Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining
Weimin Xiong · Shuhao Gu · Bowen Ye · Zihao Yue · Lei Li · Feifan Song · Sujian Li · Hao Tian
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。
Weimin Xiong · Shuhao Gu · Bowen Ye · Zihao Yue · Lei Li · Feifan Song · Sujian Li · Hao Tian
Rang Li · Lei Li · Shuhuai Ren · Hao Tian · Shuhao Gu · Shicheng Li · Zihao Yue · Yudong Wang · Wenhan Ma · Zhe Yang · Jingyuan Ma · Zhifang Sui · Fuli Luo
Ziheng Wang · Zihao Yue · Wenxuan Wang · Qin Jin
This paper explores attention attractors —tokens that draw significantly high attention—in large language models. We analyze them from three perspectives: (1) Functionality : We demonstrate their role in aggregating information from preceding contexts to facilitate future predictions. (2) Distrib...
Yichen Xu · Liangyu Chen · Liang Zhang · Zihao Yue · Jianzhe Ma · Wenxuan Wang · Qin Jin
Charts are a universally adopted medium for data communication, yet existing chart understanding benchmarks are overwhelmingly English-centric, limiting their accessibility and relevance to global audiences. To address this limitation, we introduce PolyChartQA, the first large-scale multilingual...
Liangyu Chen · Yichen Xu · Jianzhe Ma · Yuqi Liu · Donglu Yang · Liang Zhang · Zihao Yue · Wenxuan Wang · Qin Jin