计算机学院教职工、东南大学复杂工程系统测量与控制教育部重点实验室 (MCCES, Ministry of Education) 模式识别与智能系统 (PRIS) 工学博士、美国内华达大学(维加斯分校) 霍华德·休斯工学院 (Howard R. Hughes College of Engineering) 电子与计算机工程 (Electrical and Computer Engineering, ECE) 工学博士后 (Postdoc Fellow/Postdoctoral Researcher)、美国国家博士后协会 (NPA) 会员、南京边缘智能研究院首席科学家与技术总监(兼)、学术桥/五思云/知网评审专家库成员、教育部学位中心本科/硕士/博士学位论文评审专家、江苏省计算机学会会员、江苏省网络空间安全学会会员、数字化智能应用研究所成员、物联网工程系副主任、江苏科技大学副教授、学术型硕士研究生导师(计算机科学与技术, 软件工程, 人工智能)、专业型硕士研究生导师(电子信息, 人工智能). 连续多年年度教职工考核优秀,曾获校优秀学业导师称号, 曾任 NASA EPSCoR 项目评阅专家以及美国内华达州交通部南部铁路技术测评人员(FRA 49 CFR Part 243).

i) 研究方向聚焦于下一代人工智能的数学基础、量子智能、几何智能与科学智能计算，围绕人工智能理论、量子神经网络、几何深度学习、科学智能（AI for Science / Science for AI）以及复杂系统智能建模开展研究。

ii) 长期致力于探索李群/李代数、黎曼几何、拓扑谱理论等数学结构驱动的可解释人工智能方法，研究量子机器学习、参数化量子电路优化、智能模型结构压缩与高效计算理论；同时面向生命科学、物理系统和工程领域，开展几何生物信息学、蛋白质结构与动力学智能分析、物理智能建模以及复杂工程系统智能优化研究。

相关研究成果已形成多个开源项目，包括量子智能、几何人工智能和科学智能计算框架。部分代码及学术成果已公开：

代码仓库：https://github.com/Harmenlv?tab=repositories

相关论文：https://scholar.google.com/citations?user=d3mvChQAAAAJ&hl=en

工作与社会服务经历

曾任 NASA EPSCoR 项目评阅专家(科研项目评审)

曾任 Olive Crest 州福利院志愿者(公益与社会服务活动)

担任 教育部学位中心本科/硕士/博士学位论文评审专家

担任 泰晤士高等教育(THE)全球学术评议人员(国际学术评估)

兼任 南京边缘智能研究院首席科学家与技术总监(科研与技术规划)

曾任 美国内华达州交通部南部铁路技术测评人员(FRA 49 CFR Part 243)

