As words can have multiple meanings that depend on sentence context, genes can have
various functions that depend on the surrounding biological system. This pleiotropic nature …

Transformer networks have revolutionized NLP representation learning since they were
introduced. Though a great effort has been made to explain the representation in …

In high-throughput functional genomic screens, each gene product is commonly assumed to
exhibit a singular biological function within a defined protein complex or pathway. In …

One of the roadblocks to a better understanding of neural networks' internals is\textit
{polysemanticity}, where neurons appear to activate in multiple, semantically distinct …

We describe a minimalistic and interpretable method for unsupervised learning, without
resorting to data augmentation, hyperparameter tuning, or other engineering designs, that …

Flow-based generative models have become an important class of unsupervised learning
approaches. In this work, we incorporate the key ideas of renormalization group (RG) and …

We describe a minimalistic and interpretable method for unsupervised representation
learning that does not require data augmentation, hyperparameter tuning, or other …

Learning word embeddings is an essential topic in natural language processing. Most
existing works use a vast corpus as a primary source while training, but this requires …

Word embeddings are a powerful natural language processing technique, but they are
extremely difficult to interpret. To enable interpretable NLP models, we create vectors where …

Large pretrained language models have demonstrated impressive capabilities, but there is
still much to learn about how they operate mechanically. In this study, we conduct a …