What Makes a Representation Good for Single-Cell Perturbation Prediction?

ArXi:2605.19343v1 Announce Type: new Single-cell perturbation modeling is fundamental for understanding and predicting cellular responses to genetic perturbations. However, existing approaches, from causal representation learning to foundation models, often struggle with an overlooked challenge: gene expression is dominated by perturbation-invariant information, while perturbation-specific signals are intrinsically sparse.