Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

18365472 · Jun 202019922001200920182026
48 results for multimodal autoencoder

Enhances multimodal generation with Normalizing Flows and correlation analysis.

problem Generating coherent cross-modal data from multiple sources.
method Uses Deep Canonical Correlation Analysis for shared information, Normalizing Flows for diversity, and Product of Experts for scalability.
result Improves likelihood, diversity, and coherence in conditional generation.

New method disentangles shared and private latent factors in multimodal data.

problem Challenges in disentangling shared and private latent factors in multimodal data.
method Proposes a modification to existing multimodal Variational Autoencoders (MMVAE) to better handle modality-specific variation.
result Demonstrates improved robustness of modified MMVAE to modality-specific variation.

Integrates MRF into multimodal VAE for better complex intermodal interactions.

problem Lack of effective modeling of complex intermodal interactions in multimodal VAEs.
method Incorporates Markov Random Field into prior and posterior distributions of multimodal VAE.
result Demonstrates superior performance in managing complex intermodal dependencies.

daep learns from irregular, multimodal astronomical data.

problem Learning from irregular, multimodal astronomical sequences.
method Diffusion Autoencoder with Perceivers (daep) tokenizes, compresses, and reconstructs data.
result daep outperforms VAE and maep baselines in reconstruction and fine-scale structure preservation.

InVA models image outcomes from multiple modalities, outperforming standard VAEs.

problem Understanding relationships across multiple imaging modalities in neuroimaging.
method Integrative Variational Autoencoder (InVA) framework for image-on-image regression.
result InVA accurately predicts PET scans from structural MRI, outperforming conventional models.

New model improves multimodal autoencoders by learning joint and conditional distributions.

problem Limitations in recent multimodal autoencoders restrict their quality on complex datasets.
method Proposes a multistage training process with variational inference and Normalizing Flows, leveraging shared modality information.
result Achieves state-of-the-art results on benchmark datasets.

Anomaly detection method using multimodal autoencoder and sparse optimization.

problem Interpreting anomalies detected by deep learning models in complex ICT systems.
method Proposes a sparse optimization algorithm to estimate contributing dimensions of anomalies detected by multimodal autoencoders.
result Superiority of the proposed estimation algorithm in specifying contributing dimensions of anomalous data and detecting anomalies in cross-domain data.

PIMA autoencoders discover shared features in multimodal scientific data.

problem Discovering shared information in high-throughput scientific datasets.
method Physics-informed multimodal autoencoders (PIMA) with Gaussian mixture prior and product of experts formulation.
result Accurate cross-modal inference between images and mechanical stress-strain response in lattice metamaterials.

Evidential Softmax preserves multimodality in sparse probability distributions for generative models.

problem Sparse probability distributions in deep generative models make exact marginalization computationally intractable.
method Introduce ev-softmax, a sparse normalization function that preserves multimodality and can be trained with probabilistic loss functions.
result ev-softmax outperforms existing techniques in distributional accuracy and dimensionality reduction.

VAEs struggle with surjective multimodal data, especially class labels describing images.

problem VAEs struggle to capture variability in surjective multimodal data.
method Theoretical and empirical demonstration of VAEs with a mixture of experts posterior.
result VAEs with a mixture of experts posterior can disregard variation in surjective multimodal data.

LRMM learns to recommend with missing modalities, improving robustness to data sparsity and cold-start issues.

problem Learning to recommend with missing modalities and cold-start problems.
method LRMM uses modality dropout and multimodal sequential autoencoder to learn multimodal representations and impute missing modalities.
result LRMM achieves state-of-the-art performance on rating prediction tasks and is more robust to data sparsity and cold-start issues.

Bayesian model updating uses VAEs to approximate likelihood with small data.

problem Approximating likelihood for small data sets in structural analysis.
method Uses multimodal VAEs to approximate likelihood, suitable for high-dimensional correlated observations.
result Demonstrates computational efficiency and accuracy compared to original VAE approach.

Framework detects anomalies in industrial processes using deep learning.

problem Detect anomalies in complex industrial processes.
method Causal-based framework with unsupervised deep learning.
result Successfully validated abstract contexts of blast furnace assets.

In this paper, we describe the "implicit autoencoder" (IAE), a generative autoencoder in which both the generative path and the recognition path are parametrized by implicit distributions. We use two generative adversarial networks to define the reconstruction and the regularization cost functions of the implicit autoe…

2018-05-24abs ↗pdf ↗

The paper introduces multimodal generative models to improve data marginal likelihood.

problem Improving data marginal likelihood in multimodal settings.
method Derives variational bounds on the evidence for multimodal deep generative models, generalizes objectives for different model types, and benchmarks across various datasets.
result Multimodal VAEs excel in image, label, and text datasets with and without weak supervision.

Push-forward models struggle to fit multimodal distributions due to high Lipschitz constants.

problem Expressivity of push-forward generative models in fitting multimodal distributions.
method Analyzing the Lipschitz constant and its relation to the total variation distance and Kullback-Leibler divergence.
result Push-forward models require high Lipschitz constants to approximate multimodal distributions, leading to a trade-off between expressivity and stability.

