Yichi Zhang (张溢弛)

Ph.D. Candidate in Computer Science, Zhejiang University

Multi-modal Knowledge Graphs · Knowledge-centric LLMs · Data Synthesis

Ph.D. Candidate, ZJUKG-Lab
College of Computer Science and Technology
Zhejiang University

Email: zhangyichi.each@zju.edu.cn

[Google Scholar] [DBLP] [GitHub]

Short Bio

I am currently a CS Ph.D. candidate at Zhejiang University, advised by Prof. Huajun Chen and Prof. Wen Zhang at the ZJUKG-Lab. My research focuses on multi-modal knowledge graphs (MMKG) and knowledge-centric large language models to achieve synergized applications.

Multi-modal Knowledge Graphs: incorporating diverse modalities (image, text, numeric) of entities to enhance representation learning, MMKG reasoning and completion.
Knowledge-centric (M)LLM Reasoning: utilizing structural knowledge (both parameterized and non-parameterized) to improve LLMs' reasoning performance; knowledge-augmented and trustworthy generation.
Knowledgeable Data Synthesis for (M)LLMs: constructing high-quality post-training data to enhance multi-modal and structured reasoning capabilities of LLMs.
Real-world Application for KG & LLMs: applying KGs and LLMs to solve real-world problems in specific domains.

If you are interested in my field of work, any form of collaboration and communication is welcome. Please feel free to contact me!

Research Summary

Multi-modal Knowledge Graphs

Large Language Models

Application

Multi-modal Knowledge Graph Representation & Reasoning & Completion: Represent entities and relations in vector spaces to conduct structured knowledge reasoning and new knowledge discovery. Our research mainly focuses on incorporating diverse modalities (image, text, numeric, audio, video) of entities to enhance representation learning and further benefit MMKG reasoning and completion:

Imbalanced Modality Distribution: Adversarial Training (AdaMF-MAT, NATIVE)
Fine-grained Modality Fusion: Modality Tokenization and Hierarchical Modeling (MyGO)
Modality Entanglement and Disentanglement: Mixture-of-Experts Networks (MoMoK)
Federated Multi-modal Knowledge Aggregation: Multi-modal Codebook-based Knowledge Sharing (MUCO)

Knowledge-enhanced Large Language Models: Incorporating structural knowledge into LLMs to achieve the harmonious combination of KGs and LLMs — both employing LLMs to enhance structured reasoning, and utilizing structural knowledge to improve LLMs' performance:

Incorporate Parameterized Structural Information into LLMs: Knowledge Prefix Adapter (KoPA)
Systematic Evaluation of LLM's Structural Understanding Ability: Structural Knowledge Prompting Benchmark (SUBARU)
Select Better Context Knowledge: Knowledgeable Preference Alignment (KnowPAT)
Understand and Reason with Structured Visual Contents: Abstractive Visual Reasoning (M3STR), Knowledge-informed GRPO (STAR & KGRPO)

Application of KGs and LLMs in Specific Domains: Utilizing KGs and LLMs to solve real-world problems in specific domains, mainly focusing on telecom network service and E-commerce:

Telecom Network Analysis and Fault Diagnosis: KG-enhanced Domain BERT Pre-training (TeleBERT)
Intelligent Telecom Customer Service: Knowledgeable Preference Alignment (KnowPAT)
E-commerce Recommendation / QA / Review Prediction: Transferable Text-informed KG Pre-training (MuDoK)
Reliable Answer Generation with Entity-level Citations: Knowledge-informed Citation (Self-KFC)

News

[2026.05] One paper accepted to IEEE TKDE.
[2026.04] I join Alibaba Taobao and Tmall Group for a summer internship.
[2026.01] One paper is accepted by Computer Engineering and Application Journal (in Chinese).
[2026.05] Two papers accepted to ACL 2026 (1 Main, 1 Findings).
[2025.07] Two papers accepted to ACM MM 2025.
[2025.05] One papers accepted to ACL 2025 (Main Conference).

Education

Zhejiang University, 2025.02 – present
Ph.D. Candidate in Computer Science and Technology
Zhejiang University, 2022.09 – 2025.01
Master in Computer Science and Technology
Zhejiang University, 2018.09 – 2022.06
Bachelor in Software Engineering

Publications

★ representative work | * equal contribution

2026

MORTIS: Towards Multi-Modal and Multi-Scale Federated Knowledge Graph Completion

Yichi Zhang, Linyu Li, Zhi Jin, Zhuo Chen, Lingbing Guo, Wen Zhang, Huajun Chen

IEEE TKDE

Paper arXiv

Know the Known and the Unknown: Reasonable Answer Generation with Knowledge-Informed Citations

Yichi Zhang, Zhuo Chen, Lingbing Guo, Jun Xu, Mengshu Sun, Zhizheng Liu, Lei Liang, Wen Zhang, Huajun Chen

