Tabular foundation models excel on tiny- to medium-sized IID data but are outperformed by traditional tree-based and deep learning models on non-IID, large, and high-dimensional datasets, based on evaluations across 11 models and 142 datasets in the new BeyondArena benchmark.
Time: Tabpfn-integrated multimodal engine for robust tabular-image learning.arXiv preprint arXiv:2506.00813
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 4
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
MulTaBench is a new collection of 40 image-tabular and text-tabular datasets designed to test target-aware representation tuning in multimodal tabular models.
DFPL introduces prototype-based disentanglement and alignment modules to preserve fine-grained consistency across heterogeneous modalities for better performance under missing data conditions.
TabPFN-3 scales tabular foundation models to 1M rows with synthetic pretraining, test-time compute, and benchmark-leading performance on tabular, relational, and tabular-text tasks while being up to 20x faster than TabPFN-2.5.
MultiModalPFN extends TabPFN with modality projectors, a multi-head gated MLP, and cross-attention pooler to unify tabular and non-tabular inputs, outperforming prior methods on medical and general multimodal datasets.
TabPFN-2.5 scales tabular foundation models to 20x larger datasets, outperforms tuned tree models on TabArena, achieves near-perfect win rates against default XGBoost, and adds a distillation engine for fast production deployment.
TI-Adapter applies embedding-level and bottleneck adapters to achieve competitive or better performance than full fine-tuning on 20 tabular-image datasets while training far fewer parameters.
CoMET achieves strong multimodal classification performance by composing frozen modality encoders, PCA compression, and tabular foundation models without any training, reaching state-of-the-art on diverse benchmarks including large-scale hierarchical tasks.
TCD-derived MOCAIP and HRV features predict chronological age in healthy adults (MAE ~3.7 y), and diseased cohorts show larger errors that the authors interpret as accelerated cerebrovascular aging.
citing papers explorer
-
Beyond IID: How General Are Tabular Foundation Models, Really?
Tabular foundation models excel on tiny- to medium-sized IID data but are outperformed by traditional tree-based and deep learning models on non-IID, large, and high-dimensional datasets, based on evaluations across 11 models and 142 datasets in the new BeyondArena benchmark.
-
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.
-
Disentangled Fine-Grained Prototype Learning for Incomplete Image-Tabular Classification
DFPL introduces prototype-based disentanglement and alignment modules to preserve fine-grained consistency across heterogeneous modalities for better performance under missing data conditions.
-
TabPFN-3: Technical Report
TabPFN-3 scales tabular foundation models to 1M rows with synthetic pretraining, test-time compute, and benchmark-leading performance on tabular, relational, and tabular-text tasks while being up to 20x faster than TabPFN-2.5.
-
MultiModalPFN: Extending Prior-Data Fitted Networks for Multimodal Tabular Learning
MultiModalPFN extends TabPFN with modality projectors, a multi-head gated MLP, and cross-attention pooler to unify tabular and non-tabular inputs, outperforming prior methods on medical and general multimodal datasets.
-
TabPFN-2.5: Advancing the State of the Art in Tabular Foundation Models
TabPFN-2.5 scales tabular foundation models to 20x larger datasets, outperforms tuned tree models on TabArena, achieves near-perfect win rates against default XGBoost, and adds a distillation engine for fast production deployment.
-
Parameter-Efficient Adapter Tuning for Tabular-Image Multimodal Learning
TI-Adapter applies embedding-level and bottleneck adapters to achieve competitive or better performance than full fine-tuning on 20 tabular-image datasets while training far fewer parameters.
-
Modular Multimodal Classification Without Fine-Tuning: A Simple Compositional Approach
CoMET achieves strong multimodal classification performance by composing frozen modality encoders, PCA compression, and tabular foundation models without any training, reaching state-of-the-art on diverse benchmarks including large-scale hierarchical tasks.
-
Brain Vascular Age Prediction Using Cerebral Blood Flow Velocity and Machine Learning Algorithms
TCD-derived MOCAIP and HRV features predict chronological age in healthy adults (MAE ~3.7 y), and diseased cohorts show larger errors that the authors interpret as accelerated cerebrovascular aging.