Tenured Professor, Doctoral Supervisor, Tongji University

Brief Introduction

Haofen Wang is a tenured Professor and PhD Supervisor at Tongji University, focusing on research in knowledge graphs and knowledge-enhanced large language models. His core achievements include OpenSPG, an enterprise-level open-source knowledge graph, KAG-Thinker, the world’s first open-source knowledge-enhanced reasoning model with more than 10,000 GitHub stars, MemOS, a native operating system for large model memory with over 500,000 daily calls, and AI-Ceping, a crowdsourcing platform for large model evaluation with 300,000 monthly active users, which have been applied in scenarios such as airport operation control, financial risk management and intelligent cockpit interaction. In the past five years, he has published 3 academic monographs and 45 papers as first or corresponding author in top-tier conferences and journals including CVPR, WWW, ICLR, ACL, AAAI and IJCAI, with his Google Scholar citations exceeding 11,000 and a single paper cited more than 5,000 times, and he has received awards such as the Best Student Paper Award at DASFAA 2025 and the Best Paper Award at HCII 2024. He has presided over 4 ministerial and provincial-level projects including the National Key R&D Program of China for Next-Generation Artificial Intelligence, Key and General Programs of the National Natural Science Foundation of China, and the Shanghai Special Zone Program for Basic Research, and has been granted 8 authorized patents. He has taught 9 undergraduate and graduate courses and supervised nearly 40 students at the bachelor’s, master’s and doctoral levels. His honors include the First Prize of Science and Technology Progress from the China Communications and Transportation Association, the Silver Award of the MUSE Creative Awards, and the Third Prize of Science and Technology Progress from the China Computer Federation (CCF). He serves as the inaugural rotating chair of OpenKG, the largest Chinese open knowledge graph community, Executive Editor of Data Intelligence, Secretary-General of the CCF Technical Committee on Natural Language Processing, and Deputy Secretary-General of the CIPS Technical Committee on Language and Knowledge Computing. He has delivered invited talks at IJCAI, VLDB, the World Artificial Intelligence Conference, the China Computer Congress and other academic venues, and has long been committed to promoting academic innovation and industrial translation in the fields of knowledge graphs and large language models

Research

Knowledge Graphs

Natural Language Processing

Retrieval-Augmented Generation

Knowledge-Enhanced Large Language Models

Teaching

Undergraduate courses: Python Programming, Professional Design, Interaction Design

Graduate courses: Innovation Design & Entrepreneurship Frontiers, Innovation Project Practice, Design Practice Research

Academic and social Post

[1] Rotating Chair, OpenKG Knowledge Graph Community (2024–2026)

[2] Chair, Technical Committee, OpenMem Memory-Centric AI System Open-Source Community (2025–present)

[3] Executive Editor-in-Chief, Data Intelligence journal (2024–present)

[4] Associate Editor, Knowledge Engineering & Review journal (2025–present)

[5] Secretary-General, CCF (China Computer Federation) Technical Committee on Natural Language Processing (2024–2027)

[6] Chair, CCF Technical Frontier — Knowledge Graph Special Interest Group (2024–2027)

[7] Deputy Director, CCF Terminology Review Working Committee (2024–2026)

[8] Member, CCF Academic Affairs Committee (2024–2026)

[9] Standing Committee Member, CCF Technical Committee on Information Systems (2024–2027)

[10] Council Member, Chinese Information Processing Society of China (CIPS) (2021–2026)

[11] Deputy Secretary-General, CIPS Special Committee on Language and Knowledge Computing (2021–2026)

[12] Program Committee Chair, IJCNLP-AACL 2025 (International Joint Conference on Natural Language Processing & Asia-Pacific Chapter of the Association for Computational Linguistics, 2025)

[13] Chair, Large Knowledge-Enhanced Models Workshop @ IJCAI 2024

[14] Program Committee Chair, WISA 2024 (International Conference on Web Information Systems and Applications)

[15] General Chair, CCKS 2023 (China Conference on Knowledge Graph and Semantic Computing)

