作者位次 #5/6ICLR 2026Poster· Computer Vision / Vision Models & Multimodal
Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models
Jianghao Yin · Qin Chen · Kedi Chen · Jie Zhou · Xingjiao Wu · Liang He
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。
Jianghao Yin · Qin Chen · Kedi Chen · Jie Zhou · Xingjiao Wu · Liang He
Dongliang Chen · Xinlin Zhuang · Junjie Xu · Luojian Xie · Zehui Wang · Jiaxi Zhuang · Haolin Yang · Liang Dou · Xiao He · Xingjiao Wu · Ying Qian
Multi-objective alignment for text-to-image generation is commonly implemented via static linear scalarization, but fixed weights often fail under heterogeneous rewards, leading to optimization imbalance where models overfit high-variance, high-responsiveness objectives (e.g., OCR) while under-op...