paper.dinq.meAI 与前沿科学顶会 · 学术新星雷达
登录 DINQ
返回新星榜
MF

Mingxiao Feng

ACL 2026×2ICML 2026推理强化学习与后训练多模态评测与基准效率与系统
新星分贡献者
49
一作贡献0
核心/参与15
方向广度13
合作网络9
0 一作 · 3 篇 · ACL 2026 / ICML 2026

获取完整研究档案

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。

联系方式

实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。

2026 顶会论文

3
作者位次 #6/8ACL 2026Findings· Findings of ACL

C ode C ontests- O : Powering LLM s via Feedback-Driven Iterative Test Case Generation

Jianfeng Cai · Jinhua Zhu · Ruopei Sun · Kangwen Zhao · Dongyun Xue · Mingxiao Feng · Wengang Zhou · Houqiang Li

摘要

The rise of reasoning models necessitates large-scale verifiable data, for which programming tasks serve as an ideal source. However, while competitive programming platforms provide abundant problems and solutions, high-quality test cases for verification remain scarce. Existing approaches attemp...

推理强化学习与后训练评测与基准OpenReview 项目页
作者位次 #4/8ACL 2026Findings· Findings of ACL

SGA - MCTS : Decoupling Planning from Execution via Training-Free Atomic Experience Retrieval

Xin Xie · Dongyun Xue · Wuguannan Yao · Mingxiao Feng · Wengang Zhou · Xiang Qi · Houqiang Li · Peng Zhang

摘要

LLM-powered systems require complex multi-step decision-making abilities to solve real-world tasks, yet current planning approaches face a trade-off between the high latency of inference-time search and the limited generalization of supervised fine-tuning. To address this limitation, we introduce...

推理强化学习与后训练效率与系统OpenReview 项目页

常见合作者