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

Chang Yao

ACL 2026×2AAAI 2026ICLR 2026代码可解释性智能体与工具强化学习与后训练对齐与偏好
新星分贡献者
61
一作贡献0
核心/参与27
方向广度16
合作网络9
0 一作 · 4 篇 · ACL 2026 / AAAI 2026 / ICLR 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

4
作者位次 #4/6ACL 2026Poster· Natural Language Processing

QB ridge: Bridging Natural Language and SQL via Gold Query Rewriting with Agentic Refinement

Zhensheng Luo · Sai Wu · Yuan Qiu · Chang Yao · Gang Chen · Xiu Tang

摘要

Natural language to SQL (NL2SQL) provides an intuitive interface for querying structured data, yet real user questions are often noisy, ambiguous, and weakly grounded to database semantics.As a result, token-level schema linking and single-pass SQL decoding can be brittle: small misunderstandings...

代码可解释性智能体与工具OpenReview 项目页
作者位次 #6/7ACL 2026Poster· Natural Language Processing

Enhancing Reinforcement Learning for Radiology Report Generation with Evidence-aware Rewards and Self-correcting Preference Learning

Qin Zhou · Guoyan Liang · Qianyi Yang · Jingyuan Chen · Sai Wu · Chang Yao · Zhe Wang

摘要

Recent reinforcement learning (RL) approaches have advanced radiology report generation (RRG), yet two core limitations persist: (1) report-level rewards offer limited evidence-grounded guidance for clinical faithfulness; and (2) current methods lack an explicit self-improving mechanism to align...

强化学习与后训练对齐与偏好社会与人本OpenReview 项目页

常见合作者