When Does Synthetic Relational Data Teach Models to Use Relations? Tracing Predictive Structure from Pretraining Data to Model Behavior
cs.LG
Submitted: 2026-10-02
Updated: 2026-10-02
Sources
- TabPFN-3.5: Technical Report
- TabICLv2: A better, faster, scalable, and open tabular foundation model
- LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence
- Orion-MSP: Multi-Scale Sparse Attention for Tabular In-Context Learning
- Griffin: Towards a Graph-Centric Relational Database Foundation Model
- Shaping the Prior: How Synthetic Task Distributions Determine Tabular Foundation Model Quality
- RelDiff: Relational Data Generative Modeling with Graph-Based Diffusion Models
- PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models
- Relational In-Context Learning via Synthetic Pre-training with Structural Prior
- TRAK: Attributing Model Behavior at Scale
- RelBench v2: A Large-Scale Benchmark and Repository for Relational Data
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks