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。
Zhuo Li · Guodong DU · Weiyang Guo · Yigeng Zhou · Xiucheng Li · Wenya Wang · Fangming Liu · Yequan Wang · Deheng Ye · Min Zhang · Jing Li
Weiyang Guo · Zesheng Shi · Zeen Zhu · Yuan Zhou · Min Zhang · Jing Li
Reinforcement Learning with Verifiable Rewards (RLVR) is an emerging paradigm that significantly boosts a Large Language Model’s (LLM’s) reasoning abilities on complex logical tasks, such as mathematics and programming. However, we identify, for the first time, a latent vulnerability to backdoor...
Weiyang Guo · Zesheng Shi · Liye Zhao · Jiayuan Ma · Zeen Zhu · Junxian He · Min Zhang · Jing Li
While Large Language Models (LLMs) have demonstrated significant potential in Tool-Integrated Reasoning (TIR), existing training paradigms face significant limitations: Zero-RL suffers from inefficient exploration and mode degradation due to a lack of prior guidance, while SFT-then-RL is limited...
Zhuo Li · Guodong DU · Zesheng Shi · Weiyang Guo · Weijun Yao · Yuan Zhou · Jiabo Zhang · Jing Li
In this work, we introduce SkillWeave, a modular improvement framework that enables large language models to specialize under fixed memory budgets. SkillWeave partitions full capabilities of a general-purpose model into domain-specific skillpacks—lightweight, domain-specific delta modules—that re...