Discovery of a Hematopoietic Manifold in scGPT Yields a Method for Extracting Performant Algorithms from Biological Foundation Model Internals

Documenti analoghi

• Sparse autoencoders reveal organized biological knowledge but minimal regulatory logic in single-cell foundation models: a comparative atlas of Geneformer and scGPT
  di: Kendiukhov, Ihor
  Pubblicazione: (2026)
• Causal Circuit Tracing Reveals Distinct Computational Architectures in Single-Cell Foundation Models: Inhibitory Dominance, Biological Coherence, and Cross-Model Convergence
  di: Kendiukhov, Ihor
  Pubblicazione: (2026)
• HEIST: A Graph Foundation Model for Spatial Transcriptomics and Proteomics Data
  di: Madhu, Hiren, et al.
  Pubblicazione: (2025)
• scI2CL: Effectively Integrating Single-cell Multi-omics by Intra- and Inter-omics Contrastive Learning
  di: Liu, Wuchao, et al.
  Pubblicazione: (2025)
• LapDDPM: A Conditional Graph Diffusion Model for scRNA-seq Generation with Spectral Adversarial Perturbations
  di: Bini, Lorenzo, et al.
  Pubblicazione: (2025)