37 citations · 60 across the 52 of their papers we have counts for
Showing 2026Show all
3 papers · 1 filter
q-bio.GN2026
Auditing pretraining contamination in single-cell foundation model benchmarks
Sarwan Ali
Single-cell foundation models (scFMs) such as Geneformer, scGPT, and Universal Cell Embeddings (UCE) are pretrained on tens of millions of cells drawn from public repositories. The…
q-bio.GN2026
Causal dictionary learning reveals and validates transcription-factor binding features in genomic language models
Sarwan Ali
Genomic language models achieve strong performance across regulatory-genomics tasks, yet what these models internally represent remains opaque, and the field lacks a principled pro…
cs.LG2026
Multi-Scale Reversible Chaos Game Representation: A Unified Framework for Sequence Classification
Sarwan Ali, Taslim Murad
Biological classification with interpretability remains a challenging task. For this, we introduce a novel encoding framework, Multi-Scale Reversible Chaos Game Representation (MS-…