← Back to all news
arXiv AI By Kai Chen, Josephine Lamp, Somesh Jha, Tianhao Wang

Differentially Private Paired Table-Image Multimodal Synthesis

Read the original on arXiv AI →

The paper introduces DP-TabImage, a framework that synthesizes paired table–image data while preserving differential privacy. It factorizes the joint distribution into a private probabilistic graphical model for tables and a table‑conditioned diffusion model for images, using DP‑SGD and a privacy‑preserving warm‑up strategy. Experiments on three real datasets demonstrate a strong balance between table fidelity, image fidelity, and cross‑modal alignment.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Aug 11

Multimodal Federated Learning under Dual-Axis Modality Missingness

arXiv:2608. 09240v1 Announce Type: cross Abstract: Multimodal federated learning (FL) supports collaborative modeling in privacy-sensitive health-sensing and medical settings, but realistic deployments often exhibit dual-axis modality missingness: clients have different modality sets, and individual samples may contain only subsets of the modalities available locally.

By Adiba Orzikulova, Jaehyun Kwak, Jaemin Shin, Yunqi Guo, Xiaomin Ouyang, Guoliang Xing, Steven Euijong Whang, Sung-Ju Lee
multimodalsafety
More like this →
arXiv AI
Sep 25

M$^2$PFN: End-to-End Disentangled Alignment for Generalizable Multimodal In-Context Learning in Alzheimer's Disease

M$^2$PFN is an end‑to‑end multimodal framework that extends the TabPFN in‑context learning engine to Alzheimer’s disease diagnosis by aligning 3D‑MRI and tabular features in a shared subspace. It performs differentiable inference through TabPFN’s transformer, back‑propagates gradients into the encoders, and incorporates a frozen tabular‑only prediction via a gated shortcut. On the ADNI cohort it achieves 65.55 % macro‑F1 and 82.21 % macro‑AUC, surpassing unimodal and multimodal baselines, and it generalizes to external cohorts without retraining.

By Lujia Zhong, Shuo Huang, Jianwei Zhang, Xinyu Nie, Yonggang Shi
llmsmultimodalsafety
More like this →