Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation
Daily Paper Cast · Jingwen Liang, Gengyu Wang
July 16, 202619m 17s
Audio is streamed directly from the publisher (media.transistor.fm) as published in their RSS feed. Play Podcasts does not host this file. Rights-holders can request removal through the copyright & takedown page.