ExGRPO: Learning to Reason from Experience
Runzhe Zhan · Yafu Li · Zhi Wang · Xiaoye Qu · Dongrui Liu · Jing Shao · Derek Wong · Yu Cheng
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。
Runzhe Zhan · Yafu Li · Zhi Wang · Xiaoye Qu · Dongrui Liu · Jing Shao · Derek Wong · Yu Cheng
Xin Chen · Junchao Wu · Shu Yang · Runzhe Zhan · Zeyu Wu · Min Yang · Shujian Huang · Lidia Chao · Derek Wong
Jingkun Ma · Runzhe Zhan · Yang Li · Di Sun · Hou Pong Chan · Lidia S. Chao · Derek F. Wong
A hallmark of advanced artificial intelligence is the capacity to progress from passive visual perception to the strategic modification of visual information to facilitate complex reasoning. This advanced capability, however, remains critically underdeveloped in current Large Multi-modal Models (...
Fengying Ye · Yanming Sun · Runzhe Zhan · Lidia S. Chao · Zheqi Zhang · Derek F. Wong
Idioms are difficult to transfer across languages due to their non-compositionality and weak surface-form grounding, making literal mappings unreliable. We present G-IdiomAlign, a gloss-pivoted benchmark where each idiom is anchored by an English gloss from Wiktionary. We further construct a high...
Yanming Sun · Runzhe Zhan · Chi Seng Cheang · Han Wu · Xuebo Liu · Yuyao Niu · Fengying Ye · Kaixin Lan · Lidia S. Chao · Derek F. Wong