作者位次 #3/7ICLR 2026Poster· Deep Learning / Attention Mechanisms
Scaling Attention via Feature Sparsity
Yan Xie · Tiansheng Wen · Tang Da Huang · Bo Chen · Chenyu You · Stefanie Jegelka · Yifei 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。
Yan Xie · Tiansheng Wen · Tang Da Huang · Bo Chen · Chenyu You · Stefanie Jegelka · Yifei Wang
Tang Da Huang · Weidong Tang · Wen Qi Xu · Xianpeng Guo
Multimodal Large Language Models typically assume linguistic context invariably enhances visual understanding. We study this assumption in semantic adversarial scenarios, specifically magic tricks, where narration deliberately diverges from physical reality. We introduce MagicBench, a diagnostic...