English
Related papers

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

200 papers

Variational Autoencoders (VAEs) are well-established as a principled approach to probabilistic unsupervised learning with neural networks. Typically, an encoder network defines the parameters of a Gaussian distributed latent space from…

Machine Learning · Computer Science 2025-05-16 Alan Jeffares , Liyuan Liu

In this paper, we show how Transformers can be interpreted as dense Expectation-Maximization algorithms performed on Bayesian Nets. Based on the above interpretation, we propose a new model design paradigm, namely Vertical LoRA (VLoRA),…

Artificial Intelligence · Computer Science 2024-06-14 Zhuolin Fu

Recent vision-language-action (VLA) models have significantly advanced robotic manipulation by unifying perception, reasoning, and control. To achieve such integration, recent studies adopt a predictive paradigm that models future visual…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Yijie Zhu , Jie He , Rui Shao , Kaishen Yuan , Tao Tan , Xiaochen Yuan , Zitong Yu

Despite the recent advances in applying pre-trained language models to generate high-quality texts, generating long passages that maintain long-range coherence is yet challenging for these models. In this paper, we propose DiscoDVT, a…

Computation and Language · Computer Science 2021-10-13 Haozhe Ji , Minlie Huang

Generative modeling aims to generate new data samples that resemble a given dataset, with diffusion models recently becoming the most popular generative model. One of the main challenges of diffusion models is solving the problem in the…

Numerical Analysis · Mathematics 2025-10-08 Wonjun Lee , Riley C. W. O'Neill , Dongmian Zou , Jeff Calder , Gilad Lerman

Latent variable models like the Variational Auto-Encoder (VAE) are commonly used to learn representations of images. However, for downstream tasks like semantic classification, the representations learned by VAE are less competitive than…

Machine Learning · Statistics 2022-05-31 Mingtian Zhang , Tim Z. Xiao , Brooks Paige , David Barber

Recent video generation models largely rely on video autoencoders that compress pixel-space videos into latent representations. However, existing video autoencoders suffer from three major limitations: (1) fixed-rate compression that wastes…

Computer Vision and Pattern Recognition · Computer Science 2026-02-05 Yao Teng , Minxuan Lin , Xian Liu , Shuai Wang , Xiao Yang , Xihui Liu

Variational autoencoders learn unsupervised data representations, but these models frequently converge to minima that fail to preserve meaningful semantic information. For example, variational autoencoders with autoregressive decoders often…

Machine Learning · Computer Science 2019-05-21 Bryan Seybold , Emily Fertig , Alex Alemi , Ian Fischer

Vision-Language-Action (VLA) models enable generalist robotic manipulation but suffer from high inference latency. This bottleneck stems from the massive number of visual tokens processed by large language backbones. Existing methods either…

Robotics · Computer Science 2026-03-12 Yuquan Li , Lianjie Ma , Han Ding , Lijun Zhu

Latent variables (LVs) play a crucial role in encoder-decoder models by enabling effective data compression, prediction, and generation. Although their theoretical properties, such as generalization, have been extensively studied in…

Machine Learning · Statistics 2025-11-07 Futoshi Futami , Masahiro Fujisawa

Variational Autoencoders are powerful models for unsupervised learning. However deep models with several layers of dependent stochastic variables are difficult to train which limits the improvements obtained using these highly expressive…

Machine Learning · Statistics 2016-05-30 Casper Kaae Sønderby , Tapani Raiko , Lars Maaløe , Søren Kaae Sønderby , Ole Winther

Recent advances in training-free video editing have enabled lightweight and precise cross-frame generation by leveraging pre-trained text-to-image diffusion models. However, existing methods often rely on heuristic frame selection to…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Zhangkai Wu , Xuhui Fan , Zhongyuan Xie , Kaize Shi , Longbing Cao

As one of the most popular generative models, Variational Autoencoder (VAE) approximates the posterior of latent variables based on amortized variational inference. However, when the decoder network is sufficiently expressive, VAE may lead…

Machine Learning · Computer Science 2021-10-26 Dazhong Shen , Chuan Qin , Chao Wang , Hengshu Zhu , Enhong Chen , Hui Xiong

The Variational Autoencoder (VAE) is a popular and powerful model applied to text modelling to generate diverse sentences. However, an issue known as posterior collapse (or KL loss vanishing) happens when the VAE is used in text modelling,…

Computation and Language · Computer Science 2020-11-04 Ruizhe Li , Xiao Li , Guanyi Chen , Chenghua Lin

The framework of variational autoencoders allows us to efficiently learn deep latent-variable models, such that the model's marginal distribution over observed variables fits the data. Often, we're interested in going a step further, and…

Machine Learning · Statistics 2020-12-22 Ilyes Khemakhem , Diederik P. Kingma , Ricardo Pio Monti , Aapo Hyvärinen

We propose a cross-domain latent modulation mechanism within a variational autoencoders (VAE) framework to enable improved transfer learning. Our key idea is to procure deep representations from one data domain and use it as perturbation to…

Machine Learning · Computer Science 2020-12-23 Jinyong Hou , Jeremiah D. Deng , Stephen Cranefield , Xuejie Ding

Latent variable models such as the Variational Auto-Encoder (VAE) have become a go-to tool for analyzing biological data, especially in the field of single-cell genomics. One remaining challenge is the interpretability of latent variables…

Genomics · Quantitative Biology 2023-02-20 Romain Lopez , Nataša Tagasovska , Stephen Ra , Kyunghyn Cho , Jonathan K. Pritchard , Aviv Regev

We introduce a novel generative framework for functions by integrating Implicit Neural Representations (INRs) and Transformer-based hypernetworks into latent variable models. Unlike prior approaches that rely on MLP-based hypernetworks with…

Machine Learning · Computer Science 2025-11-04 Ignacio Peis , Batuhan Koyuncu , Isabel Valera , Jes Frellsen

Transformers have been the dominant architecture for Speech Translation in recent years, achieving significant improvements in translation quality. Since speech signals are longer than their textual counterparts, and due to the quadratic…

Computation and Language · Computer Science 2023-03-15 Ioannis Tsiamas , Gerard I. Gállego , José A. R. Fonollosa , Marta R. Costa-jussà

Variational autoencoders (VAEs), that are built upon deep neural networks have emerged as popular generative models in computer vision. Most of the work towards improving variational autoencoders has focused mainly on making the…

Machine Learning · Statistics 2016-11-17 Siddharth Agrawal , Ambedkar Dukkipati