rishabh ranjan (@_rishabhranjan_) - Twitter Profili

Sabitlenmiş Tweet

rishabh ranjan@_rishabhranjan_·30 Eki

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

English

5

40

149

49.9K

rishabh ranjan@_rishabhranjan_·27 Şub

@kvignesh1420 made some really amazing slides for this talk! Check them out here: drive.google.com/file/d/1oF-hNY…

Vignesh Kothapalli@kvignesh1420

Thoroughly enjoyed the discussions on PluRel and Relational Foundation Models during the talk! Thanks to an amazing audience @tempgraph_rg Slides: drive.google.com/file/d/1oF-hNY… Website: snap-stanford.github.io/plurel/ Github: github.com/snap-stanford/…

English

0

7

203

rishabh ranjan retweetledi

Vignesh Kothapalli@kvignesh1420·27 Şub

Thoroughly enjoyed the discussions on PluRel and Relational Foundation Models during the talk! Thanks to an amazing audience @tempgraph_rg Slides: drive.google.com/file/d/1oF-hNY… Website: snap-stanford.github.io/plurel/ Github: github.com/snap-stanford/…

temporal graph learning reading group@tempgraph_rg

📚 Today at the Reading Group, Thu, Feb 26, 11am EST, we’re excited to host Vignesh Kothapalli @kvignesh1420 (Stanford University) presenting: PLUREL: Synthetic Data Unlocks Scaling Laws for Relational Foundation Models zoom link on our website See you there! 🚀

English

2

5

21

1.4K

rishabh ranjan@_rishabhranjan_·19 Şub

Enjoyed presenting our ICLR 2026 work (Relational Transformer) at the TGL reading group today. Thanks for the insightful discussion! Slides from today: drive.google.com/file/d/1CPSUZC… Paper: arxiv.org/abs/2510.06377 Code, data, models: github.com/snap-stanford/…

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: github.com/snap-stanford/… Hope to see you there! zoom link on website!

English

1

5

30

3K

rishabh ranjan@_rishabhranjan_·19 Şub

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 shenyanghuang.github.io/rg.html 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: github.com/snap-stanford/… Hope to see you there! zoom link on website!

English

0

6

179

rishabh ranjan retweetledi

Vignesh Kothapalli@kvignesh1420·19 Şub

The PluRel webpage is now live! snap-stanford.github.io/plurel/

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

English

0

3

14

834

rishabh ranjan retweetledi

Jure Leskovec@jure·10 Şub

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

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

English

2

9

57

9.2K

rishabh ranjan@_rishabhranjan_·10 Şub

@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.

English

0

23

Navneet@navneet_rabdiya·10 Şub

@_rishabhranjan_ The real challenge w/ synthetic data for RFMs is maintaining referential integrity and realistic join cardinality distributions. Curious if you're using any specialized techniques for handling n:m relationships in your generator?

English

1

0

31

rishabh ranjan@_rishabhranjan_·9 Şub

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: arxiv.org/abs/2602.04029 Code, data, models: github.com/snap-stanford/…

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

English

1

5

24

2K

rishabh ranjan retweetledi

Vignesh Kothapalli@kvignesh1420·9 Şub

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

GIF

English

4

24

51

15.3K

rishabh ranjan@_rishabhranjan_·27 Oca

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

English

0

2

26

1.2K

rishabh ranjan retweetledi

Carlos Guestrin@guestrin·22 Oca

Relational Transformers provide zero shot predictions for complex databases!

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

English

0

7

37

5.3K

rishabh ranjan@_rishabhranjan_·12 Oca

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: relbench.stanford.edu 💻 GitHub: github.com/snap-stanford/… 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!

English

0

3

9

446

rishabh ranjan retweetledi

Jure Leskovec@jure·12 Oca

🚀 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: relbench.stanford.edu 💻 GitHub: github.com/snap-stanford/… 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!

English

0

25

41

4.6K

rishabh ranjan@_rishabhranjan_·6 Ara

Our "Relational Transformer" work is ORAL at the AI for Tabular Data Workshop! If you are in Europe for NeurIPS (EurIPS), come find us (mainly @VHudovernik) on Dec 6! #h.dqzmyglgdos5" target="_blank" rel="nofollow noopener">sites.google.com/view/eurips25-…

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

English

0

5

287

rishabh ranjan retweetledi

Frank Hutter@FrankRHutter·6 Kas

The data science revolution continues — TabPFN is now SOTA up to 50k data points and 2000 features 🚀 For the size limits of TabPFNv2, in a forward pass Real-TabPFN-2.5 outperforms AutoGluon 1.4 (complex ensemble including TabPFNv2 tuned for 4h) by 93 ELO points on TabArena.🧵1/

English

1

6

31

2.1K

rishabh ranjan@_rishabhranjan_·5 Kas

original post: linkedin.com/posts/philipp-…

English

0

1

150

rishabh ranjan@_rishabhranjan_·5 Kas

Exciting to see new model releases already 🚀 Championing by the world's largest vendor of enterprise software and the fifth-largest software company (by revenue) speaks to the immense real-world significance of foundation models for relational data. x.com/_rishabhranjan…

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

English

3

0

5

363

rishabh ranjan@_rishabhranjan_·2 Kas

@anag004 @SkildAI Congratulations!!

English

0

52

Ananye Agarwal@anag004·31 Eki

it's halloween🎃!! in other news — i got selected by MIT Tech Review as an Innovator Under 35 (Asia Pacific) for my work on AI and robotics! wouldn’t be half as fun (or possible) without my insanely talented collaborators at @SkildAI and CMU. tr35.mittrasia.com/awards

English

36

10

203

33.3K

rishabh ranjan

Keşfet