I am currently a second-year Masterโ€™s student in Computer Science at Northeastern University, focusing on Retrieval-Augmented Generation, Large Language Models, and Multi-Modal Large Language Models. Google Scholar:

Now I am engaged in research internships at NEUIR Lab under the guidance of Associate Professor Zhenghao Liu, as well as at THUNLP, supervised by Yukun Yan .

My hobbies are dancing ๐Ÿ’ƒ and guitar ๐ŸŽธ. My favorite dance styles are jazz and hiphop. I usually play folk guitar. If you share these interests, I would be glad to connect and grow together ๐Ÿ“ž.

๐Ÿ‘€ I am looking for a Ph.D. position starting in Fall 2027 and would love to explore potential collaborations. Letโ€™s connect!

๐Ÿ”ฅ News

  • 2025.08: ย ๐ŸŽ‰ We released UltraRAG 2.0 , an low-code framework for building complex RAG systems!
  • 2025.05: ย ๐ŸŽ‰ Our paper RankCoT is accepted by ACL 2025!

๐Ÿ“ Publications

* indicates equal contribution, and โ€  indicates corresponding author.

ACL 2025
sym

RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts

Mingyan Wu, Zhenghao Liuโ€ ,Yukun Yanโ€ , Xinze Li, Shi Yu, Zheni Zeng, Yu Gu, Ge Yu

๐Ÿ“ƒPaper | ๐Ÿ“„PDF |

  • This work leverages the strengths of both ranking and summarization to effectively refine the knowledge from retrieval results, thereby aiding LLMs in generating more accurate responses.
Arxiv Print
sym

Graph-Anchored Knowledge Indexing for Retrieval-Augmented Generation

Zhenghao Liu*โ€ , Mingyan Wu*, Xinze Li, Yukun Yanโ€ , Shuo Wang, Cheng Yang, Minghe Yu, Zheni Zeng, Maosong Sun

๐Ÿ“ƒPaper | ๐Ÿ“„PDF |

  • This work reconceptualizes knowledge graphs as dynamically evolving indices that anchor salient entities and relations to guide iterative retrieval and answer generation.

๐Ÿ“– Educations

  • 2024.09 - now, M.S. School of Computer Science and Engineering, Northeastern University
  • 2020.09 - 2024.07, B.S. School of Computer Science, Yangtze University

๐Ÿ’ป Internships