曾任美国 Brightline West 高速铁路项目测试人员，开展特殊车站实地测试与运营测量

曾任 技术咨询考察联合太平洋铁路公司(Union Pacific Railroad)加州巴斯特大型编组站

科研与教学成果

主持国家自然基金 1 项（已结题）

主持江苏省高校自然科学研究面上项目 1 项（已结题）

第一作者及通讯作者发表 SCI 期刊论文60余篇

第一作者出版学术专著 1 部以及第一申请人申请与授权发明专利 10 余项

第一指导教师指导硕研/本科获2019~2025年数模/电子设计赛/物联网设计赛等国赛/美赛/省赛一/二/三等奖10余次

代表性系统与项目经验

模块化船体三维建模与检验软件系统, 面向复杂工业结构建造精度管控，主导研发多源点云统一处理与三维可视化系统，支持大型系统离线/在线部署。

工业智能运维安全演练与虚实联动系统, 聚焦工业软件安全与智能运维，融合 AI 视觉巡检与三维场景可视化，构建虚拟—物理协同的安全演练架构。

大型装备项目目标完成度与技术成熟度评估系统, 构建覆盖虚拟仿真与现场试验阶段的目标完成度与 TRL 评估方法，为复杂工程项目提供量化决策支持。

工业仿真参数建模与可视化配置工具, 面向工业电弧测试，开发与 Fluent 平台协同的参数管理与可视化配置软件。

Ph.D. in Engineering (Pattern Recognition and Intelligent Systems), Southeast UniversityPostdoctoral Fellow/Researcher in Electrical and Computer Engineering, University of Nevada, Las Vegas (UNLV), USAMember of the National Postdoctoral Association (NPA, USA), Jiangsu Computer Society, and Jiangsu Cybersecurity SocietyMember of the Expert Review Panel for Academic Bridge, Wusi Cloud, and CNKI; Expert Reviewer for Undergraduate/Master/Ph.D. Dissertations, Academic Degrees Evaluation Center of the Ministry of Education, ChinaMember of the Institute of Digital Intelligent ApplicationsChief Scientist and Technical Director, Nanjing Edge Intelligence Research InstituteAssociate Professor, Deputy Director of the Internet of Things Engineering Department, Jiangsu University of Science and TechnologyAcademic Master’s Supervisor (Computer Science and Technology, Software Engineering, Artificial Intelligence); Professional Master’s Supervisor (Electronic Information, Artificial Intelligence) 

Professional & Academic Services Experience

Railway Employee at the Southern Division of Nevada Department of Transportation (Compliant with FRA 49 CFR Part 243)

Reviewer for NASA Experimental Program to EPSCoR Projects

Global Academic Reviewer for Times Higher Education (THE)

Volunteer at NV Olive Crest Welfare Institute

Participant in the field tests and station operation measurement of special stations for Brightline West's first high-speed railway project in the U.S.

Technical Consultant for the inspection of the largest marshalling yard of Union Pacific Railroad Inc. in Barstow, California

Research & Academic Achievements

Principal Investigator of 1 National Natural Science Foundation of China project (Completed)

Principal Investigator of 1 General Project of Natural Science Research in Jiangsu Provincial Universities (Completed)

Over 50 SCI journal papers as the first/corresponding author

Author of 1 academic monograph as the first authorFirst applicant for more than 10 invention patents (granted and pending)

First supervisor guiding students to win over 10 national/provincial/international awards (e.g., Mathematical Modeling Competition, Electronic Design Competition, IoT Design Competition) during 2019–2025

Systems and Project Experience

Modular Ship Hull 3D Modeling and Inspection System
 Targeting construction accuracy control for complex industrial structures, led the development of a unified multi-source point cloud processing and 3D visualization system, supporting both offline and online deployment for large-scale applications.

Industrial Intelligent Operation and Maintenance Security Drill System with Virtual–Physical Integration
 Focusing on industrial software security and intelligent operation and maintenance, integrated AI-based visual inspection with 3D scene visualization to construct a virtual–physical collaborative architecture for security drills and validation.

Project Completion and Technology Readiness Assessment System for Large-Scale Equipment
 Developed project completion assessment and Technology Readiness Level (TRL) evaluation methods covering both virtual simulation and on-site testing stages, providing quantitative decision support for complex engineering projects.

Industrial Simulation Parameter Modeling and Visual Configuration Tool
 Targeting industrial arc testing scenarios, developed a parameter management and visual configuration tool interoperable with the Fluent simulation platform.

主要科研方向：

面向下一代人工智能（Next Generation Artificial Intelligence）的数学理论、几何智能、量子智能与科学智能研究，主要包括：

i) 量子人工智能与可扩展量子机器学习（Quantum AI & Scalable Quantum Machine Learning）

参数化量子电路（Parameterized Quantum Circuits, PQC）结构优化、量子神经网络（Quantum Neural Networks, QNN）、量子机器学习理论、量子表示学习、量子智能架构自动生成；基于李群/李代数理论的量子动力学分析、量子模型压缩、量子剪枝与量子训练可行性理论，探索量子计算与人工智能融合的新型智能计算范式。

ii) 几何智能与数学基础人工智能（Geometric Intelligence & Mathematical Foundations of AI）

黎曼流形几何建模、李群/李代数智能动力学、微分几何驱动白盒人工智能（White-box AI）、拓扑谱分析、流形约束表征学习、对称保持神经网络（Symmetry-Preserving Neural Networks）以及代数结构驱动的可解释智能学习理论。