New method learns complex, multimodal distributions in ADVI.

problem Learning unimodal approximate posteriors limits ADVI's ability to capture complex data structures.
method Use stratified sampling to allow mixture distributions as approximate posteriors, derive a tighter evidence lower bound.
result SIWAE objective allows ADVI to learn more complex, multimodal distributions, improving accuracy and calibration.

Novel SVAE learns interpretable discrete data representations from deep learning.

problem Learning interpretable discrete data representations from deep learning.
method Structured variational autoencoder (SVAE) with novel optimization algorithms.
result First competitive comparisons with state-of-the-art time series models.

We investigate deep generative models that can exchange multiple modalities bi-directionally, e.g., generating images from corresponding texts and vice versa. Recently, some studies handle multiple modalities on deep generative models, such as variational autoencoders (VAEs). However, these models typically assume that…

2016-11-07abs ↗pdf ↗

In this paper, we address the problem of conditional modality learning, whereby one is interested in generating one modality given the other. While it is straightforward to learn a joint distribution over multiple modalities using a deep multimodal architecture, we observe that such models aren't very effective at cond…

2016-03-06abs ↗pdf ↗

This paper introduces a spline-based method for nonparametric ADVI that handles complex posterior distributions.

problem Learning complex posterior distributions with skewness, multimodality, and bounded support.
method Develops a spline-based nonparametric approximation approach for ADVI.
result Establishes the asymptotic consistency of the derived lower bound for importance weighted autoencoder.

Generative data augmentation improves unsupervised anomaly detection.

problem Improving anomaly detection performance in unsupervised settings.
method Oversampling infrequent normal samples using adversarial autoencoder (AAE) to transform high-dimensional multimodal data into low-dimensional unimodal latent distributions.
result Consistent improvements in anomaly detection across various real-world datasets.

Multiple modalities often co-occur when describing natural phenomena. Learning a joint representation of these modalities should yield deeper and more useful representations. Previous generative approaches to multi-modal input either do not learn a joint distribution or require additional computation to handle missing …

2018-02-14abs ↗pdf ↗

Improved IFA with Generative Adversarial Networks for high-dimensional latent variables.

problem Limited expressiveness of traditional VAEs in high-dimensional latent variable modeling.
method Introducing Adversarial Variational Bayes (AVB) and Importance-weighted Adversarial Variational Bayes (IWAVB) algorithms.
result IWAVB demonstrated superior expressiveness and higher likelihood compared to IWAE.

A VAE model predicts material properties and microstructures.

problem Building forward and inverse structure-property linkages in materials science.
method Combines VAE with regression, using a two-level prior and multi-modal Gaussian mixture.
result The model achieves accurate forward and inverse predictions of material properties and microstructures.

A framework for disentangling class-related and class-independent factors in data.

problem Learning disentangled representations in variational autoencoders.
method Attention mechanism in latent space, mixture models, Bhattacharyya coefficient, semi-supervised training.
result Disentangles class-related and class-independent factors of variation.

Normalizing flows and autoregressive models have been successfully combined to produce state-of-the-art results in density estimation, via Masked Autoregressive Flows (MAF), and to accelerate state-of-the-art WaveNet-based speech synthesis to 20x faster than real-time, via Inverse Autoregressive Flows (IAF). We unify a…

2018-04-03abs ↗pdf ↗

Predicts whether an image is an abstraction of text or vice versa.

problem Understanding semantic cross-modal relations between images and text.
method Introduces a new metric (ABS) and a deep learning autoencoder approach to predict it.
result Demonstrates feasibility of predicting the relative abstractness level of image-text pairs.

TCT learns multimodal sequence representations by translating from related sequences.

problem Challenges in learning semantic representations from multimodalities.
method Transformer based Cross-modal Translator (TCT) combined with Multimodal Transformer Network (MTN).
result Proposed method achieves new state-of-the-art performance on video-grounded dialogue.

Paper proposes RMFN for multimodal language analysis.

problem Modeling interactions between language, visual, and acoustic modalities.
method Recurrent Multistage Fusion Network (RMFN) decomposes fusion into stages focusing on subsets of multimodal signals.
result RMFN achieves state-of-the-art performance across multimodal sentiment analysis, emotion recognition, and speaker traits recognition datasets.

FMT model improves multimodal sequential learning across language, vision, and acoustic data.

problem Modeling spatio-temporal dynamics across multiple modalities.
method Factorized Multimodal Transformer (FMT) that models intramodal and intermodal dynamics in a factorized manner.
result FMT outperforms existing models on 3 datasets and 21 labels, setting new state of the art.

VSCOUT detects anomalies in high-dimensional data using a hybrid VAE approach.

problem Challenges in classical SPC for high-dimensional, non-Gaussian data.
method Hybrid VAE architecture with ARD prior, ensemble filtering, and changepoint detection.
result VSCOUT achieves superior sensitivity to special-cause structure and controlled false alarms.