AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Relational In-Context Learning via Synthetic Pre-training with Structural Prior

Yanbo Wang, Jiaxuan You, Chuan Shi, Muhan Zhang

ICML 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Medical vision-language models

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add relational synthetic pre-training stage on top of single-table pre-training (ablation)RDB-PFN-Single · single-table few-shot benchmarkaccuracyImproved
use RDB-PFN relational prior instead of generic single-table priors with same DFS inputssingle-estimator TFMs · 19 relational tasksROC-AUCImproved
compare RDB-PFN to specialized single-table TFMs on single-table dataRDB-PFN · single-table benchmarkaccuracyHurt
use LayerDAG learned schema generator instead of simpler DAG generator (ablation)relational prior · 19 relational tasksROC-AUCImproved
simplify schema generator, link mechanism, temporal component, locality assumption or interleaved attention (ablation)RDB-PFN · 19 relational tasksperformanceHurt
target-task fine-tuning beyond ICL (ablation)RDB-PFN · relational tasksperformanceImproved
cross-task fine-tuning (ablation)RDB-PFN · relational tasksperformanceImproved
chunked-support ensembling with larger effective support size (ablation)RDB-PFN · relational tasksperformanceImproved
strengthen classical baselines with tuned XGBoost and AutoGluon best_quality (ablation)classical baselines · relational tasksROC-AUCNo clear effect
evaluate with PR-AUC instead of ROC-AUC (ablation)RDB-PFN comparison · imbalanced relational tasksPR-AUCNo clear effect
disable default ensembling for baselines (Lite) (ablation)tabular foundation models · 19 relational tasksROC-AUCMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy