作者位次 #2/7NeurIPS 2026Poster
Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
Qianhao Yuan · Jie Lou · XingYu Li · Hongyu Lin · Le Sun · Xianpei Han · Yaojie Lu
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。
Qianhao Yuan · Jie Lou · XingYu Li · Hongyu Lin · Le Sun · Xianpei Han · Yaojie Lu
Qianhao Yuan · Jie Lou · Zichao Li · Jiawei Chen · Yaojie Lu · Hongyu Lin · Le Sun · Debing Zhang · Xianpei Han
LLM-based search agents often concatenate the full interaction history into the context, producing long and noisy inputs, and increasing compute cost and GPU memory overhead. To address this issue, we propose MemSearcher, an agent framework that maintains a compact memory during multi-turn intera...