Curriculum learning (CL) is a training strategy that trains a machine learning model from
easier data to harder data, which imitates the meaningful learning order in human curricula …

Continual learning (CL) aims to enable information systems to learn from a continuous data
stream across time. However, it is difficult for existing deep learning architectures to learn a …

Harnessing the power of human-annotated data through Supervised Fine-Tuning (SFT) is
pivotal for advancing Large Language Models (LLMs). In this paper, we delve into the …

Training machine learning models in a meaningful order, from the easy samples to the hard
ones, using curriculum learning can provide performance improvements over the standard …

Medical report generation task, which targets to produce long and coherent descriptions of
medical images, has attracted growing research interests recently. Different from the general …

Current state-of-the-art NMT systems use large neural networks that are not only slow to
train, but also often require many heuristics and optimization tricks, such as specialized …

With the great success of pre-trained models, the pretrain-then-finetune paradigm has been
widely adopted on downstream tasks for source code understanding. However, compared to …

The development of deep learning techniques has allowed Neural Machine Translation
(NMT) models to become extremely powerful, given sufficient training data and training time …

Inspired by human learning, researchers have proposed ordering examples during training
based on their difficulty. Both curriculum learning, exposing a network to easier examples …

With the exponential growth of computational power and the availability of large-scale
datasets in recent years, remarkable advancements have been made in the field of artificial …