Related papers: Fuse It More Deeply! A Variational Transformer wit…
Diffusion-based large language models (Diffusion LLMs) have shown promise for non-autoregressive text generation with parallel decoding capabilities. However, the practical inference speed of open-sourced Diffusion LLMs often lags behind…
The ability of learning disentangled representations represents a major step for interpretable NLP systems as it allows latent linguistic features to be controlled. Most approaches to disentanglement rely on continuous variables, both for…
Deep learning approaches process data in a layer-by-layer way with intermediate (or latent) features. We aim at designing a general solution to optimize the latent manifolds to improve the performance on classification, segmentation,…
In this thesis, we explore the use of deep neural networks for generation of natural language. Specifically, we implement two sequence-to-sequence neural variational models - variational autoencoders (VAE) and variational encoder-decoders…
The ability to accurately model random fields plays a critical role in science and engineering for problems involving uncertain, spatially-varying quantities such as heterogeneous material properties and turbulent flows. Deep generative…
Variational Autoencoders (VAEs) are powerful generative models capable of learning compact latent representations. However, conventional VAEs often generate relatively blurry images due to their assumption of an isotropic Gaussian latent…
Text variational autoencoders (VAEs) are notorious for posterior collapse, a phenomenon where the model's decoder learns to ignore signals from the encoder. Because posterior collapse is known to be exacerbated by expressive decoders,…
Conditional variational models, using either continuous or discrete latent variables, are powerful for open-domain dialogue response generation. However, previous works show that continuous latent variables tend to reduce the coherence of…
Generating high quality texts with high diversity is important for many NLG applications, but current methods mostly focus on building deterministic models to generate higher quality texts and do not provide many options for promoting…
Constraint-based causal discovery is widely used for learning causal structures, but heavy reliance on conditional independence (CI) testing makes it computationally expensive in high-dimensional settings. To mitigate this limitation, many…
Variational Autoencoders (VAEs) were originally motivated (Kingma & Welling, 2014) as probabilistic generative models in which one performs approximate Bayesian inference. The proposal of $\beta$-VAEs (Higgins et al., 2017) breaks this…
Deep generative models have demonstrated successful applications in learning non-linear data distributions through a number of latent variables and these models use a nonlinear function (generator) to map latent samples into the data space.…
Latent diffusion models offer an attractive alternative to discrete diffusion for non-autoregressive text generation by operating on continuous text representations and denoising entire sequences in parallel. The major challenge in latent…
A variational autoencoder (VAE) is a probabilistic machine learning framework for posterior inference that projects an input set of high-dimensional data to a lower-dimensional, latent space. The latent space learned with a VAE offers…
While much work on deep latent variable models of text uses continuous latent variables, discrete latent variables are interesting because they are more interpretable and typically more space efficient. We consider several approaches to…
We introduce a Deep Kernel Learning Variational Autoencoder (VAE-DKL) framework that integrates the generative power of a Variational Autoencoder (VAE) with the predictive nature of Deep Kernel Learning (DKL). The VAE learns a latent…
Latent Video Diffusion Models (LVDMs) rely on Variational Autoencoders (VAEs) to compress videos into compact latent representations. For continuous Variational Autoencoders (VAEs), achieving higher compression rates is desirable; yet, the…
Variational autoencoders are prominent generative models for modeling discrete data. However, with flexible decoders, they tend to ignore the latent codes. In this paper, we study a VAE model with a deterministic decoder (DD-VAE) for…
Currently end-to-end deep learning based open-domain dialogue systems remain black box models, making it easy to generate irrelevant contents with data-driven models. Specifically, latent variables are highly entangled with different…
Large climate-model ensembles are computationally expensive; yet many downstream analyses would benefit from additional, statistically consistent realizations of spatiotemporal climate variables. We study a generative modeling approach for…