Why Tabular Foundation Models Excel on Relational Data They Have Never Seen
cs.AI, cs.DB, cs.LG
Submitted: 2026-11-02
Updated: 2026-11-03
Terminology
Sources
- A Fair Benchmarking of Deep Relational Database Learning Models
- RelGNN: Composite Message Passing for Relational Deep Learning
- OpenRFM: Dissecting Relational In-Context Learning
- Supervised Learning on Relational Databases with Graph Neural Networks
- Relational Graph Transformer
- EXAONE Tabular 1.0 : Technical Report
- Relational Deep Learning: Graph Representation Learning on Relational Databases
- TabPFN-3: Technical Report
- Fraud Dataset Benchmark and Applications
- RelBench v2: A Large-Scale Benchmark and Repository for Relational Data
- Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning
- Advancing Open and Reproducible Relational Learning: RelArena- alpha, TabPFN-Rel and RPI
- TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
- RelAgent: LLM Agents as Data Scientists for Relational Learning
- KumoRFM-2: Scaling Foundation Models for Relational Learning
- TabPFN-3.5: Technical Report
- PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models
- The CTU Prague Relational Learning Repository
- Transformers Can Do Bayesian Inference
- Beyond IID: How General Are Tabular Foundation Models, Really?
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents