作者位次 #3/9NeurIPS 2026Poster
Heads That Write, Not Just Point: Image Retrieval Heads in Vision-Language Models
Junsung Park · Uiwon Hwang · Donghun Kang · Yeongtak Oh · Jaewon Jeong · Gyeongtae Yoo · Han Cheol Moon · Jungbeom Lee · Sungroh Yoon
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。
Junsung Park · Uiwon Hwang · Donghun Kang · Yeongtak Oh · Jaewon Jeong · Gyeongtae Yoo · Han Cheol Moon · Jungbeom Lee · Sungroh Yoon
Sangkwon Park · Donghun Kang · Jisoo Mok · Sungroh Yoon
The conventional Retrieval-Augmented Generation (RAG) paradigm of injecting raw retrieved texts into the Large Language Model (LLM)’s context often results in suboptimal integration of retrieved information. This paper proposes to bridge retrieval results and the LLM’s reasoning ability through V...