SToFM pretrains an SE(2) Transformer on multi-scale sub-slices of spatial transcriptomics data, using virtual cells to capture tissue structure, and reports state-of-the-art results on several ST benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-bio.GN 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SToFM: a Multi-scale Foundation Model for Spatial Transcriptomics
SToFM pretrains an SE(2) Transformer on multi-scale sub-slices of spatial transcriptomics data, using virtual cells to capture tissue structure, and reports state-of-the-art results on several ST benchmarks.