Yiheng Shu

Yiheng Shu

PhD Student @ Ohio State

About Me

I’m a second-year doctoral student at The Ohio State University, advised by Prof. Yu Su. My research interests include language agents and retrieval-augmented generation (RAG): 1) how to ground large language models to real-world environments, and 2) how to retrieve from environments and augment large language models.

I received my Master degree from Nanjing University in 2023 and Bachelor degree from Northeastern University (CN) in 2020. I was research intern at MSRA in 2022.

Feel free to reach out to me if you’re interested in my research. I’m looking for summer internship opportunities.

Preprints

  • [arXiv] Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents
    Boyu Gou, Ruohan Wang, Boyuan Zheng, Yanan Xie, Cheng Chang, Yiheng Shu, Huan Sun, Yu Su
    [paper] [code] [home]

Publications

  • [NeurIPS’24] HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
    Bernal Jiménez Gutiérrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, Yu Su
    [paper] [code]
  • [EMNLP’24] Middleware for LLMs: Tools Are Instrumental for Language Agents in Complex Environments
    Yu Gu, Yiheng Shu, Hao Yu, Xiao Liu, Yuxiao Dong, Jie Tang, Jayanth Srinivasa, Hugo Latapie, Yu Su
    [paper] [code] [benchmark] [proceedings] [BibTeX]
  • [EACL’24 SRW] Distribution Shifts Are Bottlenecks: Extensive Evaluation for Grounding Language Models to Knowledge Bases
    Yiheng Shu, Zhiwei Yu
    [paper] [code] [data] [poster] [video] [proceedings] [BibTeX]
  • [AAAI’23] Question Decomposition Tree for Answering Complex Questions over Knowledge Bases
    Xiang Huang, Sitao Cheng, Yiheng Shu, Yuheng Bao, Yuzhong Qu
    [paper] [code] [proceedings] [BibTeX]
  • [EMNLP’22] TIARA: Multi-grained Retrieval for Robust Question Answering over Large Knowledge Base
    Yiheng Shu, Zhiwei Yu, Yuhan Li, Börje F. Karlsson, Tingting Ma, Yuzhong Qu, Chin-Yew Lin
    [paper] [code] [data] [poster] [slides] [video] [proceedings] [BibTeX]
  • [COLING’22] Logical Form Generation via Multi-task Learning for Complex Question Answering over Knowledge Bases
    Xixin Hu, Xuan Wu, Yiheng Shu, Yuzhong Qu
    [paper] [code] [slides] [video] [proceedings] [BibTeX]
  • [ISWC’21] EDG-based Question Decomposition for Complex Question Answering over Knowledge Bases
    Xixin Hu, Yiheng Shu, Xiang Huang, Yuzhong Qu
    [paper] [code] [home] [video] [proceedings] [BibTeX]
  • [TOIS’20] Deep Learning for Sequential Recommendation: Algorithms, Influential Factors, and Evaluations
    Hui Fang, Danning Zhang, Yiheng Shu, Guibing Guo
    [paper] [code] [ACM Library] [BibTeX]
  • [ICWE’19 tutorial] Deep Learning-based Sequential Recommender Systems: Concepts, Algorithms, and Evaluations
    Hui Fang, Danning Zhang, Guibing Guo, Yiheng Shu
    [slides] [intro] [Springer Link] [BibTeX]

Services