测试时个性化：学习图像生成的用户偏好

1. 12:00
   arXiv · Computer Vision

   扩散模型如何在测试时学习用户偏好以个性化图像生成

   一项新研究提出从用户历史图像偏好对直接学习个性化奖励模型，以在推理时引导扩散模型生成更贴合个人偏好的图像。方法用自编码器将数百个视觉属性压缩为 50 个属性锚定偏好维度，并在 Bradley-Terry 模型下估计用户权重。

Current heat 9·Comparable peak 10（Oct 8）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.