The article introduces CFM for CNFs, addressing training challenges and improving results in various generative tasks. It discusses OT-CFM for dynamic OT approximation and SB-CFM for Schrödinger bridge inference. Experiments show improved training efficiency and performance in single-cell dynamics, image generation, and unsupervised translation.
לשפה אחרת
מתוכן המקור
arxiv.org
תובנות מפתח מזוקקות מ:
by Alexander To... ב- arxiv.org 03-12-2024
https://arxiv.org/pdf/2302.00482.pdfשאלות מעמיקות