[16] Forum Chair, Sixth Knowledge Graph Forum @ CNCC 2022 — “Knowledge Graphs Empowering Big Data and Massive Computing”

[17] General Chair, IJCKG 2022 (International Joint Conference on Knowledge Graphs)

[18] Program Committee Vice-Chair, WISA 2022

[19] Program Committee Chair, IJCKG 2021

[20] Program Committee Chair, CCKS 2021

Guest Editor Roles (Selected)

[1] CAS Tier 1 Journal Big Data Mining and Analytics — Special Issue: “Challenges and Opportunities in Retrieval-Augmented Generation for LLMs: Techniques, Trends and Applications”

[2] CCF-B Journal World Wide Web Journal — Special Issue: “Neuro-Symbolic Intelligence: Large Language Model Enabled Knowledge Engineering”

[3] CCF-B Chinese Journal Journal of Frontiers of Computer Science and Technology (计算机科学与探索) — Special Issue: “Construction and Application of Domain-Specific Large Language Models”

Education Background

2007.09-2013.12  Ph.D. in Computer Science, Shanghai Jiao Tong University, China

2005.09-2007.06  Master's Stage of a Combined Master's-PhD Program in Computer Science, Shanghai Jiao Tong University, China

2003.09-2006.06  B.S. in Mathematics and Applied Mathematics, Shanghai Jiao Tong University, China

2001.09-2005.06  B.S. in Computer Science, Shanghai Jiao Tong University, China

Work Experience

2026.02-present  Tenured Professor，College of Design and Innovation，Tongji University,

2019.09-2026.01  Distinguished Researcher，College of Design and Innovation，Tongji University

2018.07-2019.08  CTO，Shanghai Leyan Information Technology Co., Ltd. (valuation over USD 1 billion; AI-powered e-commerce customer service platform serving over 1 billion users)

2016.02-2018.06  CTO，Shenzhen Goome Robotics Co., Ltd. (AI unicorn in emotional companion robots; launched the world's first cultivatable virtual idol "Amber·XuYan")

2014.01-2016.01  Lecturer，East China University of Science and Technology

Design

Over the past five years, centered on knowledge graphs and large language models, the following projects have been led as principal investigator:

[1] National Key R&D Program (Ministry of Science and Technology) — New Generation AI 2030 Major Project: Knowledge-Enhanced Scientific Embodied Agent Platform and Applications, CNY 48.54 million, Dec 2025 – Nov 2028, Principal Investigator of the subject (responsible for knowledge-enhanced simulated experimental environments and skill learning by agents)

[2] National Natural Science Foundation of China (NSFC) Key Project: Research on Large-Scale Systematic Knowledge Computation Platform Construction, CNY 2.53 million, Jan 2024 – Dec 2027, Principal Investigator

[3] NSFC General Program: Research on Multi-Hop Knowledge Question Answering Based on Explainable Neuro-Symbolic Reasoning, CNY 570,000, Jan 2022 – Dec 2025, Principal Investigator

[4] Shanghai Basic Research Special Zone Program: Urban Characteristic Style Shaping Based on Multimodal Knowledge-Enhanced Large Models, CNY 1.6 million, Jan 2024 – Dec 2027, Co-Principal Investigator

[5] Industry Project: Huawei Personal Intelligence Engine 2.0 Technology Collaboration, CNY 2.55 million, Oct 2023 – Dec 2025, Principal Investigator

[6] Industry Project: Datagrand Information Technology Knowledge Graph & Semantic Understanding Intelligent System Research, CNY 1 million, Jul 2021 – Jul 2025, Principal Investigator

[7] Industry Project: Samsung Multimodal Knowledge Construction & Reasoning for Personal Memory Systems from Long Videos, CNY 490,000, Oct 2025 – Dec 2025, Principal Investigator

[8] Industry Project: Meituan LLM Evaluation Dataset Construction Based on Crowdsourcing Competition, CNY 330,000, Sep 2023 – Dec 2023, Principal Investigator

[9] Industry Project: miHoYo Platform Public Opinion Monitoring and Guidance, CNY 400,000, Aug 2021 – Mar 2022, Principal Investigator

Publications

In the past five years, 90 papers have been published, including 50+ high-level papers in CCF-A/B or CAS Tier 1/2 journals and conferences. Total Google Scholar citations: 11,001; highest single-paper citations: 5,404.

