Want to create an interactive transcript for this episode?
Podcast: Arxiv Papers
Episode: PLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity
Description: PLADIS enhances pre-trained diffusion models using sparse attention, improving text-to-image generation without extra training, while integrating with guidance techniques and achieving better text alignment and human preference.https://arxiv.org/abs//2503.07677YouTube: https://www.youtube.com/@ArxivPapersTikTok: https://www.tiktok.com/@arxiv_papersApple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers