闫凯 👨‍💻

闫凯

讲师|特聘青年研究员|硕士生导师

佛山大学 计算机与人工智能学院

关于我

佛山大学特聘青年研究员、讲师及硕士生导师,佛山市电子政务工程技术研究中心副主任。哈工大博士,曾赴微软亚研联合培养,师从赵铁军与洪小文教授。目前聚焦具身智能(家政机器人)、多智能体建模及数字人文交叉研究。核心参与国家基金及地方政务系统项目,致力于在真实场景中解决实际问题,推动产学研落地。

教育背景

计算机应用博士

2015-09-10
2023-03-22

哈尔滨工业大学-计算学部

联合培养博士生

2015-06-10
2019-11-10

微软亚洲研究院

工学学士

2010-09-01
2014-06-27

哈尔滨工业大学-英才学院(Honor School)

研究兴趣

具身智能 多智能体模拟 大语言模型 AI生成内容检测 数字人文与非物质文化遗产 计算文学 计算音乐学 数据可视化
📚 研究领域

目前的研究工作聚焦于具身智能、数字人文与大语言模型的应用,包括家政机器人、非遗古琴数字化研究、基于大模型的多智能体协作、AI 生成内容检测等。希望能够利用具身智能技术解放人的双手,剥离人的工具意义,帮助人类专注于个性化价值的实现;追求利用数字化技术,为传统文化的数字化保护与传播提供新的工具。

虽然目前发表成果仍然不算显赫,但在国家社科基金、国家自科基金以及地方政务系统建设等项目中的多年实践,让我积累了一定的一线经验。我期待在教学与科研中,与学生一起在真实问题和开放数据中持续打磨能力,在踏实的工作中一点点“长出来”有价值的成果。

代表工作
GRAPHULY: GRAPH U-Nets-Based Multi-Level Graph LaYout featured image

GRAPHULY: GRAPH U-Nets-Based Multi-Level Graph LaYout

Graph layout is a critical component in graph visualization. This paper proposes GRAPHULY, a graph u-nets-based neural network, for end-to-end graph layout generation. GRAPHULY …

avatar
闫凯
BCGL: Binary Classification-Based Graph Layout featured image

BCGL: Binary Classification-Based Graph Layout

Graph layouts reveal global or local structures of graph data. However, there are few studies on assisting readers in better reconstructing a graph from a layout. This paper …

avatar
闫凯
A visual recommendation system for co-authorship social networks featured image

A visual recommendation system for co-authorship social networks

User recommendation plays a crucial role in social network applications such as co-authorship networks. Existing techniques mostly strive to pursue the similarity between nodes or …

avatar
闫凯
Visualizing the uncertainty induced by graph layout algorithms featured image

Visualizing the uncertainty induced by graph layout algorithms

Given a graph structure, different layout algorithms (even different settings of the same algorithm) usually result in different arrangements of vertices, and each layout may …

avatar
闫凯
近期发表
(2026). Personalized sentiment analysis via historical behavior integration: a multi-strategy feature fusion approach. Internaltional Journal of Machine Learning and Cybernetics.
(2022). GRAPHULY: GRAPH U-Nets-Based Multi-Level Graph LaYout. IEICE TRANS. INF. & SYST..
PDF
(2022). BCGL: Binary Classification-Based Graph Layout. IEICE TRANS. INF. & SYST..
PDF
(2019). A visual recommendation system for co-authorship social networks. Journal of Visualization.
(2017). Visualizing the uncertainty induced by graph layout algorithms. PacificVis 2017.