishabhranjan_]

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 share what I have been working on over the last year: a Foundation Model architecture which brings the power of Transformers to relational domains, enabling large-scale pretraining and zero-shot generalization in enterprise settings. 🧵1/n

[Vignesh Kothapalli @kvignesh1420]

Can reasoning models become overly reliant on chain-of-thought examples? 🤔

Our #ACL2026 work shows excessive CoT supervision is not always beneficial, and gives a recipe for tuning the CoT fraction to improve novel-task accuracy. 🧵

Website: https://t.co/hZmPCF6bue

[rishabh ranjan @_rishabhranjan_]

PluRel has been accepted to ICML 2026!✨ See you in Seoul 🇰🇷

[Vignesh Kothapalli @kvignesh1420]

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 RFMs. 🧵

Kudos to the amazing collaborators at @StanfordAILab @Kumo_ai_team , and @SAP : @_rishabhranjan_ @VHudovernik @vijaypradwi @johanneshoffart @guestrin @jure

[rishabh ranjan @_rishabhranjan_]

We're presenting PluRel at the Data for Foundation Models Workshop at ICLR! 🇧🇷

[Vignesh Kothapalli @kvignesh1420]

Come check out PluRel at the DATA-FM workshop @iclr_conf tomorrow (04/26) Room 203 A/B

[rishabh ranjan @_rishabhranjan_]

If you're at ICLR, come check out our poster for RelBench v2 (https://t.co/YuABahiFdi) at the DATA-FM (Data for Foundation Models) Workshop! Apr 26, Hall 203 A/B 🇧🇷

[rishabh ranjan @_rishabhranjan_]

Although relational databases are everywhere, there is no equivalent of the public internet for pretraining Relational Foundation Models (RFMs). Excited to see RelBench bridging that gap, growing from 7 datasets in v1 to 88+ datasets in v2.
Deeply grateful to the numerous community contributions for helping RelBench serve as the central data repository for RFM research. ❤️

[rishabh ranjan @_rishabhranjan_]

Excited to present Relational Transformer at ICLR 2026 tomorrow (Apr 25)! 🇧🇷 Please come by our poster (#823, Pavilion 3) in session 1 (10:30am - 1pm) 🧑‍🎓

[rishabh ranjan @_rishabhranjan_]

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 share what I have been working on over the last year: a Foundation Model architecture which brings the power of Transformers to relational domains, enabling large-scale pretraining and zero-shot generalization in enterprise settings. 🧵1/n

[rishabh ranjan @_rishabhranjan_]

@kvignesh1420 made some really amazing slides for this talk! Check them out here: https://t.co/ykisMg09L4

[Vignesh Kothapalli @kvignesh1420]

Thoroughly enjoyed the discussions on PluRel and Relational Foundation Models during the talk! Thanks to an amazing audience @tempgraph_rg

Slides: https://t.co/04P226ajil
Website: https://t.co/0JvREDwu9a
Github: https://t.co/FIVNrovEDT

[Vignesh Kothapalli @kvignesh1420]

Thoroughly enjoyed the discussions on PluRel and Relational Foundation Models during the talk! Thanks to an amazing audience @tempgraph_rg

Slides: https://t.co/04P226ajil
Website: https://t.co/0JvREDwu9a
Github: https://t.co/FIVNrovEDT

[rishabh ranjan @_rishabhranjan_]

Enjoyed presenting our ICLR 2026 work (Relational Transformer) at the TGL reading group today. Thanks for the insightful discussion!

Slides from today: https://t.co/xouFt7njSR
Paper: https://t.co/JXikptIiEz
Code, data, models: https://t.co/sg0jVLcuBq

[temporal graph learning reading group @tempgraph_rg]

This Thursday (Feb 19, 11am EST) at the reading group: Rishabh Ranjan (Stanford) presents Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data.

Paper & code: https://t.co/GIfqdgJpXU

Hope to see you there! zoom link on website!

[rishabh ranjan @_rishabhranjan_]

Excited to talk about our recent work on Relational Transformers at the TGL Reading Group tomorrow. Please drop by on Feb 19, 11am EST (see https://t.co/hVqC7pCzOm for Zoom link).

[temporal graph learning reading group @tempgraph_rg]

This Thursday (Feb 19, 11am EST) at the reading group: Rishabh Ranjan (Stanford) presents Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data.

Paper & code: https://t.co/GIfqdgJpXU

Hope to see you there! zoom link on website!

