作者位次 #5/7ECCV 2026Oral
MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation
Yang Chen · Xiaowei Xu · Shuai Wang · Xinwen Zhang · Qiushi Guo · Tiezheng Ge · Limin Wang
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。
Yang Chen · Xiaowei Xu · Shuai Wang · Xinwen Zhang · Qiushi Guo · Tiezheng Ge · Limin Wang
Ziwei Huang · Ying Shu · Fanghao · Quanyu Long · Wenya Wang · Qiushi Guo · Tiezheng Ge · Leilei Gan
Subject-driven image generation models face a fundamental trade-off between identity preservation (fidelity) and prompt adherence (editability). While online reinforcement learning (RL), specifically GPRO, offers a promising solution, we find that a naive application of GRPO leads to competitive...