I am currently a third-year Ph.D. Student at the School of Data Science and Engineering, East China Normal University (ECNU), under the supervision of Prof. Xiang Li in the PLANING lab. My previous work mainly focused on graph data mining, including graph neural networks and heterogeneous graph mining. I am currently exploring several directions around graph learning and large language models, including their integration, graph foundation models, and LLM applications in scientific research.
- Graph Data Mining: graph neural networks, heterogeneous graph mining
- LLM Agents: agent skills, agentic routing, agentic RL
- LLM for Science: scientific applications of large language models
- Integration of GNNs and LLMs: graph foundation models, graph prompt learning
🎉🎉🎉 Feel free to reach out to me for academic discussions and collaborations!
📝 Publications 
Leveraging Large Language Models for Node Generation in Few-Shot Learning on Text-Attributed Graphs
Jianxiang Yu, Yuxiang Ren, Chenghua Gong, Jiaqi Tan, Xiang Li, Xuecang Zhang.
- First to leverage LLMs for node generation in graph learning. 🔍
- A plug-and-play, lightweight framework with minimal overhead with minimal overhead. 🚀
Automated Peer Reviewing in Paper SEA: Standardization, Evaluation, and Analysis 
Jianxiang Yu*, Zichen Ding*, Jiaqi Tan, Kangyang Luo, Zhenmin Weng, Chenghua Gong, Long Zeng, Renjing Cui, Chengcheng Han, Qiushi Sun, Zhiyong Wu, Yunshi Lan, Xiang Li.
- Check demos at Our Website. 🌐
- The model is available at hugging face. 🤗
- An innovative framework for automating peer review. 🌊
Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Adaptively Weighted Negative Samples
Jianxiang Yu, Qingqing Ge, Xiang Li, Aoying Zhou.
- Coarse and fine-grained views for HIN contrastive learning. 🐾
- Gradient-based InfoNCE analysis and weighted contrastive loss design. 🎯
SEAGraph: Unveiling the Whole Story of Paper Review Comments
Jianxiang Yu*, Jiaqi Tan*, Zichen Ding, Jiapeng Zhu, Jiaqi Li, Yao Cheng, Qier Cui, Yunshi Lan, Yao Liu, Xiang Li.
- Constructing Semantic Mind Graphs and Hierarchical Background Graphs to simulate reviewer thinking. 🧠
- Retrieving with GraphRAG to unevil review comments. 📚
-
EMNLP 2026Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learning,
Jiapeng Zhu, Jianxiang Yu, Yibo Zhao, Chengcheng Han, Qi GU, Xunliang Cai, Xiang Li, Weining Qian. -
EMNLP 2026Node-to-Neighborhood Semantic Consistency: Text-Topology Alignment for TAGs Anomaly Detection,
Bochen Lin, Jianxiang Yu, Jiayi Wu, Lin Qi, Huang Lu, Xiang Li -
EMNLP 2026Breaking the Cloak! Unveiling Chinese Cloaked Toxicity with Homophone Graph and Toxic Lexicon,
Xuchen Ma, Jianxiang Yu, Wenming Shao, Bo Pang, Xiang Li. -
EMNLP 2026Beyond Chunk-Local Extraction: Cross-Chunk Graph Augmentation for GraphRAG,
Jiaming Zhang, Yibo Zhao, Jing Yu, Jianxiang Yu, Xiang Li -
EMNLP 2026APEX: Academic Poster Editing Agentic Expert,
Chengxin Shi, Qinnan Cai, Zeyuan Chen, Long Zeng, Yibo Zhao, Jing Yu, Jianxiang Yu, Xiang Li, -
NeurIPS 2025 workshopDiffusion-augmented Graph Contrastive Learning for Collaborative Filtering,
