Related papers: Recurrence Boosts Diversity! Revisiting Recurrent …
This paper proposes a new model, called condition-transforming variational autoencoder (CTVAE), to improve the performance of conversation response generation using conditional variational autoencoders (CVAEs). In conventional CVAEs , the…
We present a syntax-infused variational autoencoder (SIVAE), that integrates sentences with their syntactic trees to improve the grammar of generated sentences. Distinct from existing VAE-based text generative models, SIVAE contains two…
Recent state-of-the-art autoencoder based generative models have an encoder-decoder structure and learn a latent representation with a pre-defined distribution that can be sampled from. Implementing the encoder networks of these models in a…
Generative autoencoders offer a promising approach for controllable text generation by leveraging their latent sentence representations. However, current models struggle to maintain coherent latent spaces required to perform meaningful text…
The Variational Autoencoder (VAE) is a powerful framework for learning probabilistic latent variable generative models. However, typical assumptions on the approximate posterior distribution of the encoder and/or the prior, seriously…
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,…
Generative models able to synthesize layouts of different kinds (e.g. documents, user interfaces or furniture arrangements) are a useful tool to aid design processes and as a first step in the generation of synthetic data, among other…
Controllable text generation has taken a gigantic step forward these days. Yet existing methods are either constrained in a one-off pattern or not efficient enough for receiving multiple conditions at every generation stage. We propose a…
Density estimation, compression and data generation are crucial tasks in artificial intelligence. Variational Auto-Encoders (VAEs) constitute a single framework to achieve these goals. Here, we present a novel class of generative models,…
Simultaneous recordings from thousands of neurons across multiple brain areas reveal rich mixtures of activity that are shared between regions and dynamics that are unique to each region. Existing alignment or multi-view methods neglect…
As an extension of variational autoencoder (VAE), complex VAE uses complex Gaussian distributions to model latent variables and data. This work proposes a complex recurrent VAE framework, specifically in which complex-valued recurrent…
The variational autoencoder (VAE) is a popular probabilistic generative model. However, one shortcoming of VAEs is that the latent variables cannot be discrete, which makes it difficult to generate data from different modes of a…
Deep generative models are reported to be useful in broad applications including image generation. Repeated inference between data space and latent space in these models can denoise cluttered images and improve the quality of inferred…
This paper introduces the Descriptive Variational Autoencoder (DVAE), an unsupervised and end-to-end trainable neural network for predicting vehicle trajectories that provides partial interpretability. The novel approach is based on the…
Anomaly detection is a classical but worthwhile problem, and many deep learning-based anomaly detection algorithms have been proposed, which can usually achieve better detection results than traditional methods. In view of reconstruct…
Selective manipulation of data attributes using deep generative models is an active area of research. In this paper, we present a novel method to structure the latent space of a Variational Auto-Encoder (VAE) to encode different…
Variational Autoencoders (VAEs) are powerful generative models for learning latent representations. Standard VAEs generate dispersed and unstructured latent spaces by utilizing all dimensions, which limits their interpretability, especially…
Imitation learning is an intuitive approach for teaching motion to robotic systems. Although previous studies have proposed various methods to model demonstrated movement primitives, one of the limitations of existing methods is that the…
We introduce an improved variational autoencoder (VAE) for text modeling with topic information explicitly modeled as a Dirichlet latent variable. By providing the proposed model topic awareness, it is more superior at reconstructing input…
We study the problem of using (partial) constituency parse trees as syntactic guidance for controlled text generation. Existing approaches to this problem use recurrent structures, which not only suffer from the long-term dependency problem…