ACL 2026 Main

Paper arXiv

★ Structured and Abstractive Reasoning on Multi-modal Relational Knowledge Images

Yichi Zhang, Zhuo Chen, Lingbing Guo, Wen Zhang, Huajun Chen

ACL 2026 Findings

Paper arXiv Code

2025

Client-Server Co-design with Multi-modal Codebooks Makes Better and Faster Federated Knowledge Sharing

Yichi Zhang, Zhuo Chen, Lingbing Guo, Yajing Xu, Lei Liang, Wen Zhang, Huajun Chen

ACM MM 2025

Paper

★Abstractive Visual Understanding of Multi-modal Structured Knowledge: A New Perspective for MLLM Evaluation

Yichi Zhang, Zhuo Chen, Lingbing Guo, Yajing Xu, Min Zhang, Wen Zhang, Huajun Chen

ACM MM 2025

Paper arXiv Code Dataset

Have We Designed Generalizable Structural Knowledge Promptings? Systematic Evaluation and Rethinking

Yichi Zhang, Zhuo Chen, Lingbing Guo, Yajing Xu, Shaokai Chen, Mengshu Sun, Binbin Hu, Zhiqiang Zhang, Lei Liang, Wen Zhang, Huajun Chen

ACL 2025 Main

Paper arXiv Code

★ Multiple Heads are Better than One: Mixture of Modality Knowledge Experts for Entity Representation Learning

Yichi Zhang, Zhuo Chen, Lingbing Guo, Yajing Xu, Binbin Hu, Ziqi Liu, Wen Zhang, Huajun Chen

ICLR 2025

Paper arXiv Code

★ Tokenization, Fusion, and Augmentation: Towards Fine-grained Multi-modal Entity Representation

Yichi Zhang, Zhuo Chen, Lingbing Guo, Yajing Xu, Binbin Hu, Ziqi Liu, Wen Zhang, Huajun Chen

AAAI 2025

Paper arXiv Code

K-ON: Stacking Knowledge On the Head Layer of Large Language Model

Lingbing Guo, Yichi Zhang, Zhongpu Bo, Zhuo Chen, Mengshu Sun, Zhiqiang Zhang, Wen Zhang, Huajun Chen

AAAI 2025 Oral

Paper arXiv Code

2024

★ Making Large Language Models Perform Better in Knowledge Graph Completion

Yichi Zhang, Zhuo Chen, Lingbing Guo, Yajing Xu, Binbin Hu, Ziqi Liu, Wen Zhang, Huajun Chen

ACM MM 2024 Oral

Paper arXiv Code

★ Knowledgeable Preference Alignment for LLMs in Domain-specific Question Answering

Yichi Zhang*, Zhuo Chen*, Yin Fang, Lei Cheng, Yanxi Lu, Fangming Li, Wen Zhang, Huajun Chen

ACL 2024 Findings

Paper arXiv Code

★ NativE: Multi-modal Knowledge Graph Completion in the Wild

Yichi Zhang, Zhuo Chen, Lingbing Guo, Yajing Xu, Binbin Hu, Ziqi Liu, Wen Zhang, Huajun Chen

SIGIR 2024

Paper arXiv Code

Unleashing the Power of Imbalanced Modality Information for Multi-modal Knowledge Graph Completion

Yichi Zhang, Zhuo Chen, Lei Liang, Wen Zhang, Huajun Chen

COLING 2024

Paper Code

2023

MACO: A Modality Adversarial and Contrastive Framework for Modality-missing Multi-modal Knowledge Graph Completion

Yichi Zhang, Zhuo Chen, Wen Zhang

NLPCC 2023

Paper Code

Honors & Awards

2025.11 National Scholarship (国家奖学金)
2024.11 National Scholarship (国家奖学金)
2024.04 Chiang Chen Scholarship (蒋震奖学金)
2023.08 ISWC 2023 Best Paper Candidate Award (Paper Link)
2023.04 Chiang Chen Scholarship (蒋震奖学金)
2022.06 Outstanding Bachelor's Degree Graduates (优秀毕业生)
2022.04 Distinguished Engineer Scholarship (卓越工程师奖学金)
2020.12 College Scholarship from Higgs Technology (希格斯奖学金)
2020.10 Zhejiang Provincial Government Scholarship (浙江省政府奖学金)
2019.10 / 2020.10 / 2021.10 Second-class Scholarships in Zhejiang University (校二等奖学金)

Academic Services

Conference Reviewer: ICLR 2025/2026, NeurIPS 2024/2025, WWW 2024/2025, ACL ARR 2023/2024/2025/2026, ACM MM 2024/2025/2026, AAAI 2026/2027, IJCNN 2024/2025
Journal Reviewer: IEEE TAI, IEEE TKDE, IEEE TPAMI
Conference Volunteer: ISWC 2023, IJCKG 2022