CoVAE: correlated multimodal generative modeling

• URL: http://arxiv.org/abs/2603.01965v1
• Date: Mon, 02 Mar 2026 15:14:59 GMT
• Title: CoVAE: correlated multimodal generative modeling
• Authors: Federico Caretti, Guido Sanguinetti,
• Abstract summary: We introduce Correlated Variational Autoencoders (CoVAE), a new generative architecture that captures the correlations between modalities.<n>We test CoVAE on a number of real and synthetic data sets demonstrating both accurate cross-modal reconstruction and effective quantification of the associated uncertainties.
• Score: 1.9336815376402718
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal Variational Autoencoders have emerged as a popular tool to extract effective representations from rich multimodal data. However, such models rely on fusion strategies in latent space that destroy the joint statistical structure of the multimodal data, with profound implications for generation and uncertainty quantification. In this work, we introduce Correlated Variational Autoencoders (CoVAE), a new generative architecture that captures the correlations between modalities. We test CoVAE on a number of real and synthetic data sets demonstrating both accurate cross-modal reconstruction and effective quantification of the associated uncertainties.

Related papers

• Cross-Modal Alignment via Variational Copula Modelling [54.25504956780864]
  It is essential to develop multimodal learning methods to aggregate various information from multiple modalities.<n>Existing methods mainly rely on concatenation or the Kronecker product, oversimplifying the interaction structure between modalities.<n>We propose a novel copula-driven multimodal learning framework, which focuses on learning the joint distribution of various modalities.
  arXiv  Detail & Related papers  (2025-11-05T05:28:28Z)
• NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching [64.10695425442164]
  We introduce NExT-OMNI, an open-source omnimodal foundation model that achieves unified modeling through discrete flow paradigms.<n>Trained on large-scale interleaved text, image, video, and audio data, NExT-OMNI delivers competitive performance on multimodal generation and understanding benchmarks.<n>To advance further research, we release training details, data protocols, and open-source both the code and model checkpoints.
  arXiv  Detail & Related papers  (2025-10-15T16:25:18Z)
• Disentanglement of Variations with Multimodal Generative Modeling [18.610989859219895]
  We propose Information-disentangled Multimodal VAE (IDMVAE) to address the issue of learning robust representations of multimodal data.<n>Compared to existing approaches, IDMVAE shows a clean separation between shared and private information, demonstrating superior generation quality and semantic coherence on challenging datasets.
  arXiv  Detail & Related papers  (2025-09-28T00:54:39Z)
• Bridging the inference gap in Mutimodal Variational Autoencoders [6.246098300155483]
  Multimodal Variational Autoencoders offer versatile and scalable methods for generating unobserved modalities from observed ones.<n>Recent models using mixturesof-experts aggregation suffer from theoretically grounded limitations that restrict their generation quality on complex datasets.<n>We propose a novel interpretable model able to learn both joint and conditional distributions without introducing mixture aggregation.
  arXiv  Detail & Related papers  (2025-02-06T10:43:55Z)
• A Markov Random Field Multi-Modal Variational AutoEncoder [1.2233362977312945]
  This work introduces a novel multimodal VAE that incorporates a Markov Random Field (MRF) into both the prior and posterior distributions.<n>Our approach is specifically designed to model and leverage the intricacies of these relationships, enabling a more faithful representation of multimodal data.
  arXiv  Detail & Related papers  (2024-08-18T19:27:30Z)
• Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning [80.44084021062105]
  We propose a novel latent partial causal model for multimodal data, featuring two latent coupled variables, connected by an undirected edge, to represent the transfer of knowledge across modalities.<n>Under specific statistical assumptions, we establish an identifiability result, demonstrating that representations learned by multimodal contrastive learning correspond to the latent coupled variables up to a trivial transformation.<n>Experiments on a pre-trained CLIP model embodies disentangled representations, enabling few-shot learning and improving domain generalization across diverse real-world datasets.
  arXiv  Detail & Related papers  (2024-02-09T07:18:06Z)
• Learning multi-modal generative models with permutation-invariant encoders and tighter variational objectives [5.549794481031468]
  Devising deep latent variable models for multi-modal data has been a long-standing theme in machine learning research. In this work, we consider a variational objective that can tightly approximate the data log-likelihood. We develop more flexible aggregation schemes that avoid the inductive biases in PoE or MoE approaches.
  arXiv  Detail & Related papers  (2023-09-01T10:32:21Z)
• Score-Based Multimodal Autoencoder [0.9208007322096533]
  Multimodal Variational Autoencoders (VAEs) facilitate the construction of a tractable posterior within the latent space given multiple modalities.<n>Previous studies have shown that as the number of modalities increases, the generative quality of each modality declines.<n>In this study, we explore an alternative approach to enhance the generative performance of multimodal VAEs by jointly modeling the latent space of independently trained unimodal VAEs.
  arXiv  Detail & Related papers  (2023-05-25T04:43:47Z)
• Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework [89.8609061423685]
  We propose an information-theoretic approach to quantify the degree of redundancy, uniqueness, and synergy relating input modalities with an output task. To validate PID estimation, we conduct extensive experiments on both synthetic datasets where the PID is known and on large-scale multimodal benchmarks. We demonstrate their usefulness in (1) quantifying interactions within multimodal datasets, (2) quantifying interactions captured by multimodal models, (3) principled approaches for model selection, and (4) three real-world case studies.
  arXiv  Detail & Related papers  (2023-02-23T18:59:05Z)
• Bi-Bimodal Modality Fusion for Correlation-Controlled Multimodal Sentiment Analysis [96.46952672172021]
  Bi-Bimodal Fusion Network (BBFN) is a novel end-to-end network that performs fusion on pairwise modality representations. Model takes two bimodal pairs as input due to known information imbalance among modalities.
  arXiv  Detail & Related papers  (2021-07-28T23:33:42Z)
• Improving the Reconstruction of Disentangled Representation Learners via Multi-Stage Modeling [54.94763543386523]
  Current autoencoder-based disentangled representation learning methods achieve disentanglement by penalizing the ( aggregate) posterior to encourage statistical independence of the latent factors. We present a novel multi-stage modeling approach where the disentangled factors are first learned using a penalty-based disentangled representation learning method. Then, the low-quality reconstruction is improved with another deep generative model that is trained to model the missing correlated latent variables.
  arXiv  Detail & Related papers  (2020-10-25T18:51:15Z)
• Relating by Contrasting: A Data-efficient Framework for Multimodal Generative Models [86.9292779620645]
  We develop a contrastive framework for generative model learning, allowing us to train the model not just by the commonality between modalities, but by the distinction between "related" and "unrelated" multimodal data. Under our proposed framework, the generative model can accurately identify related samples from unrelated ones, making it possible to make use of the plentiful unlabeled, unpaired multimodal data.
  arXiv  Detail & Related papers  (2020-07-02T15:08:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.