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

Zongsheng Cao

AAAI 2026×2ACL 2026×2KDD 2026×2ICML 2026推理检索与知识多模态强化学习与后训练智能体与工具
新星分新星
98
一作贡献160
核心/参与29
方向广度19
合作网络12
4 一作 · 7 篇 · AAAI 2026 / ACL 2026 / KDD 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

7
作者位次 #5/14ACL 2026Poster· Natural Language Processing

F low S earch: Advancing Deep Research with Dynamic Structured Knowledge Flow

Yusong Hu · Runmin Ma · Yue Fan · Jinxin Shi · Zongsheng Cao · Yuhao Zhou · Jiakang Yuan · Shuaiyu Zhang · Shiyang Feng · Xiangchao Yan · Shufei Zhang · Wenlong Zhang · LEI BAI · Bo Zhang

摘要

Deep research is an inherently challenging task that demands both breadth and depth of thinking. It involves navigating diverse knowledge spaces and reasoning over complex, multi-step dependencies, which presents substantial challenges for agentic systems. To address this, we propose FlowSearch,...

推理智能体与工具检索与知识OpenReview 项目页
作者位次 #2/5ACL 2026Findings· Findings of ACL

F low RAG : Synergizing Explicit Reasoning via Frequency-Aware Multi-Granularity Graph Flow

Bihao Zhan · Zongsheng Cao · Jie Zhou · Bo Zhang · Liang He

摘要

Graph-based retrieval-augmented generation (GraphRAG) is effective for knowledge-intensive and multi-hop query tasks; however, many existing methods primarily seed entity-based graphs and rely on implicit semantic relevance propagation. This often (i) under-retrieves when user queries are abstrac...

检索与知识推理对齐与偏好OpenReview 项目页
一作KDD 2026Oral· Knowledge Discovery & Data Mining

UniDocVLM: Enhancing Visual Reasoning and Document Understanding for VLM via Reinforcement Learning

Zongsheng Cao · Anran Liu · Jun Xie · Lang Chen · Feng Chen · Zigan Wang

多模态推理强化学习与后训练OpenReview
作者位次 #2/5AAAI 2026Poster· Artificial Intelligence

NumCoKE: Ordinal-Aware Numerical Reasoning over Knowledge Graphs with Mixture-of-Experts and Contrastive Learning

Ming Yin · Zongsheng Cao · Qiqing Xia · Chenyang Tu · Neng Gao

推理效率与系统检索与知识OpenReview

常见合作者