Efficiently embedding and/or integrating mechanistic information with data-driven models is
essential if it is desired to simultaneously take advantage of both engineering principles and …

Knowledge Distillation (KD) is a promising technique for reducing the high computational
demand of large language models (LLMs). However, previous KD methods are primarily …

In Bayesian machine learning, the posterior distribution is typically computationally
intractable, hence variational inference is often required. In this approach, an evidence …

We present a deep learning framework for quantifying and propagating uncertainty in
systems governed by non-linear differential equations using physics-informed neural …

Adversarial learning methods have been proposed for a wide range of applications, but the
training of adversarial models can be notoriously unstable. Effectively balancing the …

The primary goal of knowledge distillation (KD) is to encapsulate the information of a model
learned from a teacher network into a student network, with the latter being more compact …

Generative adversarial networks (GANs) have achieved significant success in generating
real-valued data. However, the discrete nature of text hinders the application of GAN to text …

Abstract A Triangle Generative Adversarial Network ($\Delta $-GAN) is developed for semi-
supervised cross-domain joint distribution matching, where the training data consists of …

The problem of catastrophic forgetting occurs in deep learning models trained on multiple
databases in a sequential manner. Recently, generative replay mechanisms (GRM) have …

Deep generative models have achieved impressive success in recent years. Generative
Adversarial Networks (GANs) and Variational Autoencoders (VAEs), as emerging families …