Representative papers published as first author or corresponding author (2022–present):

[1] Hierarchical Textual Knowledge for Enhanced Image Clustering, The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026, Corresponding Author, CCF A (Accepted)

[2] CitySeeker: How Do VLMs Explore Embodied Urban Navigation with Implicit Human Needs?, The 14th International Conference on Learning Representations (ICLR), 2026, Corresponding Author, CCF A (Accepted)

[3] HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues, The ACM Web Conference (WWW), 2026, Corresponding Author, CCF A (Accepted)

[4] U-NIAH: Unified RAG and LLM Evaluation for Long Context Needle-In-A-Haystack, ACM Transactions on Information Systems (TOIS), 2025, Corresponding Author, SCI, CCF A

[5] Scene-aware memory discrimination: Deciding which personal knowledge stays, Knowledge Based Systems (KBS), 2026, Corresponding Author, SCI, CAS Tier 1

[6] StePO-Rec: Towards Personalized Outfit Styling Assistant via Knowledge-Guided Multi-Step Reasoning, 33rd ACM International Conference on Multimedia (MM), 2025, Corresponding Author, CCF-A

[7] ODDA: An OODA Driven Diverse Data Augmentation Framework for Low Resource Relation Extraction, Association for Computational Linguistics (ACL) 2025, Corresponding Author, CCF-A

[8] MultiRAG: A Knowledge-Guided Framework for Mitigating Hallucination in Multi-source Retrieval Augmented Generation, International Conference on Data Engineering (ICDE), 2025, Co-First Author, CCF-A

[9] MetaPKE: Memory Enhanced Task Adaptive Personal Knowledge Extraction in Daily Life, Information Processing and Management (IPM), 2025, Corresponding Author, SCI, CAS Tier 1

[10] DeepSeek: Paradigm Shifts and Technical Evolution in Large AI Models, IEEE/CAA Journal of Automatica Sinica, 2025, Co-First Author, SCI, CAS Tier 1

[11] Cognitive Bias and Reassignment: Who Can Contribute High Quality LLM Data, Association for the Advancement of Artificial Intelligence (AAAI), 2025, Corresponding Author, CCF-A

[12] Large Language Model Enhanced Knowledge Representation Learning: A Survey, Data Science and Engineering (DSE), 2025, Corresponding Author, SCI, CAS Tier 2

[13] NR-GCF: Graph Collaborative Filtering with Improved Noise Resistance, ACM International Conference on Information and Knowledge Management (CIKM), 2025, Corresponding Author, CCF-B

[14] Possibilities and Challenges in the Moral Growth of Large Language Models: a Philosophical Perspective, Ethics and Information Technology, 2025, Corresponding Author, SCI, CAS Tier 2

[15] Deep Reinforcement Learning for Community Architectural Layout Generation, Knowledge and Information Systems, 2025, Corresponding Author, SCI, CCF B

[16] Towards Proactive Interactions for In Vehicle Conversational Assistants Utilizing Large Language Models, International Joint Conference on Artificial Intelligence (IJCAI), 2024,Corresponding Author, CCF-A

[17] Decoding Urban Industrial Complexity: Enhancing Knowledge Driven Insights via IndustryScopeGPT, ACM International Conference on Multimedia (MM), 2024, Corresponding Author, CCF-A

[18] A User Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesis, AAAI Conference on Artificial Intelligence (AAAI), 2024, Corresponding Author, CCF-A

[19] A Question-Answering Assistant over Personal Knowledge Graph, ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2024, Corresponding Author, CCF-A

[20] WDCIP: Spatio-Temporal AI-Driven Disease Control Intelligent Platform for Combating COVID-19 Pandemic, GeoSpatial Information Science, 2024, Corresponding Author, SCI, CAS Tier 2

