Large models represent a groundbreaking advancement in multiple application fields,
enabling remarkable achievements across various tasks. However, their unprecedented …

The booming development of deep learning applications and services heavily relies on
large deep learning models and massive data in the cloud. However, cloud-based deep …

Large pre-trained models (LPMs), such as LLaMA and GLM, have shown exceptional
performance across various tasks through fine-tuning. Although low-rank adaption (LoRA) …

Large foundation models, including large language models (LLMs), vision transformers
(ViTs), diffusion, and LLM-based multimodal models, are revolutionizing the entire machine …

In this paper we democratise caricature generation empowering individuals to effortlessly
craft personalised caricatures with just a photo and a conceptual sketch. Our objective is to …

Low-resource settings are well-established in natural lan-guage processing where many
languages lack sufficient data for deep learning at scale. However low-resource problems …

With the growing size of pre-trained models full fine-tuning and storing all the parameters for
various downstream tasks is costly and infeasible. In this paper we propose a new …

Rich textual and topological information of textual graphs need to be modeled in real-world
applications such as webpages, e-commerce, and academic articles. Practitioners have …

Adapters provide an efficient and lightweight mechanism for adapting trained transformer
models to a variety of different tasks. However they have often been found to be …

Class-incremental learning (CIL) aims to enable models to continuously learn new classes
while overcoming catastrophic forgetting. The introduction of pre-trained models has brought …