Small data are often used in scientific and engineering research due to the presence of
various constraints, such as time, cost, ethics, privacy, security, and technical limitations in …

The field of speech processing has undergone a transformative shift with the advent of deep
learning. The use of multiple processing layers has enabled the creation of models capable …

The autonomous driving community has witnessed a rapid growth in approaches that
embrace an end-to-end algorithm framework, utilizing raw sensor input to generate vehicle …

Incrementally learning new information from a non-stationary stream of data, referred to as
'continual learning', is a key feature of natural intelligence, but a challenging problem for …

Visual recognition in low-data regimes requires deep neural networks to learn generalized
representations from limited training samples. Recently, CLIP-based methods have shown …

Neural sequence models based on the transformer architecture have demonstrated
remarkable\emph {in-context learning}(ICL) abilities, where they can perform new tasks …

In-context learning is the ability of a model to condition on a prompt sequence consisting of
in-context examples (input-output pairs corresponding to some task) along with a new query …

Building models that can be rapidly adapted to novel tasks using only a handful of annotated
examples is an open challenge for multimodal machine learning research. We introduce …

Class-incremental learning (CIL) aims to adapt to emerging new classes without forgetting
old ones. Traditional CIL models are trained from scratch to continually acquire knowledge …

Quantitative evaluation of tissue images is crucial for computational pathology (CPath) tasks,
requiring the objective characterization of histopathological entities from whole-slide images …