[21] Social Media Insights into Spatio-Temporal Emotional Responses to COVID19 Crisis, HEALTH &PLACE, 2024, Corresponding Author, SCI, CAS Tier 2

[22] Time-Sensitve Retrieval-Augmented Generation for Question Answering, ACM International Conference on Information and Knowledge Management (CIKM), 2024, Corresponding Author, CCF-B

[23] Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue, Association for Computational Linguistics: EMNLP, 2024, Corresponding Author, CCF-B

[24] A Contrastive Framework for Enhancing Knowledge Graph Question Answering: Alleviating Exposure Bias，Knowledge Based Systems (KBS), 2023, Corresponding Author, SCI, CAS Tier 1

[25] ReCo: A Dataset for Residential Community Layout Planning, ACM International Conference on Multimedia (MM), 2023, Corresponding Author, CCF-A

[26] A Survey of Key Technologies in Next-Generation Knowledge Graphs (新一代知识图谱关键技术综述), Journal of Computer Research and Development (计算机研究与发展), 2022, Corresponding Author, CCF-A

[27] Position Aware Joint Entity and Relation Extraction with Attention Mechanism, International Joint Conference on Artificial Intelligence (IJCAI), 2022, Corresponding Author, CCF-A

[28] Translational Relation Embeddings for Multi-Hop Knowledge Base Question Answering, Journal of Web Semantics (JWS), 2022, Corresponding Author, SCI, CCF-B

[29] MHKD-MVQA: Multimodal Hierarchical Knowledge Distillation for Medical Visual Question Answering, IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2022, Corresponding Author, CCF-B

[30] Type Aware Medical Visual Question Answering, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022, Corresponding Author, CCF-B

Monographs

[1] Retrieval-Augmented Generation: Theory and Practice, Electronic Industry Press, Wang Haofen, Wang Nan, Luo Yun, Gao Yunfan, January 2026

[2] Multi-Source Knowledge Fusion and Applications, Electronic Industry Press, Wang Xiaoling, Wang Haofen, Yang Xiaochun, March 2025

[3] Human-Intelligence Interaction: Interdisciplinary Integration for Human-Centered AI, Tsinghua University Press, Contributing Author (Chapter 5: Data and Knowledge Dual Driven Artificial Intelligence), September 2024

[4] Knowledge Graph / AI and Intelligent Education Series, Educational Science Press, Wang Haofen, Ding Jun, Hu Fanghuai, Yang Xiangdong, July 2022

[5] Knowledge Graph: Methods, Practice and Applications, Electronic Industry Press, Wang Haofen, Qi Guilin, Chen Huajun, August 2019

[6] Natural Language Processing in Practice: Principles and Applications of Chatbot Technology, Electronic Industry Press, Wang Haofen, Shao Hao, February 2019

Granted Patents

[1] Text Conversion Encoder, Text-to-SQL Query Analysis Method and System, Feb 21, 2025, China, ZL202210443248.X, Wang Haofen, Li Shuqin

[2] A Multi-Strategy Fusion Knowledge Question Answering Method and System, Feb 2, 2021, China, ZL201910153329.4, Zhou Yang, Wang Haofen

[3] A Knowledge Graph-Empowered Information Retrieval-Based Question Answering System and Method, Oct 2, 2020, China, ZL201910134021.5, Chu Shanbo, Wang Haofen

[4] Text Embedding Representation Method and System for Medical Vision-Language Multimodal Tasks, Mar 6, 2026, China, ZL 202210180289.4, Zhang Wenqiang, Zhang Anda, Wang Haofen, Tao Wei, Li Ziyan, Wang Jianfeng

[5] A Visual Question Answering Method Based on Cognitive Dual-Channel Reasoning, Aug 1, 2025, China, ZL202210343042.X, Zhang Wenqiang, Zhang Kailei, Wang Haofen, Liu Weichen

[6] An Entity-Relation Joint Extraction Method Integrating Attention Mechanism and Segment Arrangement, Jul 1, 2025, China, ZL202210341776.4, Zhang Wenqiang, Zhang Chenglong, Wang Haofen

