2 papers
cs.LG2026
Renormalization Group Flow Matching for Scalable Local Generative Modeling
Kanta Masuki, Yuto Ashida
Despite their remarkable success in modeling complex data, generative models face a fundamental tradeoff. Global approaches can capture full structural coherence but suffer from hi…
cond-mat.stat-mech2025
Generative diffusion model with inverse renormalization group flows
Kanta Masuki, Yuto Ashida
Diffusion models represent a class of generative models that produce data by denoising a sample corrupted by white noise. Despite the success of diffusion models in computer vision…