A basic question within the emerging field of mechanistic interpretability is the degree to
which neural networks learn the same underlying mechanisms. In other words, are neural …

The rapid progress of research aimed at interpreting the inner workings of advanced
language models has highlighted a need for contextualizing the insights gained from years …

Despite the widespread adoption of prompting, prompt tuning and prefix-tuning of
transformer models, our theoretical understanding of these fine-tuning methods remains …

Self-attention is the key mechanism of transformers, which are the essential building blocks
of modern foundation models. Recent studies have shown that pure self-attention suffers …

Motivation The human microbiome may impact the effectiveness of drugs by modulating
their activities and toxicities. Predicting candidate microbes for drugs can facilitate the …

Deriving formal bounds on the expressivity of transformers, as well as studying transformers
that are constructed to implement known algorithms, are both effective methods for better …

The rise of creative machines is attributed to generative AI which enabled machines to
create new contents. Wherein the introduction of the advanced neural network architecture …

ChatGPT has now become a global phenomenon that has revolutionized the manner in
which machines interact with humans. It is a noteworthy enhancement in the field of …

Social media comments are no longer in a single textual modality, but heterogeneous data
in multiple modalities, such as vision, sound, and text, which is why multimodal sentiment …

Currently, diabetic retinopathy diagnosis tools use deep learning and machine learning
algorithms for fundus image classification. Deep learning techniques especially convolution …