Instruction tuning plays a critical role in aligning large language models (LLMs) with human
preference. Despite the vast amount of open instruction datasets, naively training a LLM on …

Selecting suitable architecture parameters and training hyperparameters is essential for
enhancing machine learning (ML) model performance. Several recent empirical studies …

We investigate the spectral properties of linear-width feed-forward neural networks, where
the sample size is asymptotically proportional to network width. Empirically, we show that the …

Recent work has highlighted the complex influence training hyperparameters, eg, the
number of training epochs, can have on the prunability of machine learning models …

Recent success of pre-trained foundation vision-language models makes Open-Vocabulary
Segmentation (OVS) possible. Despite the promising performance this approach introduces …

To understand better good generalization performance in state-of-the-art neural network
(NN) models, and in particular the success of the ALPHAHAT metric based on Heavy-Tailed …

Much recent research effort has been devoted to explain the success of deep learning.
Random Matrix Theory (RMT) provides an emerging way to this end by analyzing the …

Learning representations of well-trained neural network models holds the promise to
provide an understanding of the inner workings of those models. However, previous work …

This thesis addresses the challenge of understanding Neural Networks through the lens of
their most fundamental component: the weights, which encapsulate the learned information …

Pre-trained Large Language Models (LLMs) encapsulate large amounts of knowledge and
take enormous amounts of compute to train. We make use of this resource, together with the …