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

Pengpeng Zhao

AAAI 2026ACL 2026KDD 2026SIGIR 2026智能体与工具评测与基准推理对齐与偏好可解释性
新星分资深
30
一作贡献0
核心/参与13
方向广度19
合作网络6
0 一作 · 4 篇 · AAAI 2026 / ACL 2026 / KDD 2026 / SIGIR 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 #5/6ACL 2026Poster· Natural Language Processing

GBV - SQL : Guided Generation and SQL 2 T ext Back-Translation Validation for Multi-Agent T ext2 SQL

Daojun Chen · Xi Wang · Shenyuan Ren · Qingzhi Ma · Pengpeng Zhao · An Liu

摘要

While Large Language Models have significantly advanced Text2SQL generation, a critical semantic gap persists: syntactically valid queries can still misinterpret user intent. To mitigate this challenge, we propose GBV-SQL, a multi-agent framework that introduces Guided Generation with SQL2Text Ba...

智能体与工具评测与基准推理OpenReview 项目页
作者位次 #6/6SIGIR 2026Oral· Information Retrieval (Full)

Contrastive Flow Matching for Collaborative Filtering

Wangyu Jin · Jiansheng Qian · Wenwen Xia · Hongliang He · Guanfeng Liu · Pengpeng Zhao

摘要

Flow Matching (FM) has recently been introduced into generative collaborative filtering due to its potential to capture user preferences. However, existing FM-based methods are often trained with only the standard regression objective in flow matching and lack explicit inter-user supervision. Thi...

对齐与偏好可解释性多模态OpenReview

常见合作者