[7] A Generation Method and Device for Chinese General Knowledge Graph with Timestamps, Nov 3, 2020, China, ZL201710601438.9, Song Yanan, Qiu Nan, Wang Haofen, Shao Hao

[8] A Multi-Source Cross-Domain Data Query Method and System, Aug 15, 2025, China, ZL202510206906.7, Li Bohan, Wu Wenlong, Wen Hao, Wang Haofen, Yin Hailian, Li Jingbo, Zhuo Junnan, Zhao Xinzhe, Liu Yuanrui

A Large Language Model Safety Detection Method Based on Automated Knowledge Graph Generation, Jul 18, 2025, China, ZL202510654123.5, Li Bohan, Zhao Xinzhe, Wu Wenlong, Zhuo Junnan, Huang Ruilong, Liu Liang, Wang Haofen, Ruan Guoyue

Open Source Projects

[1] OpenKG (http://openkg.cn/): The world's largest Chinese open knowledge graph community, promoting the open-sourcing of high-quality datasets, open-source tools, open-source models, and open benchmarks.

[2] KAG Series (https://github.com/OpenSPG/KAG): A stable and efficient reasoning framework for enterprise-grade applications; includes the world's first interactive deep-reasoning open-source model KAG-Thinker; deployed across Ant Group and industries including healthcare and finance; over 10,000 GitHub Stars.

[3] MemOS (https://github.com/MemTensor/MemOS): A memory-native operating system for large language models, supporting automated conversion among explicit memory, activation memory, and parametric memory, as well as multi-granularity memory scheduling; over 6,000 GitHub Stars; 500,000 daily calls.

[4] KaLM-Embedding (https://kalm-embedding.github.io/): A lightweight and efficient multilingual knowledge embedding model achieving state-of-the-art performance on embedding benchmarks; over 1 million total downloads on Hugging Face.

[5] JoyAgent (https://github.com/jd-opensource/joyagent-jdgenie): A general-purpose multi-agent platform developed in collaboration with JD.com, supporting full lifecycle management, scheduling, monitoring, and orchestration of agents.

[6] AI-Ceping (https://ai-ceping.com/): A crowdsourcing platform for large model evaluation with 300,000 monthly active users.

Honors and Awards

[1] 2025 MUSE Design & Creativity Award, Silver Prize “AI-Ceping: Large Model Evaluation Platform”, First Contributor

[2] 2025 CCF Science and Technology Achievement Award, Third Prize for Technological Progress “Key Technologies and Applications of Knowledge-Enhanced Intelligent Decision-Making”, First Contributor

[3] 30th International Conference on Database Systems for Advanced Applications (DASFAA 2025) Best Student Paper “HBS-KGLLM: A General Framework for Generating Knowledge Graphs for Jailbreaking”

[4] 2024 First Prize, China Transportation Association Science and Technology Progress Award “Research and Application of Key Technologies for Intelligent Regulation of Shanghai Airport Operations”, Second Contributor

[5] 13th International Conference on Design, User Experience and Usability (HCII 2024) Best Paper “From Passive to Active: Towards Conversational In-Vehicle Navigation Through Large Language Model”

[6] 7th China Health Information Processing Conference (CHIP 2021) Best Paper “Construction of a Linking Data Set of COVID-19 Knowledge Graphs: Development and Applications”

[7] 2020 First Prize, Outstanding Publication (Professional Category), China Industry & Information Technology Media Publishing Group “Knowledge Graph: Methods, Practice and Applications”, First Contributor

[8] 2018 Grand Prize, Startup Track, 4th National Youth AI Innovation and Entrepreneurship Conference “Leyu AI Customer Service Robot”, Second Contributor

[9] 2016 Shanghai Outstanding Doctoral Dissertation Award “Semantic Search over Large-Scale RDF Data”

Contact

Email：carter.whfcarter@gmail.com

Homepage：https://tongji-kgllm.github.io/people/wang-haofen/