作者位次 #3/5ICLR 2026Poster· Reinforcement Learning / Online
REA-RL: Reflection-Aware Online Reinforcement Learning for Efficient Reasoning
Hexuan Deng · Wenxiang Jiao · Xuebo Liu · Jun Rao · Min Zhang
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。
Hexuan Deng · Wenxiang Jiao · Xuebo Liu · Jun Rao · Min Zhang
Rongqing Jiang · Xuebo Liu · Shengxin Liu · Yutong Wang · Min Zhang · Shimin Tao · Daimeng Wei · Min Zhang
Idiom translation remains a formidable challenge for Large Language Models (LLMs), as the constraints of static parametric memory and the noise in sentence-level retrieval often lead to literal misinterpretations. To address this, we propose DeReA, a detect-retrieve-arbitrate framework. The syste...
Junlin Li · Shuangyong Song · Guodong DU · Ngai Wong · Xuebo Liu · Yongxiang Li · Min Zhang · Jing Li · Xuelong Li
Supervised Fine-Tuning (SFT) accelerates task-specific large language models (LLMs) development, but the resulting proliferation of fine-tuned models incurs substantial memory overhead. Delta compression addresses this by retaining a single pre-trained LLM with multiple compressed delta weights....
Jun Rao · Xuebo Liu · Hexuan Deng · Zepeng Lin · Zixiong Yu · Jiansheng Wei · Xiaojun Meng · Min Zhang
In mathematical reasoning, data selection strategies predominantly rely on static, externally defined metrics, which fail to adapt to the evolving capabilities of models during training. This misalignment limits the efficiency of Supervised Fine-Tuning and Reinforcement Learning. To bridge this g...