作者位次 #2/5ICLR 2026Poster· Computer Vision / Image and Video Generation
DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models
Mor Ventura · Michael Toker · Or Patashnik · Yonatan Belinkov · Roi Reichart
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Mor Ventura · Michael Toker · Or Patashnik · Yonatan Belinkov · Roi Reichart
Guy Kaplan · Michael Toker · Yuval Reif · Yonatan Belinkov · Roy Schwartz
Text-to-image generation models suffer from alignment problems, where generated images fail to accurately capture the objects and relations in the text prompt. Prior work has focused on improving alignment by refining the diffusion process, ignoring the role of the text encoder, which guides the...