Related papers: Multimodal Datasets with Controllable Mutual Infor…

We introduce an efficient computational framework for hashing data belonging to multiple modalities into a single representation space where they become mutually comparable. The proposed approach is based on a novel coupled siamese neural…

Mutual Information (MI) is an useful tool for the recognition of mutual dependence berween data sets. Differen methods for the estimation of MI have been developed when both data sets are discrete or when both data sets are continuous. The…

Leveraging information across diverse modalities is known to enhance performance on multimodal segmentation tasks. However, effectively fusing information from different modalities remains challenging due to the unique characteristics of…

Modern applications increasingly involve many heterogeneous input streams, such as clinical sensors, wearable device data, imaging, and text, each with distinct measurement models, sampling rates, and noise characteristics. We define this…

Motivation: Clustering is a frequently used concept in variety of bioinformatical applications. We present a new method for hierarchical clustering of data called mutual information clustering (MIC) algorithm. It uses mutual information…

While multimodal fusion has been extensively studied in Multimodal Sentiment Analysis (MSA), the role of fusion depth and multimodal capacity allocation remains underexplored. In this work, we position fusion depth, scalability, and…

Multi-modal learning is a fast growing area in artificial intelligence. It tries to help machines understand complex things by combining information from different sources, like images, text, and audio. By using the strengths of each…

Multimodal machine learning has achieved remarkable progress in many scenarios, but its reliability is undermined by varying sample quality. This paper finds that existing reliable multimodal classification methods not only fail to provide…

With the success of self-supervised representations, researchers seek a better understanding of the information encapsulated within a representation. Among various interpretability methods, we focus on classification-based linear probing.…

Estimation of mutual information between (multidimensional) real-valued variables is used in analysis of complex systems, biological systems, and recently also quantum systems. This estimation is a hard problem, and universally good…

Multimodal sentiment analysis is an active research area that combines multiple data modalities, e.g., text, image and audio, to analyze human emotions and benefits a variety of applications. Existing multimodal sentiment analysis methods…

Realistic, large-scale, and well-labeled cybersecurity datasets are essential for training and evaluating Intrusion Detection Systems (IDS). However, they remain difficult to obtain due to privacy constraints, data sensitivity, and the cost…

As generative AI systems are increasingly deployed in real-world applications, regulating multiple dimensions of model behavior has become essential. We focus on test-time filtering: a lightweight mechanism for behavior control that…

Although large language models (LLMs) have demonstrated remarkable capabilities in recent years, the potential of information theory (IT) to enhance LLM development remains underexplored. This paper introduces the information theoretic…

We introduce Platform for Situated Intelligence, an open-source framework created to support the rapid development and study of multimodal, integrative-AI systems. The framework provides infrastructure for sensing, fusing, and making…

We propose learning discrete structured representations from unlabeled data by maximizing the mutual information between a structured latent variable and a target variable. Calculating mutual information is intractable in this setting. Our…

Estimating mutual information (MI) from samples is a fundamental problem in statistics, machine learning, and data analysis. Recently it was shown that a popular class of non-parametric MI estimators perform very poorly for strongly…

This paper demonstrates dynamic hyper-parameter setting, for deep neural network training, using Mutual Information (MI). The specific hyper-parameter studied in this paper is the learning rate. MI between the output layer and true outcomes…

Multimodal emotion recognition from speech is an important area in affective computing. Fusing multiple data modalities and learning representations with limited amounts of labeled data is a challenging task. In this paper, we explore the…

Recommender systems traditionally represent items using unique identifiers (ItemIDs), but this approach struggles with large, dynamic item corpora and sparse long-tail data, limiting scalability and generalization. Semantic IDs, derived…