yuliang.png

Yuliang Yan (闫宇量)

PhD Student at HKUST (GZ)

La seule façon de lutter contre la peste, c’est l’honnêteté.
(The only way to fight the plague is with decency.)
— Albert Camus

Research: Currently, I am a second year PhD student, surpervised by Enyan Dai. My research focuses on AI for Protein, with the goal of building efficient and robust deep learning models to advance protein engineering. I am also dedicated to developing algorithms with rigorous mathematical guarantees for de novo drug design, such as molecular glues and peptides. In addition, my work extends to the development of trustworthy large language models.

Previously: I earned my master’s degree from Fudan NLP Group, Fudan University and my bachelor’s degree in Mathematics from Shanghai University.

Selected Publications

* denotes equal contribution

2026

  1. triglue.png
    TriGlue: a Biology-Inspired Generative Model for Generating Molecular Glue-Induced Ternary Complex
    Yuliang Yan, Shuo Yan, Haochun Tang, and 2 more authors
    Jul 2026
    PDF
  2. protap.png
    General Protein Pretraining or Domain-Specific Designs? Benchmarking Protein Modeling on Realistic Applications
    Shuo Yan*, Yuliang Yan*, Bin Ma, and 7 more authors
    In KDD, Datasets and Benchmarks Track, Jun 2026
  3. r2a.png
    Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization
    Haochun Tang*, Yuliang Yan*, Jiahua Lu, and 2 more authors
    In ACL (Main), Apr 2026
    PDF Code
  4. duffin.png
    DuFFin: A Dual-Level Fingerprinting Framework for LLMs IP Protection
    Yuliang Yan, Haochun Tang, Shuo Yan, and 1 more author
    In EACL (Findings), Mar 2026

2023

  1. mindreading.png
    Measure Children’s Mindreading Ability with Machine Reading
    Yuliang Yan, Xiaohua Wang, Xiang Zhou, and 2 more authors
    In EMNLP (Findings), Dec 2023