Large, well described gaps exist in both what we know and what we need to know to
address the biodiversity crisis. Artificial intelligence (AI) offers new potential for filling these …

The taxonomic identification of organisms from images is an active research area within the
machine learning community. Current algorithms are very effective for object recognition and …

Masked language modelling (MLM) as a pretraining objective has been widely adopted in
genomic sequence modelling. While pretrained models can successfully serve as encoders …

Discovering the genotype-phenotype relationship is crucial for genetic engineering, which
will facilitate advances in fields such as crop breeding, conservation biology, and …

Methods for detecting label errors in training data require models that are robust to label
errors (ie, not fit to erroneously labelled data points). However, acquiring such models often …