iii) 科学智能与AI for Science / Science for AI（Scientific Intelligence）

面向生命科学、物理科学与复杂系统的人工智能建模，研究科学知识驱动的智能模型构建方法；探索从 AI 辅助科学发现（AI for Science）到科学理论反哺人工智能（Science for AI）的双向融合机制，发展具有数学结构、物理规律和可解释性的科学智能框架。

iv) 几何生物信息学与生命智能计算（Geometric Bioinformatics & Biological Intelligence）

蛋白质折叠动力学建模、生物大分子结构智能预测、突变致病性的几何机制解析、拓扑光谱缺陷理论、蛋白质语言模型与几何深度学习融合方法，构建面向精准医学和生命科学发现的新型智能计算体系。

v) 物理智能与世界模型（Physical Intelligence & World Models）

面向具身智能（Embodied Intelligence）和复杂环境交互的智能计算理论，研究物理规律约束的世界模型、动力系统学习、几何力学系统分析、多模态智能感知与推理方法，实现从数字智能向物理世界智能的拓展。

vi) 定理驱动与可解释人工智能（Theorem-driven Explainable AI）

研究基于数学定理、群表示理论、谱理论和几何约束的下一代人工智能方法，探索可证明、可解释、可验证的智能系统，包括梯度动力学理论、表达能力分析、结构冗余识别以及智能模型可靠性理论。

vii) 智能计算系统与未来计算架构（Intelligent Computing Systems）

研究面向未来AI发展的高性能智能计算架构，包括量子-经典混合计算、边缘智能、云端协同计算、AI模型高效部署、智能体（AI Agent）系统以及面向复杂任务的新型计算范式。

代码仓库：https://github.com/Harmenlv?tab=repositories

相关论文：https://scholar.google.com/citations?user=d3mvChQAAAAJ&hl=en

Research Interests

My research focuses on next-generation artificial intelligence (Next-Generation AI), including quantum intelligence, geometric intelligence, scientific intelligence, and trustworthy AI. The research aims to develop mathematically grounded, interpretable, and efficient intelligent systems by integrating theories from geometry, algebra, physics, and computational science.

i) Quantum Artificial Intelligence and Scalable Quantum Machine Learning

(Quantum AI & Scalable Quantum Machine Learning)

Research on quantum neural networks (QNNs), parameterized quantum circuits (PQCs), quantum machine learning, quantum representation learning, and quantum intelligent architectures.
 Investigate quantum-classical hybrid computing paradigms, Lie group/Lie algebra based quantum dynamics analysis, quantum model compression, quantum pruning, and trainability theories for scalable quantum artificial intelligence systems.

ii) Geometric Intelligence and Mathematical Foundations of AI

(Geometric Intelligence & Mathematical Foundations of AI)

Research on Riemannian manifold modeling, Lie group and Lie algebra based intelligent dynamics, differential geometry-driven white-box artificial intelligence (White-box AI), topological spectral analysis, manifold-constrained representation learning, symmetry-preserving neural networks, and interpretable learning theories driven by algebraic structures.

iii) Scientific Intelligence and AI for Science / Science for AI

(Scientific Intelligence)

Develop artificial intelligence models for life sciences, physical sciences, and complex systems by incorporating scientific knowledge and mathematical principles into intelligent learning frameworks.

Explore the bidirectional interaction between AI for Science, where artificial intelligence accelerates scientific discovery, and Science for AI, where scientific theories inspire new AI architectures and learning mechanisms. Develop scientific intelligence frameworks with mathematical structures, physical constraints, and interpretability.

iv) Geometric Bioinformatics and Biological Intelligence Computing

(Geometric Bioinformatics & Biological Intelligence)

Research on protein folding dynamics modeling, intelligent prediction of biomolecular structures, geometric mechanisms underlying pathogenic mutations, topological spectral defect theory, and integration of protein language models with geometric deep learning.

Develop novel intelligent computational frameworks for precision medicine, biological discovery, and quantitative analysis of molecular mechanisms.

v) Physical Intelligence and World Models

(Physical Intelligence & World Models)

Research on intelligent computing theories for embodied intelligence and complex environment interaction.

