一作ICLR 2026Poster· Computer Vision / Vision Models & Multimodal
SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense
Yiyang Huang · Liang Shi · Yitian Zhang · Yi Xu · Yun Fu
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。
Yiyang Huang · Liang Shi · Yitian Zhang · Yi Xu · Yun Fu
Yiyang Huang · Yitian Zhang · Yizhou Wang · Mingyuan Zhang · Liang Shi · Huimin Zeng · Yun Fu
Despite significant progress in video-language modeling, hallucinations remain a persistent challenge in Video Large Language Models (Vid-LLMs), referring to outputs that appear plausible yet contradict the content of the input video. This survey presents a comprehensive analysis of hallucination...