作者位次 #4/5ICML 2026Poster· Deep Learning / Large Language Models
GXPO: Group Cross-Lingual Relative Policy Optimization for Code Generation
Linzheng Chai · Jian Yang · Jiajun Wu · Ensheng Shi · Xianglong Liu
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。
Linzheng Chai · Jian Yang · Jiajun Wu · Ensheng Shi · Xianglong Liu
Jiajun Wu · Jian Yang · Wei Zhang · Linzheng Chai · Yuchi Ma · Ensheng Shi · Yuqing Ma · Zhoujun Li · Xianglong Liu
Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, their effectiveness heavily relies on supervised training with extensive labeled (e.g., question-answering pairs) or unlabeled datasets (e.g., code snippets), which are often expensive and di...
Jing Zhang · Lianghong Guo · Yanlin Wang · Terry Yue Zhuo · Yong Wang · Mingwei Liu · Jiachi Chen · Ensheng Shi · Yuchi Ma · Hongyu Zhang · Zibin Zheng
The Development Knowledge Question Answering (Dev Knowledge QA) task aims to provide accurate natural language answers to knowledge-seeking questions during software development. To investigate the importance of Dev Knowledge QA in AI-assisted software development and the extent to which it has b...