publications

📄papers~

2026

  1. From text to translation: using language models to prioritize variants for clinical review
    Li, Weijiang, Li, Xiaomin, Lavallee, Ethan, Saparov, Alice, Zitnik, Marinka, and Cassa, Christopher
    Genome Medicine 2026
  2. Do LLMs build spatial world models? evidence from grid-world maze tasks
    Li, Weijiang, Zhu, Yilin, Das, Rajarshi, and Dube, Parijat
    arXiv preprint arXiv:2604.10690 2026
  3. Language models reveal evidence gaps in variants of uncertain significance
    Li, Weijiang, Bhat, Vineel, Yu, Tian, Lebo, Matthew, Zitnik, Marinka, and Cassa, Christopher
    medRxiv 2026

2025

  1. Emails by LLMs: A Comparison of Language in AI-Generated and Human-Written Emails
    Li, Weijiang, Lai, Yinmeng, Soni, Sandeep, and Saha, Koustuv
    In Proceedings of the 17th ACM Conference on Web Science 2025

2024

    2023

    1. Towards out-of-distribution generalizable predictions of chemical kinetics properties
      Wang, Zihao, Chen, Yongqiang, Duan, Yang, Li, Weijiang, Han, Bo, Cheng, James, and Tong, Hanghang
      In NeurIPS AI for Science Workshop 2023

    2022

    1. Chemical-reaction-aware molecule representation learning
      Wang, Hongwei, Li, Weijiang, Jin, Xiaomeng, Cho, Kyunghyun, Ji, Heng, Han, Jiawei, and Burke, Martin D
      In International Conference on Learning Representations (ICLR) 2022

    2021

    1. Fine-grained chemical entity typing with multimodal knowledge representation
      Sun, Chenkai, Li, Weijiang, Xiao, Jinfeng, Parulian, Nikolaus Nova, Zhai, ChengXiang, and Ji, Heng
      In IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2021