3 papers
cs.LG2026
ProteinJEPA: Latent prediction complements protein language models
Dan Ofer, Dafna Shahaf, Michal Linial
Protein language models are trained primarily with masked language modeling (MLM), which predicts amino-acid identities at masked positions. We ask whether latent-space prediction…
cs.LG2026
ProtSent: Protein Sentence Transformers
Dan Ofer, Oriel Perets, Michal Linial +1
Protein language models (pLMs) produce per-residue representations that capture evolutionary and structural information, yet their mean-pooled sequence embeddings are not explicitl…
q-bio.QM2025
InterFeat: A Pipeline for Finding Interesting Scientific Features
Dan Ofer, Michal Linial, Dafna Shahaf
Finding interesting phenomena is the core of scientific discovery, but it is a manual, ill-defined concept. We present an integrative pipeline for automating the discovery of inter…