Back to Home
arXiv AI··Papers & Tech

Traversing the Satisfaction-Diversity Frontier in Text-to-Image Diffusion

中文摘要

该研究提出新方法,平衡文本生成图像的奖励评分与多样性,解决现有技术无法兼顾两者的问题,提升生成内容的质量与丰富度。

English Summary

This research introduces a novel framework to balance reward and diversity in text-to-image generation, overcoming limitations where high diversity often compromises image quality and user satisfaction.

Original Excerpt

arXiv:2610.02372v1 Announce Type: new Abstract: Text-to-image generation enables users to explore several images generated from the same prompt. For these generated images to be useful, each one must reflect the user's preferences, measured by a learned reward, and differ visually from the others to maintain diversity. Existing methods are limited: they either address reward and diversity separately or combine them in one aggregate score, enabling high diversity to offset low rewards. In this paper, we address these limitations by formulating generation as satisficing: every image (candidate) must satisfy a reward floor and the batch of images must satisfy a diversity cutoff. The reward floor controls the balance between worst-candidate reward and batch diversity; we show that varying this floor defines a Pareto frontier. To traverse this frontier, we introduce SatisDive, a training-free inference-time method. SatisDive uses a batch-relative reward cutoff to distinguish lower- from higher-reward candidates, emphasizing reward improvement for candidates below the cutoff and diversity among candidates above it. On Pick-a-Pic, at matched DreamSim, SatisDive improves worst-candidate re…