AI RESEARCH
Beyond Generative Priors: Minority Sampling with JEPA-Guided Diffusion
arXiv CS.AI
•
ArXi:2605.24631v1 Announce Type: cross Minority sampling aims to generate low-density instances on a data manifold and is of central importance in applications such as medical diagnosis, anomaly detection, and creative AI. Existing approaches, however, define minority samples relative to generative priors learned from