awesome-tabular-foundation-models
A curated list of resources, papers, and code for Tabular Foundation Models (TFMs), also known as Large Tabular Models (LTMs).
https://github.com/jxucoder/awesome-tabular-foundation-models
Last synced: 16 days ago
JSON representation
-
Benchmarks & Evaluation
-
Related Benchmarks
- MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image - A benchmark for multimodal tabular learning that combines text and image features. *Alan Arazi, Eilam Shapira, Shoham Grunblat, Mor Ventura, Elad Hoffer, Gioia Blayer, David Holzmüller, Lennart Purucker, Gaël Varoquaux, Frank Hutter, Roi Reichart.*
- Are Tabular Foundation Model Rankings Reliable? A Generalizability Theory Analysis of RelBench and DBInfer - Uses generalizability theory to assess the reliability of TFM rankings on RelBench and DBInfer. *Dinesh Katupputhur Ramprasath, Tom Palczewski, Joe Meyer, Roshan Reddy Upendra, Minghua Li.*
- Realistic Evaluation of TabPFN v2.5 in Open Environments - Evaluates TabPFN v2.5 under realistic open-environment conditions. *Zi-Jian Cheng, Ziyi Jia, Lan-Zhe Guo.*
- Ensembling Tabular Foundation Models: A Diversity Ceiling and a Calibration Trap - Analyzes the limits of ensembling TFMs, highlighting a diversity ceiling and a calibration trap. *Aditya Tanna, Yash Jignesh Desai, Pratinav Seth, Mohamed Bouadi, Nassim Bouarour, Vinay Sankarapu.*
- Exploring Differences Between Tabular Enterprise Data and Public Benchmarks - Contrasts the characteristics of enterprise tabular data with public benchmarks. *Myung Jun Kim, Maximilian Schambach, Frank Essenberger, Andre Sres, Johannes Höhne.*
- Benchmarking Attention for Tabular Foundation Models - Benchmarks attention mechanisms used in tabular foundation models. *Maximilian Schambach, Clemens Biehl, Sam Thelin.*
- Beyond Accuracy: Toward Trustworthy Tabular Foundation Models in Industrial Applications - Looks beyond accuracy toward trustworthiness of TFMs in industrial settings. *Johannes Keler, Matthias Woehrle, Jan Achterhold, Mark Schillinger, Maria Lyssenko, Luiz Ricardo Douat.*
- Benchmarking Tabular Foundation Models for Churn Prediction - Benchmarks tabular foundation models on customer churn prediction. *Sobhan Seyedzadeh, Mostafa Karimi.*
-
-
Introduction
-
Key References from Position Paper
-
Related Benchmarks
- Borisov et al. (2022) - Ziv & Armon (2022)](https://arxiv.org/abs/2106.03253)
- Grinsztajn et al. (2022)
- van Breugel & van der Schaar (2023)
-
-
Papers
-
Architectures & Training
- Paper
- Paper
- Paper
- Paper - z/MultiModalPFN)
- Paper
- OpenReview
- OpenReview
- OpenReview
- OpenReview
- OpenReview
- OpenReview
- OpenReview
- OpenReview
-
Causal Inference
-
Foundations & Position Papers
-
Graph & Relational Data
- Paper
- Blog & Whitepaper
- Paper
- Paper - research/G2T-FM)
- Paper
- OpenReview
- OpenReview
- OpenReview
- OpenReview
- OpenReview
- OpenReview
-
Optimization
-
Physical Systems & ODEs
-
Synthetic Data & Generation
-
Tabular Classification & Regression
- Paper
- Report
- Paper
- Paper
- Paper
- Paper - research/tabpfn-finetuning)
- Paper
- Paper
- Paper
- Paper
- Paper - inria/tabicl)
- Paper
- Paper
- Paper
- Paper - inria/tarte-ai)
- Paper
- Paper
- Paper
- Paper
- Paper - Tabular/TabSwift)
- Model - nori) | [Blog](https://www.synthefy.com/blog/synthefy-tabular-release)
- OpenReview
- OpenReview
- OpenReview
- OpenReview
- OpenReview
- OpenReview
- OpenReview
- OpenReview
- OpenReview
- OpenReview
- OpenReview
- OpenReview
- OpenReview
-
Theory & Analysis
-
-
Software & Code
-
Potential Applications
- PFNs - purpose library for creating and training Prior-Data Fitted Networks.
- TabTune - tuning across multiple tabular foundation models.
- TabICL - source, scikit-learn-compatible tabular foundation model for in-context learning (TabICLv2).
- TabPFN
- TabPFN
- TabSwift - wise attention TFM with adaptive early-exit.
- Nori - source (weights, inference, and training code) tabular foundation model for regression (`pip install synthefy-nori`).
- TabArena
-
Programming Languages
Categories
Sub Categories