publications

more to come:)

2024

2024

  1. NeurIPSSpotlight
    Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
    Saiyue Lyu *, Shadab Shaikh *, Frederick Shpilevskiy *, Evan Shelhamer, and Mathias Lécuyer
    Advances in Neural Information Processing Systems, 2024
    Spotlight Highlighted [Top 2% in 15671]
    PDF Code Poster Slides
  2. TMLR
    DP-LDMs: Differentially Private Latent Diffusion Models
    Michael F Liu *, Saiyue Lyu *, Margarita Vinaroz *, and Mijung Park
    Transactions on Machine Learning Research, 2024
    PDF Code
  3. CVPR Workshop
    Adaptive Randomized Smoothing for Certified Multi-Step Defence
    Shadab Shaikh, Saiyue Lyu, Frederick Shpilevskiy, Evan Shelhamer, and Mathias Lécuyer
    Test-Time Adaptation Workshop at CVPR, 2024
    PDF
  4. ICLR Workshop
    Differentially Private Latent Diffusion Models
    Saiyue Lyu *, Margarita Vinaroz *, Michael F Liu *, and Mijung Park
    Privacy Regulation and Protection in Machine Learning Workshop at ICLR, 2024
    PDF

2023

2023

  1. CSCW
    Exploring Temporal and Multilingual Dynamics of Post-Disaster Social Media Discourse: A Case of Fukushima Daiichi Nuclear Accident
    Saiyue Lyu, and Zhicong Lu
    In Proceedings of the ACM on Human-Computer Interaction (CSCW), 2023
    PDF

2022

2022

  1. Thesis
    Faster Algorithms for Sparse Decomposition and Sparse Series Solutions to Differential Equations
    Saiyue Lyu
    Master Thesis, 2022
    PDF