作者位次 #2/4ICLR 2026Poster· Reinforcement Learning / Everything Else
Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMs
Shulin Huang · Yiran Ding · Junshu Pan · Yue 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。
Shulin Huang · Yiran Ding · Junshu Pan · Yue Zhang
Zhen Lin · Qiujie Xie · Minjun Zhu · Shichen Li · QiYao Sun · Enhao Gu · Yiran Ding · Ke Sun · Fang Guo · Panzhong Lu · Zhiyuan Ning · Yixuan Weng · Yue Zhang
High-quality scientific illustrations are essential for communicating complex scientific and technical concepts, yet existing automated systems remain limited in editability, stylistic controllability, and efficiency. We present AutoFigure-Edit, an end-to-end system that generates fully editable...
Zhenghua Wang · Yiran Ding · Changze Lv · Yixin Wu · Tianlong Li · Zhibo Xu · Muling Wu · Tianyuan Shi · Shizheng Li · Qi Qian · Xuanjing Huang · Xiaoqing Zheng
Large Language Models (LLMs) still struggle with the “lost-in-the-middle” problem, where critical information located in the middle of long-context inputs is often underrepresented or lost. While existing methods attempt to address this by combining multi-scale rotary position embeddings (RoPE),...