<ul><li>GeneMamba is introduced as a scalable and efficient foundation model for single-cell transcriptomics built on state space modeling.</li><li>It captures bidirectional gene context with linear-time complexity, offering substantial computational gains over transformer baselines.</li><li>GeneMamba is pretrained on nearly 30 million cells and incorporates biologically informed objectives, including pathway-aware contrastive loss and rank-based gene encoding.</li><li>Evaluation of GeneMamba showcases its strong performance, interpretability, and robustness, making it a practical and powerful alternative to transformer-based methods for single-cell data analysis.</li></ul>

Bidirectional Mamba for Single-Cell Data: Efficient Context Learning with Biological Fidelity

Discover more