My name is Cehao Yang(杨策皓), a first-year PhD in Artificial Intelligence. Currently I’m studying the HKUST(GZ)-IDEA Joint PhD Program, proudly supervised by Prof.Hui Xiong and Prof.Jian Guo.

🤔 Currently, my research interests primarily focus on Large Language Models (LLMs), covering the following topics:

• Knowledge-Augmented LLMs: utilizing external knowledge base to enhance LLMs’ reasoning
• Synthetic Data: generating high-quality datasets for training LLMs efficiently
• Knowledge Graph: synergizing LLMs and knowledge graphs for application

🙌 Thanks for your reading! If you are interested in my research, welcome for discussion and collaboration!

🔥 News

• 2025.05:  🎉🎉 One paper (LongFaith) about Synthetic Data for Long-Context Reasoning is accepted by ACL 2025 Findings!
• 2025.04:  🎉🎉 Our paper (KGR3) is reported by DeepTech深科技, click (here) to read!
• 2025.01:  🎉🎉 One paper (ToG2.0) about Knowledge Graph-augmented LLM is accepted by ICLR 2025!
• 2025.01:  🎉🎉 One paper (KGR3) about LLM-driven Knowledge Graph Completion is accepted by NAACL 2025 Main!
• 2024.12:  🎉🎉 One paper (CATS) about LLM-driven Inductive Knowledge Graph Completion is accepted by AAAI 2025!

📝 Publications

1. Submission to NeurIPS 2025 SELECT2REASON: Efficient Instruction-Tuning Data Selection for Long-CoT Reasoning
   Cehao Yang^*, Xueyuan Lin^*, Chengjin Xu^*, Xuhui Jiang, Xiaojun Wu, Honghao Liu, Hui Xiong, Jian Guo.

2. Submission to ACM MM 2025 [SHARPMARK: Revisiting and Enhancing Set-of-Mark Prompting for Multimodal Web Navigation]
   Cehao Yang^*, Xueyuan Lin^*, Hongqiu Wang, Lihao Liu, Chengjin Xu, Lei Zhu, Jian Guo

3. ACL 2025 Findings LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Data
   Cehao Yang^*, Xueyuan Lin^*, Chengjin Xu^*, Xuhui Jiang, Shengjie Ma, Aofan Liu, Hui Xiong, Jian Guo

4. ICLR 2025 Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation
   Shengjie Ma, Chengjin Xu, Xuhui Jiang, Muzhi Li, Huaren Qu, Cehao Yang, Jiaxin Mao, Jian Guo

5. NAACL 2025 Main Retrieval, Reasoning, Re-ranking: A Context-Enriched Framework for Knowledge Graph Completion
   Muzhi Li^*, Cehao Yang^*, Chengjin Xu^*, Xuhui Jiang, Yiyan Qi, Jian Guo, Ho-fung Leung, Irwin King

6. AAAI 2025 Context-aware Inductive Knowledge Graph Completion with Latent Type Constraints and Subgraph Reasoning
   Muzhi Li^*, Cehao Yang^*, Chengjin Xu^*, Zixing Song, Xuhui Jiang, Jian Guo, Ho-fung Leung, Irwin King

🎖 Honors and Awards

• 2024.09 - 2028.09, Ph.D. Full Scholarship (￥720,000)
• 2022.09 - 2024.09, M.Phil. Full Scholarship (￥240,000)

📖 Educations

• 2024.09 - Now, Ph.D. in Artificial Intelligence, Hong Kong University of Science and Technology (Guangzhou).
• 2022.09 - 2024.11, M.Phil. in Artificial Intelligence, Hong Kong University of Science and Technology (Guangzhou).
• 2018.09 - 2022.06, B.S. in Computer Science and Engineering, South China University of Technology.

💁 Volunteer

• Reviewer: ACL’25, AAAI PDLM’25, ACM MM’25, NeurIPS’25, ACL SRW’25
• 2024.09 - 2024.12, AIAA5088: Natural Language Processing and Its Applications (2024-2025 Fall), Teaching Assistant
• 2023.07 - 2023.08, Red Bird Challenge Camp, HKUST(GZ), Teaching Assistant

💻 Internships

• 2023.08 - Now, NLP Research Intern, IDEA FinAI, Shenzhen.
• 2021.06 - 2021.09, Back-end Research & Development Intern, ByteDance, Shenzhen.