Metraipolis › archive › dc_4107ef8bcf24
M$^2$PFN: End-to-End Disentangled Alignment for Generalizable Multimodal In-Context Learning in Alzheimer's Disease — arXiv:2609.28836
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.28836
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T04:27:09.222Z
- SHA-256 of the archived text
bc6fe0dd7077f5a748f440db16d7bbd1277eb606615cde4e3774c41bbb56143c- Stable URL of this page
https://metraipolis.com/documento/dc_4107ef8bcf24
How to cite
M$^2$PFN: End-to-End Disentangled Alignment for Generalizable Multimodal In-Context Learning in Alzheimer's Disease — arXiv:2609.28836 — arXiv (en), https://arxiv.org/abs/2609.28836 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4107ef8bcf24 (Metraipolis archive dc_4107ef8bcf24, sha256 bc6fe0dd7077f5a748f440db16d7bbd1277eb606615cde4e3774c41bbb56143c)
BibTeX
@misc{dc4107ef8bcf24,
title = {M$^2$PFN: End-to-End Disentangled Alignment for Generalizable Multimodal In-Context Learning in Alzheimer's Disease — arXiv:2609.28836},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.28836},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4107ef8bcf24; sha256 bc6fe0dd7077f5a748f440db16d7bbd1277eb606615cde4e3774c41bbb56143c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28836. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
While various multimodal methods combining imaging and tabular data for Alzheimer's disease (AD) diagnosis were proposed, they are often limited in generalization across cohorts. In-context learning (ICL) has demonstrated excellent generalization performances and high flexibility in foundational tabular models such as TabPFN. To extend TabPFN's ICL to multimodal AD analysis, the main obstacle is that TabPFN is meta-trained on synthetic tabular priors that do not naturally match the statistical structure of image-derived features. We propose M$^2$PFN, an end-to-end framework that turns this tabular foundation model into a multimodal AD predictor. M$^2$PFN (i) performs differentiable inference through TabPFN's transformer, back-propagating task gradients into 3D-MRI and tabular encoders; (ii) aligns the two modalities into a shared subspace, via disentanglement and a contrastive objective, matched to the ICL engine's prior; and (iii) folds in a frozen tabular-only prediction through a learnable gated shortcut. Because the ICL engine stays frozen, its in-context mechanism is preserved for test-time generalization, while end-to-end training shapes the encoders into features it can exploit. On ADNI ($n=2240$, three-class CN/MCI/AD), M$^2$PFN attains $65.55\%$ macro-F1 and $82.21\%$ macro-AUC, surpassing a comprehensive set of unimodal and multimodal baselines. By swapping only the head for a TabPFN regressor, the same architecture regresses baseline MMSE on a $1250$-subject sub-cohort to test MAE $1.743$, outperforming every multimodal baseline. On two external cohorts (OASIS-3 and SCAN) with no retraining, M$^2$PFN achieves the best AUC and the lowest MMSE MAE across all baselines, and transfers even when the cognitive instrument changes. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.28836 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T03:50:57.963Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).