一作ICML 2026Poster· Deep Learning / Attention Mechanisms
Not All Answers Are Contextually Persuadable: Inference Dynamics in Large Language Models under Contextual Influence
Zongye Hu · Weiqing Luo · Yanjie Fu · Yu Gan · Haofeng Zhang · Ziyi Huang
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。
Zongye Hu · Weiqing Luo · Yanjie Fu · Yu Gan · Haofeng Zhang · Ziyi Huang
Weiqing Luo · Zongye Hu · Xiao Wang · Zhiyuan Yu · Haofeng Zhang · Ziyi Huang
Visual evidence selection is a critical component of multimodal retrieval-augmented generation (RAG), yet existing methods typically rely on semantic relevance or surface-level similarity, which are often misaligned with the actual utility of visual evidence for downstream reasoning. We reformula...