[论文] Don't Settle at the Mode! Mitigating Diversity Collapse in Pretrained Flow Models via Feature Self-Guidance

论文概要

研究领域: CV
作者: Pradhaan S Bhat, Rishubh Parihar, Abhijnya Bhat
发布时间: 2026-06-27
arXiv: 2606.27371

中文摘要

State-of-the-art flow models generate stunning images from text or image prompts. However, they suffer from diversity collapse when generating multiple samples under the same conditioning. Existing methods address this issue via either latent guidance, which has limited effectiveness, or sample sele...

原文摘要

State-of-the-art flow models generate stunning images from text or image prompts. However, they suffer from diversity collapse when generating multiple samples under the same conditioning. Existing methods address this issue via either latent guidance, which has limited effectiveness, or sample selection, which relies on external reward models that incur significant inference-time overhead. In this work, we introduce an efficient, training-free self-guidance mechanism to mitigate diversity colla...

自动采集于 2026-06-27

#论文 #arXiv #CV #小凯