English
Related papers

Related papers: Fuse It More Deeply! A Variational Transformer wit…

200 papers

A key advance in learning generative models is the use of amortized inference distributions that are jointly trained with the models. We find that existing training objectives for variational autoencoders can lead to inaccurate amortized…

Machine Learning · Computer Science 2018-05-31 Shengjia Zhao , Jiaming Song , Stefano Ermon

Hyperspectral images capture rich spectral information that enables per-pixel material identification; however, spectral mixing often obscures pure material signatures. To address this challenge, we propose the Latent Dirichlet Transformer…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Giancarlo Giannetti , Faisal Z. Qureshi

In recent years, speech emotion recognition (SER) has been used in wide ranging applications, from healthcare to the commercial sector. In addition to signal processing approaches, methods for SER now also use deep learning techniques which…

Audio and Speech Processing · Electrical Eng. & Systems 2022-03-29 Sneha Das , Nicole Nadine Lønfeldt , Anne Katrine Pagsberg , Line H. Clemmensen

Latent confounders are a fundamental challenge for inferring causal effects from observational data. The instrumental variable (IV) approach is a practical way to address this challenge. Existing IV based estimators need a known IV or other…

Machine Learning · Computer Science 2024-12-09 Debo Cheng , Jiuyong Li , Lin Liu , Ziqi Xu , Weijia Zhang , Jixue Liu , Thuc Duy Le

Multimodal variational autoencoders have demonstrated their ability to learn the relationships between different modalities by mapping them into a latent representation. Their design and capacity to perform any-to-any conditional and…

Machine Learning · Computer Science 2025-02-04 Daniel Wesego , Pedram Rooshenas

Time series sequence prediction and modelling has proven to be a challenging endeavor in real world datasets. Two key issues are the multi-dimensionality of data and the interaction of independent dimensions forming a latent output signal,…

Machine Learning · Computer Science 2020-10-09 Jakob Aungiers

Predicting the impact of genomic and drug perturbations in cellular function is crucial for understanding gene functions and drug effects, ultimately leading to improved therapies. To this end, Causal Representation Learning (CRL)…

VAEs (Variational AutoEncoders) have proved to be powerful in the context of density modeling and have been used in a variety of contexts for creative purposes. In many settings, the data we model possesses continuous attributes that we…

Machine Learning · Computer Science 2017-07-18 Gaëtan Hadjeres , Frank Nielsen , François Pachet

Variational Autoencoders (VAEs) typically rely on a probabilistic decoder with a predefined likelihood, most commonly an isotropic Gaussian, to model the data conditional on latent variables. While convenient for optimization, this choice…

Machine Learning · Statistics 2025-04-29 Chen Xu , Qiang Wang , Lijun Sun

Large language models (LLMs) based on Transformer Decoders have become the preferred choice for conversational generative AI. Despite the overall superiority of the Decoder architecture, the gradually increasing Key-Value (KV) cache during…

Computation and Language · Computer Science 2025-07-16 Luohe Shi , Zuchao Li , Lefei Zhang , Guoming Liu , Baoyuan Qi , Hai Zhao

This paper proposes Dirichlet Variational Autoencoder (DirVAE) using a Dirichlet prior for a continuous latent variable that exhibits the characteristic of the categorical probabilities. To infer the parameters of DirVAE, we utilize the…

Machine Learning · Computer Science 2019-01-10 Weonyoung Joo , Wonsung Lee , Sungrae Park , Il-Chul Moon

With the introduction of the variational autoencoder (VAE), probabilistic latent variable models have received renewed attention as powerful generative models. However, their performance in terms of test likelihood and quality of generated…

Machine Learning · Statistics 2020-01-13 Lars Maaløe , Marco Fraccaro , Valentin Liévin , Ole Winther

Advances in neural variational inference have facilitated the learning of powerful directed graphical models with continuous latent variables, such as variational autoencoders. The hope is that such models will learn to represent rich,…

Computation and Language · Computer Science 2017-09-26 Iulian V. Serban , Alexander G. Ororbia , Joelle Pineau , Aaron Courville

Variational autoencoders (VAE) represent a popular, flexible form of deep generative model that can be stochastically fit to samples from a given random process using an information-theoretic variational bound on the true underlying…

Machine Learning · Computer Science 2019-10-08 Bin Dai , Yu Wang , John Aston , Gang Hua , David Wipf

Multimodal datasets, where measurements are obtained from multiple sensors, have become central to many scientific domains. In unsupervised settings, most representation learning methods focus on identifying shared latent structures, such…

Methodology · Statistics 2026-03-11 Shira Yoffe , Amit Moscovich , Ariel Jaffe

Diffusion autoencoders (DAs) are variants of diffusion generative models that use an input-dependent latent variable to capture representations alongside the diffusion process. These representations, to varying extents, can be used for…

Machine Learning · Computer Science 2025-06-03 Magdalena Proszewska , Nikolay Malkin , N. Siddharth

In disentangled representation learning, a model is asked to tease apart a dataset's underlying sources of variation and represent them independently of one another. Since the model is provided with no ground truth information about these…

Machine Learning · Computer Science 2023-10-24 Kyle Hsu , Will Dorrell , James C. R. Whittington , Jiajun Wu , Chelsea Finn

Disentangled and interpretable latent representations in generative models typically come at the cost of generation quality. The $\beta$-VAE framework introduces a hyperparameter $\beta$ to balance disentanglement and reconstruction…

Machine Learning · Computer Science 2025-07-10 Anshuk Uppal , Yuhta Takida , Chieh-Hsin Lai , Yuki Mitsufuji

We propose a Vision-Language Transformer (VLT) framework for referring segmentation to facilitate deep interactions among multi-modal information and enhance the holistic understanding to vision-language features. There are different ways…

Computer Vision and Pattern Recognition · Computer Science 2022-11-28 Henghui Ding , Chang Liu , Suchen Wang , Xudong Jiang

Variational autoencoder is a powerful deep generative model with variational inference. The practice of modeling latent variables in the VAE's original formulation as normal distributions with a diagonal covariance matrix limits the…

Machine Learning · Computer Science 2019-03-11 Sarin Chandy , Amin Rasekh