Fan Huang, Jianxiang Yu, Wei Wang. -
EMNLP 2025 mainCan Large Language Models Act as Ensembler for Multi-GNNs?,
Hanqi Duan, Yao Cheng, Jianxiang Yu, Yao Liu, Xiang Li. -
FCS 2025Boosting Cross-Domain and Cross-Task Generalization for Text-Attributed Graphs from Structural Perspective,
Yao Cheng, Jiapeng Zhu, Yige Zhao, Jianxiang Yu, Xiang Li. -
FCS 2025A Survey on Learning from Graphs with Heterophily: Recent Advances and Future Directions,
Chenghua Gong, Yao Cheng, Jianxiang Yu, Can Xu, Caihua Shan, Siqiang Luo, Xiang Li -
WWW 2025Hierarchical Vector Quantized Graph Autoencoder with Annealing-Based Code Selection,
Long Zeng, Jianxiang Yu, Jiapeng Zhu, Qingsong Zhong, Xiang Li -
KDD 2025Variational Graph Autoencoder for Heterogeneous Information Networks with Missing and Inaccurate Attributes,
Yige Zhao, Jianxiang Yu, Yao Cheng, Chengcheng Yu, Yiding Liu, Xiang Li, Shuaiqiang Wang. -
KDD 2025RELIEF: Reinforcement Learning Empowered Graph Feature Prompt Tuning,
Jiapeng Zhu, Zichen Ding, Jianxiang Yu, Jiaqi Tan, Xiang Li. -
ECML PKDD 2024Self-Pro: Self-Prompt and Tuning Framework for Graph Neural Networks,
ChengHua Gong, Xiang Li, Jianxiang Yu, Yao Cheng, Jiaqi Tan, Chengcheng Yu.
-
SDM 2023Heterogeneous Graph Contrastive Learning with Meta-path Contexts and Weighted Negative Samples,
Jianxiang Yu, Xiang Li. -
ICKG 2023Context-Aware Session-Based Recommendation with Graph Neural Networks,
Zhihui Zhang, Jianxiang Yu, Xiang Li.
More preprints under review will be released soon, and some papers can be found on Google Scholar. 📚✨🔍
📑 Preprint
Relation-Aware Graph Foundation Model
Jianxiang Yu, Jiapeng Zhu, Hao Qian, Ziqi Liu, Zhiqiang Zhang, Xiang Li.
- A relation-aware pre-training framework for graph foundation models. ⚙️
- Robust generalization and effective transferability. 💪
Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents
Jianxiang Yu, Jiapeng Zhu, Bochen Lin, Qier Cui, Zichen Ding, Xiang Li.
- A model-aware skill alignment framework for LLM agents. 🧩
- Effective adaptation and generalization across models and tasks. 🔄
Role-GAD: Role-Aware Graph Anomaly Detection via Dual-Codebook Vector Quantization,
Jianxiang Yu*, Bochen Lin*, Shaofeng Hu, Lin Qi, Weijun Zeng, Huang Lu, Hailong Li, Jiacheng Ma, Xiang Li.
- A role-aware framework for graph anomaly detection via dual-codebook vector quantization. 🛠️
- Capturing heterogeneous anomaly patterns through discrete semantic and interaction roles. 🔍
- Improving Graph Out-of-distribution Generalization on Real-world Data,,
Can Xu, Yao Cheng, Jianxiang Yu, Haoran Wang, Jun Lv, Xiang Li.
💻 Internships
🌟 Experience
- 2024.11 Attend EMNLP 2024 in Miami, USA.
- 2024.10 Give a talk at EMNLP 2024 pre-presentation event organized by AI TIME.
🎖 Honors and Awards
- 2024.05 Outstanding Graduate, East China Normal University
- 2023.11 Second Prize Enterprise Scholarship, School of Data Science and Engineering, East China Normal University
📖 Education
🔍 Services
I have served as a reviewer or program committee member for:
- ICML 2026
- AAAI 2026 Main Conference
- KDD 2026 Datasets and Benchmark Track
- AAAI 2026 AI Alignment Track