Instruction finetuning is a popular paradigm to align large language mod...
In the last decade, Convolutional Neural Network (CNN) and transformer b...
Past work exploring adversarial vulnerability have focused on situations...
Linear neural network layers that are either equivariant or invariant to...
Successful deployment in uncertain, real-world environments requires tha...
Prompting has become an important mechanism by which users can more
effe...
The assumption that many forms of high-dimensional data, such as images,...
There is a growing body of work that leverages features extracted via
to...
It is often said that a deep learning model is "invariant" to some speci...
It is widely acknowledged that trained convolutional neural networks (CN...
Symmetry has been a fundamental tool in the exploration of a broad range...
Technological advances are in part enabled by the development of novel
m...
While it is not generally reflected in the `nice' datasets used for
benc...
In many classification problems, we want a classifier that is robust to ...
Advanced manufacturing techniques have enabled the production of materia...
Methods for model explainability have become increasingly critical for
t...
Many-to-one maps are ubiquitous in machine learning, from the image
reco...
As both machine learning models and the datasets on which they are evalu...
Building invariance to non-meaningful transformations is essential to
bu...
The field of few-shot learning has made remarkable strides in developing...
As data grows in size and complexity, finding frameworks which aid in
in...
Recently proposed few-shot image classification methods have generally
f...
Deep learning has shown great success in settings with massive amounts o...
Compressive sensing (CS) is a method of sampling which permits some clas...
Sampling is a fundamental aspect of any implementation of compressive
se...
In many situations, the classes of data points of primary interest also
...
Multidimensional scaling (MDS) is a fundamental tool for both data
visua...
Dimensionality-reduction methods are a fundamental tool in the analysis ...
A fundamental question in many data analysis settings is the problem of
...
Dimensionality-reduction techniques are a fundamental tool for extractin...
Endmember extraction plays a prominent role in a variety of data analysi...