publications

(* denotes equal contribution). All cover artworks are generated by DALL·E 3 with minimum cherry picking.

2026

  1. Predicting genome-wide functional constraints with GPN-Star
    Chengzhong Ye*, Gonzalo Benegas*, Carlos Albors, Jianan Canal Li, Sebastian Prillo, and 3 more authors
    Nature, 2026
  2. Deep Learning-Driven Discovery and Engineering of an Efficient PETase for Depolymerization and Detoxification of PET Microplastics Under Physiological Conditions
    Yuxuan Wang, Shijie He, Yuheng Chang, Sheng Mao, Jianan Canal Li, and 5 more authors
    Advanced Science, 2026

2025

  1. A Phylogenetic Approach to Genomic Language Modeling
    Carlos Albors, Jianan Canal Li, Gonzalo Benegas, Chengzhong Ye, and Yun S Song
    RECOMB 2025, 2025
  2. Large Language Model is Secretly a Protein Sequence Optimizer
    Yinkai Wang, Jiaxing He, Yuanqi Du, Xiaohui Chen, Jianan Canal Li, and 3 more authors
    LMRL Workshop at ICLR 2025, 2025
  3. Genomic Language Models: Opportunities and Challenges
    Gonzalo Benegas*, Chengzhong Ye*, Carlos Albors*, Jianan Canal Li*, and Yun S. Song
    Trends in Genetics, 2025

2023

  1. M²Hub: Unlocking the Potential of Machine Learning for Materials Discovery
    Yuanqi Du*, Yingheng Wang*, Yining Huang, Jianan Canal Li, Yanqiao Zhu, and 4 more authors
    NeurIPS 2023 Datasets and Benchmarks Track, 2023
  2. Enzyme Function Prediction using Contrastive Learning
    Tianhao Yu*, Haiyang Cui*, Jianan Canal Li, Yunan Luo, Guangde Jiang, and 1 more author
    Science, 2023

2022

  1. MCTensor: A High-Precision Deep Learning Library with Multi-Component Floating-Point
    Tao Yu*, Wentao Guo*, Jianan Canal Li*, Tiancheng Yuan*, and Christopher De Sa
    ICML Workshop on Hardware Aware Efficient Training (HAET), 2022
  2. Cyclical Kernel Adaptive Metropolis
    Jianan Canal Li*, Yimeng Zeng*, and Wentao Guo*
    arXiv Preprint, 2022