作者位次 #5/6ICLR 2026Poster· Computer Vision / Image and Video Generation
W-EDIT: A Wavelet-Based Frequency-Aware Framework for Text-Driven Image Editing
Jiahui Sun · Weining Wang · Mingzhen Sun · Peiyao Wang · Xinxin Zhu · Jing Liu
多模态OpenReview
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。
Jiahui Sun · Weining Wang · Mingzhen Sun · Peiyao Wang · Xinxin Zhu · Jing Liu
Handong Li · Zikang Liu · Longteng Guo · Tongtian Yue · Yepeng Tang · Xinxin Zhu · Chuanyang Zheng · Ziming Wang · Zhibin Wang · Jun Song · Cheng Yu · Zerui Huang (Taobao & · Jing Liu
Longteng Guo · Yifan Wang · Pengkang Huo · Tailai Chen · Yuze Wu · Jing Liu · Xinxin Zhu
Recent multimodal large language models (MLLMs) achieve strong performance on visual reasoning benchmarks, yet it remains unclear to what extent such performance reflects reasoning directly grounded in visual evidence. We introduce VisReason, a benchmark for vision-centric reasoning in everyday s...