Article

Parameter-free representations outperform single-cell foundation models on downstream benchmarks

2026-02-13

Abstract excerpt

Single-cell RNA sequencing (scRNA-seq) data exhibit strong and reproducible statistical structure. This has motivated the development of large-scale foundation models, such as TranscriptFormer, that use transformer-based architectures to learn a generative model for gene expression by embedding genes into a latent vector space. These embeddings have been used to obtain state-of-the-art (SOTA) performance on downst...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 3a1dbbd9-6786-5a88-a4b5-d8bbd4260297
DOI: 10.64898/2026.02.11.705358

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Parameter-free representations outperform single-cell foundation models on downstream benchmarksDOI 10.64898/2026.02.11.705358Read

A Cross-Species Generative Cell Atlas Across 1.5 Billion Years of Evolution: The TranscriptFormer Single-cell ModelSemantic proximity Read

RegFormer: A Single-Cell Foundation Model Powered by Gene Regulatory HierarchiesSemantic proximity Read

Species-specific small models for cell type classification approach the performance of large single cell foundation modelsSemantic proximity Read

GeneCompass: Deciphering Universal Gene Regulatory Mechanisms with Knowledge-Informed Cross-Species Foundation ModelSemantic proximity Read

Benchmarking single-cell foundation models in a zero-shot settingSemantic proximity Read

TabVI: Leveraging Lightweight Transformer Architectures to Learn Biologically Meaningful Cellular RepresentationsSemantic proximity Read

Learning interpretable cellular and gene signature embeddings from single-cell transcriptomic dataSemantic proximity Read

Transferable representations of single-cell transcriptomic dataSemantic proximity Read

Unify: Learning Cellular Evolution with Universal Multimodal EmbeddingsSemantic proximity Read

scEMB: Learning context representation of genes based on large-scale single-cell transcriptomicsSemantic proximity Read

GeneBag: training a cell foundation model for broad-spectrum cancer diagnosis and prognosis with bulk RNA-seq dataSemantic proximity Read

Learning multi-cellular representations of single-cell transcriptomics data enables characterization of patient-level disease statesSemantic proximity Read