Researcher — paper.dinq.me

2026 顶会论文

一作ICLR 2026Poster· Applications / Language, Speech and Dialog

LearNAT: Learning NL2SQL with AST-guided Task Decomposition for Large Language Models

Weibin Liao · Xin Gao · Tianyu Jia · Rihong Qiu · Yifan Zhu · Yang Lin · Xinyu Ma · Junfeng Zhao · Yasha Wang

多模态OpenReview

作者位次 #4/8ICLR 2026Poster· Deep Learning / Algorithms

ADEPT: Continual Pretraining via Adaptive Expansion and Dynamic Decoupled Tuning

Jinyang Zhang · Yue Fang · Hongxin Ding · Weibin Liao · Muyang Ye · Junfeng Zhao · Yasha Wang · Xu Chu

数据与预训练OpenReview

作者位次 #4/11ACL 2026Poster· Natural Language Processing

P ro M ed: Shapley Information Gain Guided Reinforcement Learning for Proactive Medical LLM s

Hongxin Ding · Baixiang Huang · Yue Fang · Weibin Liao · Xinke Jiang · Jinyang Zhang · Yinghao Zhu · Zheng Li · Liantao Ma · Junfeng Zhao · Yasha Wang

摘要

Interactive medical questioning is essential in clinical consultations, where physicians must actively gather necessary patient information. Yet existing medical Large Language Models (LLMs) predominantly follow a reactive paradigm, risking diagnostic errors by answering before seeking sufficient...

强化学习与后训练社会与人本可解释性OpenReview 项目页

一作KDD 2026Oral· Knowledge Discovery & Data Mining

HyFunc: Accelerating LLM-based Function Calls for Agentic AI through Hybrid-Model Cascade and Dynamic Templating

Weibin Liao · Jian-Guang Lou · Haoyi Xiong

智能体与工具检索与知识OpenReview

作者位次 #2/6KDD 2026Oral· Knowledge Discovery & Data Mining

APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL

Bowen Cao · Weibin Liao · Yushi Sun · Dong Fang · Haitao Li · Wai Lam

智能体与工具检索与知识代码OpenReview

作者位次 #6/12AAAI 2026Poster· Artificial Intelligence

Toward Better EHR Reasoning in LLMs: Reinforcement Learning with Expert Attention Guidance

Yue Fang · Yuxin Guo · Jiaran Gao · Hongxin Ding · Xinke Jiang · Weibin Liao · Yongxin Xu · Yinghao Zhu · Zhibang Yang · Liantao Ma · Junfeng Zhao · Yasha Wang

推理强化学习与后训练OpenReview

Weibin Liao

获取完整研究档案

联系方式