Author

Shawn Whitfield

Mila - Quebec Artificial Intelligence InstituteORCID 0000-0002-6309-2550Unclaimed ORCID profile · follow to get notified of new preprints

Biology Disciplines

Click to filter author papers

Bioinformatics· 1

Signature Assays, Organisms & Methods

Click to filter · or open tag

Research Focus:benchmarking· 1 Organism:human· 1 Assay:protein sequence· 1 Approach:statistical model· 1

Frequent Co-Authors

CHRISTOPHER JAMES LANGMEADiD· 1 shared Dhanya Sridhar· 1 shared Quentin FournieriD· 1 shared Robert McCoy VernoniD· 1 shared Tom MartyiD· 1 shared

Activity by Year

2026-2026 · peak 1/yr

Co-Author Collaboration Network

5 top collaborators · 10 mutual co-author links

Click any collaborator node to inspect or filter shared papers

Focal author (center)Selected co-authorORCID co-authorUnlinked name

Curved chords = mutual co-authorship

1 shared paperBioinformatics

CHRISTOPHER JAMES LANGMEADORCID

Mutual co-authors in cluster

Author profile →

1 paper

Recent·Most cited

BioinformaticsbioRxivPreprintJul 23, 2026

High-resolution dissection of concept acquisition in different families of protein language models

Shawn Whitfield, Tom Marty, Robert McCoy Vernon…·Quentin Fournier

This study analyzes how biological concepts are encoded in protein language models across their layers and finds that complexity increases with depth, with pretraining data and compute having a greater impact than parameter scaling.

DOI 10.64898/2026.07.20.739599

humanprotein sequence

𝕏 PostBluesky