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

Junting Lu

ACL 2026×2AAAI 2026推理评测与基准智能体与工具强化学习与后训练安全
新星分贡献者
55
一作贡献0
核心/参与22
方向广度13
合作网络9
0 一作 · 3 篇 · ACL 2026 / AAAI 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 #2/8ACL 2026Poster· Natural Language Processing

Metaphor Reasoning is Meta-reasoning

Qianyu He · Junting Lu · Yikai Zhang · Siyu Yuan · Xiaojun Meng · Jiansheng Wei · Jiaqing Liang · Yanghua Xiao

摘要

Metaphor reasoning is an essential cognitive ability that maps knowledge from familiar domains to more abstract domains. This ability functions as a meta-ability underlying many types of reasoning. However, existing work rarely investigates how metaphor reasoning affects other reasoning abilities...

智能体与工具强化学习与后训练推理OpenReview 项目页
作者位次 #5/9ACL 2026Poster· Natural Language Processing

Gradient-Guided Multi-Judge Prompt Optimization

ChenZhuo Zhao · Xinda Wang · Pu Zhao · Yue Huang · Junting Lu · Ziqian Liu · Qingwei Lin · Saravan Rajmohan · Dongmei Zhang

摘要

Automatic prompt optimization is a practical alternative to fine-tuning for adapting large language models (LLMs), yet existing approaches often trade off signal quality against computational cost. Methods that rely on generative feedback can be informative but expensive to scale, while sampling-...

评测与基准推理安全OpenReview 项目页

常见合作者