相关论文: Chroma-VAE: Mitigating Shortcut Learning with Gene…

Variational Auto-Encoder (VAE) has become the de-facto learning paradigm in achieving representation learning and generation for natural language at the same time. Nevertheless, existing VAE-based language models either employ elementary…

Variation Autoencoder (VAE) has become a powerful tool in modeling the non-linear generative process of data from a low-dimensional latent space. Recently, several studies have proposed to use VAE for unsupervised clustering by using…

The ability to record activities from hundreds of neurons simultaneously in the brain has placed an increasing demand for developing appropriate statistical techniques to analyze such data. Recently, deep generative models have been…

In principle, applying variational autoencoders (VAEs) to sequential data offers a method for controlled sequence generation, manipulation, and structured representation learning. However, training sequence VAEs is challenging:…

Variational Autoencoders (VAEs) remain a cornerstone of generative computer vision, yet their training is often plagued by artifacts that degrade reconstruction and generation quality. This paper introduces VIVAT, a systematic approach to…

Variational autoencoders (VAEs) are latent variable models that can generate complex objects and provide meaningful latent representations. Moreover, they could be further used in downstream tasks such as classification. As previous work…

We present a new generative autoencoder model with dual contradistinctive losses to improve generative autoencoder that performs simultaneous inference (reconstruction) and synthesis (sampling). Our model, named dual contradistinctive…

Variational auto-encoder (VAE) is a powerful unsupervised learning framework for image generation. One drawback of VAE is that it generates blurry images due to its Gaussianity assumption and thus L2 loss. To allow the generation of high…

Vector Quantized Variational Autoencoders (VQ-VAEs) are fundamental to modern generative modeling, yet they often suffer from training instability and "codebook collapse" due to the inherent coupling of representation learning and discrete…

Variational autoencoders were proven successful in domains such as computer vision and speech processing. Their adoption for modeling user preferences is still unexplored, although recently it is starting to gain attention in the current…

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…

Deep generative models have been praised for their ability to learn smooth latent representation of images, text, and audio, which can then be used to generate new, plausible data. However, current generative models are unable to work with…

Learning a disentangled, interpretable, and structured latent representation in 3D generative models of faces and bodies is still an open problem. The problem is particularly acute when control over identity features is required. In this…

Reducing token count is crucial for efficient training and inference of latent diffusion models, especially at high resolution. A common strategy is to build high-compression image tokenizers with more channels per token. However, when…

Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful node embedding methods, with promising performances on challenging tasks such as link prediction and node clustering. Graph AE, VAE and most of their…

The omnipresence of deep learning architectures such as deep convolutional neural networks (CNN)s is fueled by the synergistic combination of ever-increasing labeled datasets and specialized hardware. Despite the indisputable success, the…

We present a novel method for constructing Variational Autoencoder (VAE). Instead of using pixel-by-pixel loss, we enforce deep feature consistency between the input and the output of a VAE, which ensures the VAE's output to preserve the…

In this paper, we are interested in audio-visual speech separation given a single-channel audio recording as well as visual information (lips movements) associated with each speaker. We propose an unsupervised technique based on…

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…

The OECD pointed out that the best way to keep students up to school is to intervene as early as possible [1]. Using education big data and deep learning to predict student's score provides new resources and perspectives for early…