作者位次 #7/8ICML 2026Poster· Deep Learning / Robustness
MEDUSA: Motion Elimination in Diffusion Using Spectral Attack
Hongwei Yu · Daoqing Zha · Xinlong Ding · Jiawei Li · Junbao Zhuo · Qiankun Liu · Huimin Ma · Jiansheng Chen
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。
Hongwei Yu · Daoqing Zha · Xinlong Ding · Jiawei Li · Junbao Zhuo · Qiankun Liu · Huimin Ma · Jiansheng Chen
Hongyuan Liu · Bochao Zou · Qiankun Liu · Haochen Yu · Qi Mei · Jianfei Jiang · Chen Liu · Cheng Bi · Zhao Wang · Xueyang Zhang · Yifei Zhan · Jiansheng Chen · Huimin Ma
Siqi Liu · Xinyang Li · Bochao Zou · Junbao Zhuo · Huimin Ma · Jiansheng Chen
Liyong Wang · Junliang Xing · Tianyu Hu · Jianfei Jiang · Jihuai Zhao · Huimin Ma
Audio-Visual Speech Recognition enhances speech recognition robustness in noisy conditions by leveraging visual cues. However, current Multimodal LLMs suffer from a fundamental temporal gap. This gap is characterized by limited fine-grained temporal modeling in vision encoders and progressive tem...