一作ICML 2026Poster· Social Aspects / Alignment
Language Bias in LVLMs: From In-Depth Analysis to Simple and Effective Mitigation
Yangneng Chen · Jing 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。
Yangneng Chen · Jing Li
Yangneng Chen · Junlin Li · Weijun Yao · Xilai Ma · Guodong DU · Wenya Wang · Jing Li
Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal tasks, yet their reliability is persistently undermined by hallucinations—generating text that contradicts visual input. Recent studies often attribute these errors to inadequate visual attention. In this work, w...