[Vignesh Kothapalli @kvignesh1420]

The PluRel webpage is now live!
https://t.co/0JvREDwu9a

[Jure Leskovec @jure]

Quite exciting work on synthetic data generation that for the first time demonstrates scaling laws for graph/relational foundation models.

Great work by @kvignesh1420 @_rishabhranjan_ @VHudovernik and our collaborators at @Kumo_ai_team and @SAP

[rishabh ranjan @_rishabhranjan_]

@navneet_rabdiya Yes! We use Hierarchical Stochastic Block Model (HSBM) to randomly sample bipartite graphs that capture realistic foreign--primary key relationship patterns. Please check the paper for more details.

[rishabh ranjan @_rishabhranjan_]

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 with @kvignesh1420, @VHudovernik, @vijaypradwi, @johanneshoffart, @guestrin and @jure.

Paper: https://t.co/4jzttapESf
Code, data, models: https://t.co/gd58JA9imo

[Vignesh Kothapalli @kvignesh1420]

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 RFMs. 🧵

Kudos to the amazing collaborators at @StanfordAILab @Kumo_ai_team , and @SAP : @_rishabhranjan_ @VHudovernik @vijaypradwi @johanneshoffart @guestrin @jure

[Vignesh Kothapalli @kvignesh1420]

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 RFMs. 🧵

Kudos to the amazing collaborators at @StanfordAILab @Kumo_ai_team , and @SAP : @_rishabhranjan_ @VHudovernik @vijaypradwi @johanneshoffart @guestrin @jure

[rishabh ranjan @_rishabhranjan_]

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

[rishabh ranjan @_rishabhranjan_]

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 share what I have been working on over the last year: a Foundation Model architecture which brings the power of Transformers to relational domains, enabling large-scale pretraining and zero-shot generalization in enterprise settings. 🧵1/n

[Carlos Guestrin @guestrin]

Relational Transformers provide zero shot predictions for complex databases!

[rishabh ranjan @_rishabhranjan_]

Although relational databases are everywhere, there is no equivalent of the public internet for pretraining Relational Foundation Models (RFMs). Excited to see RelBench bridging that gap, growing from 7 datasets in v1 to 88+ datasets in v2.
Deeply grateful to the numerous community contributions for helping RelBench serve as the central data repository for RFM research. ❤️

[Jure Leskovec @jure]

🚀 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 features:
🍺 4 new databases, spanning domains like e-commerce and beer reviews to scientific research and clinical healthcare.
🧩 40 new predictive tasks, including 28 autocomplete tasks, across new and existing databases.
🔌 External data integrations: 70+ datasets from CTU, 7 datasets from 4DBInfer, and your own data via SQL connector, all in RelBench format.
🛠️ Bug fixes and performance improvements.

🔥 Introducing autocomplete tasks: As opposed to forecasting tasks, autocomplete tasks predict existing columns in the database. We found that models need to deeply understand the relational context to autocomplete database fields, a critical capability that expands the scope of real-world RDL applications.

Learn more:
🌐 Website: https://t.co/G4OBtj0R92
💻 GitHub: https://t.co/99FBJK5kji
Huge thanks to @justingu32 @_rishabhranjan_ @jakub_peleska @VHudovernik @CKanatsoulis @fengyuli607, Tang Haiming, Alistiq and everyone else who contributed to our GitHub for making this possible!

[Jure Leskovec @jure]

🚀 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 features:
🍺 4 new databases, spanning domains like e-commerce and beer reviews to scientific research and clinical healthcare.
🧩 40 new predictive tasks, including 28 autocomplete tasks, across new and existing databases.
🔌 External data integrations: 70+ datasets from CTU, 7 datasets from 4DBInfer, and your own data via SQL connector, all in RelBench format.
🛠️ Bug fixes and performance improvements.

🔥 Introducing autocomplete tasks: As opposed to forecasting tasks, autocomplete tasks predict existing columns in the database. We found that models need to deeply understand the relational context to autocomplete database fields, a critical capability that expands the scope of real-world RDL applications.

Learn more:
🌐 Website: https://t.co/G4OBtj0R92
💻 GitHub: https://t.co/99FBJK5kji
Huge thanks to @justingu32 @_rishabhranjan_ @jakub_peleska @VHudovernik @CKanatsoulis @fengyuli607, Tang Haiming, Alistiq and everyone else who contributed to our GitHub for making this possible!