This comprehensive survey explored the evolving landscape of generative Artificial
Intelligence (AI), with a specific focus on the transformative impacts of Mixture of Experts …

While Feedforward Neural Networks (FNNs) have achieved remarkable success in various
tasks, they are vulnerable to adversarial examples. Several techniques have been …

Recurrent neural networks (RNNs) have emerged as powerful tools for processing
sequential data in various fields, including natural language processing and speech …

Over the past decade, Artificial Intelligence (AI) has had great success recently and is being
used in a wide range of academic and industrial fields. More recently, Large Language …

In modern machine (ML) learning systems, Transformer-based architectures have achieved
milestone success across a broad spectrum of tasks, yet understanding their operational …

Since the seminal work by Angluin, active learning of automata, by membership and
equivalence queries, has been extensively studied and several generalisations have been …

Adversarial examples are notably characterized by their strong transferability, allowing
attackers to craft these examples on their models and subsequently deploy them against …

Weighted finite automata (WFAs) are a generalisation of nondeterministic finite automata,
where transitions are additionally equipped with weights from a semiring. This induces a …

Abstract Recently, the mysterious In-Context Learning (ICL) ability of Transformer
architecture, particularly in large language models, has garnered considerable research …

ABSTRACT Large Language Models (LLMs) have achieved remarkable success across
diverse tasks, yet they remain vulnerable to adversarial attacks, notably the welldocumented …