AI RESEARCH
Expert-Data Alignment Governs Generation Quality in Decentralized Diffusion Models
arXiv CS.LG
•
ArXi:2602.02685v2 Announce Type: replace Decentralized Diffusion Models (DDMs) route denoising through experts trained independently on disjoint data clusters, which can strongly disagree in their predictions. What governs the quality of generations in such systems? We present the first ever systematic investigation of this question. A priori, the expectation is that minimizing denoising trajectory sensitivity -- minimizing how perturbations amplify during sampling -- should govern generation quality. We nstrate this hypothesis is incorrect: a stability-quality dissociation.