作者位次 #6/8ICML 2026Poster· Deep Learning / Generative Models and Autoencoders
Stabilizing Reinforcement Learning for Diffusion Language Models
Jianyuan Zhong · Wang Kaibo · Ding Ding · Zijin Feng · Haoli Bai · Yang Xiang · Jiacheng Sun · Qiang Xu
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。
Jianyuan Zhong · Wang Kaibo · Ding Ding · Zijin Feng · Haoli Bai · Yang Xiang · Jiacheng Sun · Qiang Xu
Zaiyuan Di · Jianting Chen · Yunxiao Yang · Xiaoying Gao · Li Yang · Zhihao Wang · Yang Xiang
While recent studies have increasingly emphasized the role of reflection in code repair tasks, existing benchmarks still target the repair generation capability of LLMs, lacking fine-grained evaluation of reflection generation capability. To this end, we propose Code Reffix, a benchmark featuring...