一作ICML 2026Poster· Reinforcement Learning / Multi-agent
PADD: Path-Aligned Decompression Distillation for Non-Router Teacher to Guide MoE Student Learning
Xinyue Peng · Yi Qian · Jiaojiao Lin · Wenjian Shao · Yanming 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。
Xinyue Peng · Yi Qian · Jiaojiao Lin · Wenjian Shao · Yanming Liu
Yanming Liu · Xinyue Peng · Jiannan Cao · Xinyi Wang · Songhang Deng · Jintao Chen · Jianwei Yin · Xuhong Zhang
Large Language Models (LLMs) augmented with external tools have demonstrated remarkable capabilities in complex reasoning tasks. However, existing frameworks rely heavily on natural language reasoning to determine when tools can be invoked and whether their results should be committed, lacking fo...