Reproduce “Learning the Shared Latent Structure of Cryo-EM Inverse Problems” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Nithin Chalapathi, Theo Sternlieb, Ethan Han, Sonya M. Hanson, Pilar Cossio, Aditi S. Krishnapriyan, Ritwik Gupta
EMber learns reusable representations for cryo-EM particle images across views and imaging conditions. It renders paired views with a cryo-EM image-formation model and trains spatial features through self-distillation and masked-patch prediction. On synthetic Tomotwin-8, its particle groups reach 3.57 ± 0.03 Å FSC=0.5 resolution after two pose-search epochs, near the 3.56 Å oracle, with final reconstructions using ground-truth poses.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.