Related papers: List Autoencoder: Towards Deep Learning Based Reli…

Dense retrieval requires high-quality text sequence embeddings to support effective search in the representation space. Autoencoder-based language models are appealing in dense retrieval as they train the encoder to output high-quality…

In this paper, we introduce an autoencoder (AE)-based scheme for end-to-end optimization of a multi-user molecule mixture communication system. In the proposed scheme, each transmitter leverages an encoder network that maps the user symbol…

Textual graphs are ubiquitous in real-world applications, featuring rich text information with complex relationships, which enables advanced research across various fields. Textual graph representation learning aims to generate…

As the basis of generative AI, an autoregressive model requires the generation of a new token depending on all the previously generated tokens, which brings high quality but also restricts the model to generate tokens one by one, forming a…

Clustering using deep neural network models have been extensively studied in recent years. Among the most popular frameworks are the VAE and GAN frameworks, which learns latent feature representations of data through encoder / decoder…

Despite advances in deep probabilistic models, learning discrete latent representations remains challenging. This work introduces a novel method to improve inference in discrete Variational Autoencoders by reframing the inference problem…

Masked Image Modeling (MIM)-based models, such as SdAE, CAE, GreenMIM, and MixAE, have explored different strategies to enhance the performance of Masked Autoencoders (MAE) by modifying prediction, loss functions, or incorporating…

Pretraining neural networks with massive unlabeled datasets has become popular as it equips the deep models with a better prior to solve downstream tasks. However, this approach generally assumes that the downstream tasks have access to…

Generative priors have been shown to provide improved results over sparsity priors in linear inverse problems. However, current state of the art methods suffer from one or more of the following drawbacks: (a) speed of recovery is slow; (b)…

Variational Autoencoders (VAEs) provide a theoretically-backed and popular framework for deep generative models. However, learning a VAE from data poses still unanswered theoretical questions and considerable practical challenges. In this…

We propose Denoising Masked Autoencoder (Deno-MAE), a novel multimodal autoencoder framework for denoising modulation signals during pretraining. DenoMAE extends the concept of masked autoencoders by incorporating multiple input modalities,…

With the mass construction of Gen III nuclear reactors, it is a popular trend to use deep learning (DL) techniques for fast and effective diagnosis of possible accidents. To overcome the common problems of previous work in diagnosing…

We propose a generative model of paraphrase generation, that encourages syntactic diversity by conditioning on an explicit syntactic sketch. We introduce Hierarchical Refinement Quantized Variational Autoencoders (HRQ-VAE), a method for…

Finding an interpretable non-redundant representation of real-world data is one of the key problems in Machine Learning. Biological neural networks are known to solve this problem quite well in unsupervised manner, yet unsupervised…

In this paper, we present an in-depth investigation of the convolutional autoencoder (CAE) bottleneck. Autoencoders (AE), and especially their convolutional variants, play a vital role in the current deep learning toolbox. Researchers and…

B-mode ultrasound tongue imaging is widely used in the speech production field. However, efficient interpretation is in a great need for the tongue image sequences. Inspired by the recent success of unsupervised deep learning approach, we…

Humans increasingly interact with Artificial intelligence(AI) systems. AI systems are optimized for objectives such as minimum computation or minimum error rate in recognizing and interpreting inputs from humans. In contrast, inputs created…

This paper proposes an alternative algorithm for multichannel variational autoencoder (MVAE), a recently proposed multichannel source separation approach. While MVAE is notable in its impressive source separation performance, the…

Shape illustration images (SIIs) are common and important in describing the cross-sections of industrial products. Same as MNIST, the handwritten digit images, SIIs are gray or binary and containing shapes that are surrounded by large areas…

Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one that describes only…