3 papers
cs.LG2026
TwinPurify: Purifying gene expression data to reveal tumor-intrinsic transcriptional programs via self-supervised learning
Zhiwei Zheng, Kevin Bryson
Advances in single-cell and spatial transcriptomic technologies have transformed tumor ecosystem profiling at cellular resolution. However, large scale studies on patient cohorts c…
cs.LG2026
LaCoGSEA: Unsupervised deep learning for pathway analysis via latent correlation
Zhiwei Zheng, Kevin Bryson
Motivation: Pathway enrichment analysis is widely used to interpret gene expression data. Standard approaches, such as GSEA, rely on predefined phenotypic labels and pairwise compa…
cs.CL2025
Can We Edit LLMs for Long-Tail Biomedical Knowledge?
Xinhao Yi, Jake Lever, Kevin Bryson +1
Knowledge editing has emerged as an effective approach for updating large language models (LLMs) by modifying their internal knowledge. However, their application to the biomedical…