Yifei Sun (孙逸飞)

I am an assistant professor (ZJU-100 Young Professor) at Zhejiang University. I received my Ph.D. degree from the College of Computer Science and Technology at Zhejiang University (ZJU) in 2025, under the supervision of Prof. Yang Yang. Since graduating with my PhD, I have been working closely with Prof. Yunjun Gao and his DAILY Group. Previously, I visited National University of Singapore (NUS) from Nov 2023 to Jun 2024. (working with Prof. Bingsheng He, Prof. Bryan Hooi and Prof. Zemin Liu).

My research interests include foundation models for structured data, agentic RL, and whole-body VLA. I have published several papers in top tier venues, with citations on google scholar and on github.

Ongoing Work

• Planning and Evolving for Agentic Systems.

• Reasoning Models for Relational Data.

• Memory for Whole-body VLA.

If interested, please drop me a message by email.

News

• [2026.1] Our paper “A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation” is accepted by WWW 2026. Congrats to Haoyang Zhong on getting it accepted on the first submission!
• [2025.11] Our paper “Table as a modality for Large Language models” is accepted by NeurIPS 2025. Congrats to Liyao Li!
• [2025.1] Our paper “Multi-Label Node Classification with Label Influence Propagation” is accepted by ICLR 2025.
• [2025.1] One co-authored paper accepted by WWW’25 (Oral)! Congrats to Yufei He! “UniGraph2: Learning a Unified Embedding Space to Bind Multimodal Graphs”.
• [2024.11] Our paper “Handling Feature Heterogeneity with Learnable Graph Patches” is accepted by KDD 2025.
• [2024.10] Attended SMP’24 and received the Best Poster Award! Thank you all for the recognition!
• [2024.10] Our paper “G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering” is accepted by NeurIPS 2024. Congrats to Xiaoxin He! <!– - [2024.5] Our paper “Chromosomal Structural Abnormality Diagnosis by Homologous Similarity” is accepted by KDD 2024 (ADS). Congrats to Juren Li!
• [2024.5] Our paper “Exploring Correlations of Self-supervised Tasks for Graphs” is accepted by ICML 2024. Congrats to Taoran Fang! –>

Selected Publications (Full version see Google Scholar)

TL;DR: Unifies context-aware and relation-aware retrieval through hierarchical hybrid structure, enabling reasoning beyond retrieval.

• Haoyang Zhong, Yifei Sun$^\dagger$, Antong Zhang, Chunping Wang, Lei Chen, Yang Yang. A Unified Framework for Context-Aware and Relation-Aware Graph Retrieval-Augmented Generation. Accepted by WWW 2026.

TL;DR: Provide insights into multi-label node classification (MLNC) and model the propagation of label influences.

• Yifei Sun, Zemin Liu$^\dagger$, Bryan Hooi, Yang Yang$^\dagger$, Rizal Fathony, Jia Chen, Bingsheng He$^\dagger$. Multi-Label Node Classification with Label Influence Propagation. Accepted by ICLR 2025.

TL;DR: Generalized graph model that tackles feature heterogeneity to achieve cross-domain transferability.

• Yifei Sun, Yang Yang$^\dagger$, Xiao Feng, Zijun Wang, haoyang zhong, Chunping Wang, Lei Chen. Handling Feature Heterogeneity with Learnable Graph Patches. Accepted by ACM KDD 2025.

TL;DR: Narrow the Gap between Graph Pre-training and Fine-tuning to enhance the generalization of graph models.

• Yifei Sun, Qi Zhu, Yang Yang$^\dagger$, Chunping Wang, Tianyu Fan, Jiajun Zhu, Lei Chen. Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns. Accepted by AAAI 2024.

TL;DR: Break the limitations of GNNs by creating new message passing paradigm.

• Yifei Sun, Haoran Deng, Yang Yang$^\dagger$, Chunping Wang, Jiarong Xu, Renhong Huang, Linfeng Cao, Yang Wang, and Lei Chen. Beyond Homophily: Structure-aware Path Aggregation Graph Neural Network. Accepted by IJCAI 2022.

$\dagger$: Corresponding author.

Academic Activities

• [2024.10] Gave a talk on “Exploring the Generalization of Graph Models” at the Doctoral Forum of SMP 2024.
• [2024.5] Co-organized the full-day workshop on Graph Foundation Models at the WebConf 2024.