一作ICML 2026Poster· Deep Learning / Large Language Models
Training Data Efficiency in Multimodal Process Reward Models
Jinyuan Li · Chengsong Huang · Langlin Huang · Shaoyang Xu · Haolin Liu · Wenxuan Zhang · Jiaxin Huang
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。
Jinyuan Li · Chengsong Huang · Langlin Huang · Shaoyang Xu · Haolin Liu · Wenxuan Zhang · Jiaxin Huang
Hongze Mi · Yibo Feng · Wenjie Lu · Song Cao · Jinyuan Li · Yanming Li · Xuelin Zhang · Haotian Luo · Songyang Peng · He Cui · Tengfei Tian · Jun Fang · Hua Chai · Naiqiang Tan
Hongze Mi · Yibo Feng · Wenjie Lu · Yuqi Wang · Jinyuan Li · Song Cao · He Cui · Tengfei Tian · Xuelin Zhang · Haotian Luo · Di Sun · Jun Fang · Hua Chai · Naiqiang Tan · Gang Pan
Graphical User Interface (GUI) agents aim to automate a wide spectrum of human tasks by emulating user interaction. Despite rapid advancements, current approaches are hindered by several critical challenges: data bottleneck in end-to-end training, high cost of delayed error detection, and risk of...