paper-with-me

Papers

How Far Are We from Predicting Missing Modalities with Foundation Models?

2025-06-04 · Guanzhou Ke, Yi Xie, Xiaoli Wang, Guoqing Chao, Bo wang, Shengfeng He

Multimodal foundation models have demonstrated impressive capabilities across diverse tasks. However, their potential as plug-and-play solutions for missing modality prediction remains underexplored. To investigate this, we categorize existing approaches into three representative paradigms, encompassing a total of 42 model variants, and conduct a comprehensive evaluation in terms of prediction accuracy and adaptability to downstream tasks. Our analysis reveals that current foundation models often fall short in two critical aspects: (i) fine-grained semantic extraction from the available modalities, and (ii) robust validation of generated modalities. These limitations lead to suboptimal and, at times, misaligned predictions. To address these challenges, we propose an agentic framework tailored for missing modality prediction. This framework dynamically formulates modality-aware mining strategies based on the input context, facilitating the extraction of richer and more discriminative semantic features. In addition, we introduce a \textit{self-refinement mechanism}, which iteratively verifies and enhances the quality of generated modalities through internal feedback. Experimental results show that our method reduces FID for missing image prediction by at least 14% and MER for missing text prediction by at least 10% compared to baselines.

📄 PDF Abstract BibTeX arXiv:2506.03530

Code (1)

guanzhou-ke/afm2 공식 구현

Tasks

Prediction

Similar Papers 제목 키워드 기반

Toward Robust Multimodal Learning using Multimodal Foundational Models

2024-01-20 · Xianbing Zhao, Soujanya Poria, Xuejiao Li, Yixin Chen 외

Existing multimodal sentiment analysis tasks are highly rely on the assumption that the training and test sets are complete multimodal data, while this assumption can be difficult to hold: the multimodal data are often i…

Multimodal Sentiment AnalysisSentiment Analysis

Accommodating Missing Modalities in Time-Continuous Multimodal Emotion Recognition

2023-11-16 · Juan Vazquez-Rodriguez, Grégoire Lefebvre, Julien Cumin, James L. Crowley

Decades of research indicate that emotion recognition is more effective when drawing information from multiple modalities. But what if some modalities are sometimes missing? To address this problem, we propose a novel Tr…

Emotion RecognitionMultimodal Emotion Recognition

Multi-modal Data Binding for Survival Analysis Modeling with Incomplete Data and Annotations

2024-07-25 · Linhao Qu, Dan Huang, Shaoting Zhang, Xiaosong Wang

Survival analysis stands as a pivotal process in cancer treatment research, crucial for predicting patient survival rates accurately. Recent advancements in data collection techniques have paved the way for enhancing sur…

Survival Analysis

A Contrastive Variational AutoEncoder for NSCLC Survival Prediction with Missing Modalities

2026-02-19 · Michele Zanitti, Vanja Miskovic, Francesco Trovò, Alessandra Laura Giulia Pedrocchi 외 arxiv

Predicting survival outcomes for non-small cell lung cancer (NSCLC) patients is challenging due to the different individual prognostic features. This task can benefit from the integration of whole-slide images, bulk tran…

TRACE: A Temporal Conditional Estimation for Multimodal Time Series Foundation Models

2026-06-04 · Ziwen Kan, Yishuo Chen, Kecheng Li, Andrew Wen 외 arxiv

Time series foundation models (TS-FMs) aim to learn generalizable temporal representations that can be adapted to a wide range of downstream tasks. In real-world multimodal settings, time series are frequently affected b…

Multimodal Sentiment Analysis