Investigate physics-informed world models, dynamical system learning, geometric mechanics analysis, multimodal intelligent perception and reasoning, aiming to extend artificial intelligence from digital environments toward physical-world intelligence.

vi) Theorem-driven and Explainable Artificial Intelligence

(Theorem-driven Explainable AI)

Develop next-generation AI methods based on mathematical theories, including theorem-driven learning, group representation theory, spectral theory, and geometric constraints.

Explore provable, interpretable, and reliable intelligent systems, including gradient dynamics theories, expressive capability analysis, structural redundancy identification, and reliability evaluation of intelligent models.

vii) Intelligent Computing Systems and Future Computing Architectures

(Intelligent Computing Systems)

Research future-oriented intelligent computing architectures, including quantum-classical hybrid computing, edge intelligence, cloud-edge collaborative computing, efficient AI model deployment, AI agents, and novel computing paradigms for complex intelligent tasks.

Representative Research and Software Systems

Modular Ship Hull 3D Modeling and Inspection Methods and Software System
 Led the research and development of a modular ship hull 3D modeling and inspection software framework supporting both offline and online deployment for large-scale systems. Focusing on key challenges in construction accuracy control, proposed unified processing and modeling methods for multi-source radar point cloud data, and established an integrated technical framework encompassing basic information management, inspection data management, and 3D visualization.

Industrial Intelligent Operation and Maintenance Security Drills with Virtual–Physical Integration
 Led the research on security drill methodologies and system implementation for industrial intelligent operation and maintenance scenarios. Targeting full-process attack–defense drills for industrial software vulnerabilities, explored the deep integration of AI-based visual inspection and 3D scene visualization, and constructed a virtual–physical collaborative architecture for immersive security training and validation.

Project Completion and Technology Readiness Assessment Methods for Large-Scale Equipment Systems
 Led the research on full-lifecycle evaluation methods for large-scale equipment projects. Developed indicator systems for project objective completion assessment and Technology Readiness Level (TRL) evaluation, supporting multi-stage scenarios such as virtual simulation-based validation and on-site experimental testing, and providing quantitative decision support for complex engineering projects.

Modeling and Visual Configuration of Industrial Arc Simulation Parameters
 Led the research on modeling and visual configuration methods for industrial arc simulation parameters. Developed a parameter management and visualization tool interoperable with the Fluent industrial simulation platform, enabling structured parsing and visual representation of complex simulation parameters, and proposed a C/C++ parameter file parsing mechanism based on regular expressions.

(A complete list of published works can be found:https://scholar.google.com/citations?user=d3mvChQAAAAJ&hl=en )

工学博士 (Ph.D., Doctor of Engineering, Recipient of the Phoenix Scholarship)

理学硕士 (M.S., Master of Science in Natural Sciences, Recipient of the Outstanding Master's Thesis, Excellent Graduate and First-Class Scholarship)

管理学学士 (B.S., Bachelor of Science in Management, Recipient of the Subject-Specific Scholarship)

2016～2017第1学期，本科生课程《数字与电子取证》

2016～2017第2学期，研究生课程《图像理解与分析》

2017～2018第1学期，本科生课程《信安数学》《离散数学》

2017～2018第2学期，本科生课程《数字与电子取证》、研究生课程《图像理解与分析》

2018～2019第1学期，本科生课程《信安数学》《离散数学》

2018～2019第2学期，留学生课程《Operating Systems》、本科生课程《离散数学》

2019～2020第2学期，本科生课程《离散数学》

2020～2021第1学期，本科生课程《通信原理》《信号通信与控制系统》

2020～2021第2学期，研究生课程《神经网络与量子计算》、研究生课程《通信技术》

2021～2022第1学期，本科生课程《信号通信与控制系统》

2021～2022第2学期，本科生课程《信安数学》

2023～2024第2学期，研究生课程《通信技术》、留学生课程《Operating Systems》

2024～2025第1学期，本科生课程《物联网通信技术》

2024～2025第2学期，本科生课程《信安数学》、研究生课程《通信技术》

2025～2026第1学期，留学生课程《Computer Organization and Architecture》