# InfMasking: A Unified Variational Framework for Synergistic Multimodal Learning

**Authors:** Liangjian Wen, Qun Dai, Jiang Duan, Yong Dai, Jianzhuang Liu, Dongkai Wang, Jun Wang, Fuyuan Cao, Zenglin Xu, Zhao Kang  
**Lab:** Shanxi University · **Published:** 5 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.07702) · [PDF](https://arxiv.org/pdf/2611.07702) · [Code](https://github.com/brightest66/InfMasking) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.07702.html)

## Abstract

Multimodal models are expected to exploit synergistic information, that is, information available only when multiple modalities are observed together. In practice, however, a fusion module can fit the training objective by relying on a dominant modality or on information that modalities share, and the synergy between modalities is often left unused. We propose InfMasking, a unified multimodal learning framework based on Infinite Masking. Before fusion, InfMasking randomly masks the features of each modality; each sampled mask produces a different partial combination of cross-modal evidence and a fused representation of the corresponding modality interactions. All masked fused representations are required to remain consistent with a reference target: the unmasked fused view when training is unsupervised, and the class proxy of the task label when labels are available. Maintaining this consistency across diverse partial combinations discourages reliance on a dominant modality or on shared information alone, and drives the fusion module to learn cross-modal interaction patterns that remain meaningful under partial observations. Since the objective is an expectation over infinitely many masks, we model the masked fused representations as Gaussian and optimize closed-form variational bounds, whose population-moment gaps are controlled by the masking-induced covariance under this model. On the evaluated benchmarks, InfMasking improves predictive performance and yields higher mean PID estimates of task-label synergy in learned modality-specific representations, alongside higher InterSHAP interaction attribution in the trained predictors. Code is available at https://github.com/brightest66/InfMasking.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.