DFPL introduces prototype-based disentanglement and alignment modules to preserve fine-grained consistency across heterogeneous modalities for better performance under missing data conditions.
MultiModalPFN: Extending Prior-Data Fitted Networks for Multimodal Tabular Learning
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
Recently, TabPFN has gained attention as a foundation model for tabular data. However, it struggles to integrate heterogeneous modalities such as images and text, which are common in domains like healthcare and marketing, thereby limiting its applicability. To address this, we present the Multi-Modal Prior-data Fitted Network (MMPFN), which extends TabPFN to handle tabular and non-tabular modalities in a unified manner. MMPFN comprises per-modality encoders, modality projectors, and pre-trained foundation models. The modality projectors serve as the critical bridge, transforming non-tabular embeddings into tabular-compatible tokens for unified processing. To this end, we introduce a multi-head gated MLP and a cross-attention pooler that extract richer context from non-tabular inputs while mitigates attention imbalance issue in multimodal learning. Extensive experiments on medical and general-purpose multimodal datasets demonstrate that MMPFN consistently outperforms competitive state-of-the-art methods and effectively exploits non-tabular modalities alongside tabular features. These results highlight the promise of extending prior-data fitted networks to the multimodal setting, offering a scalable and effective framework for heterogeneous data learning. The source code is available at https://github.com/too-z/MultiModalPFN.
citation-role summary
background 2
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1representative citing papers
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.
A tabular foundation model pipeline with ETF preprocessing transfers across 7 modalities on 95 datasets, matching lightweight tuned baselines on frozen features at much higher speed while providing calibration for deployment.
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.
citing papers explorer
-
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.
-
When Tabular Foundation Models Transfer Across Modalities: A Systematic Evaluation Across 95 Datasets, 7 Modalities, and Two Regimes
A tabular foundation model pipeline with ETF preprocessing transfers across 7 modalities on 95 datasets, matching lightweight tuned baselines on frozen features at much higher speed while providing calibration for deployment.
-
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.