Topic: Foundation model

Develop ARCA, a foundation model that combines crop microbiome, genome and environmental data to predict microbial community behaviour and support crop resilience. The NOAH consortium connects model development with greenhouse and field experiments. This 36–40-hour postdoctoral appointment starts in January 2027, initially for one year with a three-year extension after positive evaluation. Apply with a CV, motivation letter, two referee contacts and evidence of PhD completion or a planned defence.

Connor Lane will lead a journal club on the recent BrainLM preprint, a foundation model for fMRI trained using self-supervised masked autoencoder training. Preprint: https://www.biorxiv.org/content/10.1101/2023.09.12.557460v1 Tweeprint: https://twitter.com/david_van_dijk/status/1702336882301112631?t=Q2-U92-BpJUBh9C35iUbUA&s=19

We present a comprehensive dataset of neural activity, compiled from 11 neuroimaging experiments in the nematode worm C. elegans. These source datasets, while collected under different experimental protocols, all measure neural activity via changes in calcium fluorescence in labeled subsets of the hermaphrodite worm’s 300 neurons. Our contribution is to standardize these disparate datasets into a unified framework including ordering the neural data from labeled neurons consistently, resampling traces to a common timestep, and including a feature mask to indicate which neurons were labeled in e