作者位次 #2/6NeurIPS 2026Poster· Computer Vision / Vision Models & Multimodal
Where Are MLLMs Looking When They Hallucinate? Mitigating Visual Hallucination via Gaze Steering
Yebo Wu · Han Jin · Feng Liu · Changwang Zhang · Jun Wang · Li Li
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。
Yebo Wu · Han Jin · Feng Liu · Changwang Zhang · Jun Wang · Li Li
Yebo Wu · Han Jin · Zhijiang Guo · Li Li
Multimodal Large Language Models (MLLMs) have demonstrated remarkable reasoning capabilities yet continue to suffer from hallucination, where generated text contradicts visual content. In this paper, we introduce Dual-Anchor Introspective Decoding (DaID), a novel contrastive decoding framework th...