作者位次 #2/6ICLR 2026Poster
OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning
Mingxin Huang · Yongxin Shi · Dezhi Peng · Songxuan Lai · Zecheng Xie · Lianwen Jin
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。
Mingxin Huang · Yongxin Shi · Dezhi Peng · Songxuan Lai · Zecheng Xie · Lianwen Jin
Jiahuan Cao · Yongxin Shi · Zeyu Shan · Zhengyang Lu · Lianwen Jin
Chinese historical documents encode millennia of cultural heritage, yet remain largely inaccessible to computational analysis. While multimodal large language models (MLLMs) have achieved strong performance on modern document OCR, their application to historical Chinese texts suffers from severe...
Yongxin Shi · Jiapeng Wang · Zeyu Shan · Dezhi Peng · Zening Lin · Lianwen Jin