AI RESEARCH

Generalization and Memorization in Rectified Flow

arXiv CS.LG

ArXi:2603.13421v1 Announce Type: new Generative models based on the Flow Matching objective, particularly Rectified Flow, have emerged as a dominant paradigm for efficient, high-fidelity image synthesis. However, while existing research heavily prioritizes generation quality and architectural scaling, the underlying dynamics of how RF models memorize