MulTaBench is a new collection of 40 image-tabular and text-tabular datasets designed to test target-aware representation tuning in multimodal tabular models.
org/abs/2511.02818
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.LG 8years
2026 8roles
background 2polarities
background 2representative citing papers
TFM-Retouche is an architecture-agnostic input-space residual adapter that improves tabular foundation model accuracy on 51 datasets by learning input corrections through the frozen backbone, with an identity guard to fall back to the original model.
O'Prior, a compositional synthetic prior with hierarchical SCMs, realism engines, stress modules, and curriculum protocols, improves tabular foundation model accuracy and robustness on real benchmarks when architecture and compute are held fixed.
Distilling TabICLv2 into XGBoost via stratified OOF labeling yields 0.882 macro-mean AUC (96.5% of teacher) at 1.9 ms CPU across 153 datasets, with significant gains over tuned CatBoost on low-dimensional data.
Leakage-aware distillation transfers at least 90% of tabular foundation model AUC to lightweight students across 19 health datasets, with 26x CPU speedup and preserved calibration/fairness.
Six modern tabular foundation models are near-redundant, limiting ensemble gains to +0.18% accuracy at high cost while some methods degrade calibration.
Context construction strategies such as balanced sampling improve AUC-ROC by 3-4 points over uniform sampling in tabular foundation models for credit risk, exceeding differences between model families and matching classical baselines.
TabPFN maintains high ROC-AUC and structured attention under controlled additions of irrelevant features, nonlinear correlations, and mislabeled targets in binary classification.
citing papers explorer
-
MulTaBench: Benchmarking Multimodal Tabular Learning with Text and Image
MulTaBench is a new collection of 40 image-tabular and text-tabular datasets designed to test target-aware representation tuning in multimodal tabular models.
-
TFM-Retouche: A Lightweight Input-Space Adapter for Tabular Foundation Models
TFM-Retouche is an architecture-agnostic input-space residual adapter that improves tabular foundation model accuracy on 51 datasets by learning input corrections through the frozen backbone, with an identity guard to fall back to the original model.
-
Shaping the Prior: How Synthetic Task Distributions Determine Tabular Foundation Model Quality
O'Prior, a compositional synthetic prior with hierarchical SCMs, realism engines, stress modules, and curriculum protocols, improves tabular foundation model accuracy and robustness on real benchmarks when architecture and compute are held fixed.
-
Pocket Foundation Models: Distilling TFMs into CPU-Ready Gradient-Boosted Trees
Distilling TabICLv2 into XGBoost via stratified OOF labeling yields 0.882 macro-mean AUC (96.5% of teacher) at 1.9 ms CPU across 153 datasets, with significant gains over tuned CatBoost on low-dimensional data.
-
Distilling Tabular Foundation Models for Structured Health Data
Leakage-aware distillation transfers at least 90% of tabular foundation model AUC to lightweight students across 19 health datasets, with 26x CPU speedup and preserved calibration/fairness.
-
Ensembling Tabular Foundation Models - A Diversity Ceiling And A Calibration Trap
Six modern tabular foundation models are near-redundant, limiting ensemble gains to +0.18% accuracy at high cost while some methods degrade calibration.
-
Data Presentation Over Architecture: Resampling Strategies for Credit Risk Prediction with Tabular Foundation Models
Context construction strategies such as balanced sampling improve AUC-ROC by 3-4 points over uniform sampling in tabular foundation models for credit risk, exceeding differences between model families and matching classical baselines.
-
Noise Immunity in In-Context Tabular Learning: An Empirical Robustness Analysis of TabPFN's Attention Mechanisms
TabPFN maintains high ROC-AUC and structured attention under controlled additions of irrelevant features, nonlinear correlations, and mislabeled targets in binary classification.