publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2025

  1. Preprint
    S^3: Unlocking the Full Potential of Sparse Attention for Long Context LLM Serving
    Wooseok Gwak*, Sangjin Choi*, Sukmin Cho, and Youngjin Kwon
    Preprint, 2025
  2. Preprint
    DynoSpec: Dynamic Colocation to Accelerate Speculative Decoding in LLM Serving
    Sangjin Choi, Hyunjae Lee, Seungjae Lim, Sukmin Cho, Wooseok Gwak, and Youngjin Kwon
    Preprint, 2025
  3. Preprint
    TETRIS: Efficient Large Language Model Serving with Adaptive Search for Test-time Scaling
    Sukmin Cho, Seungjae Lim, Sangjin Choi, Hyunsoo Ye, Wooseok Gwak, Sumin Lee, and Youngjin Kwon
    Preprint, 2025

2024

  1. USENIX Security’24
    BUDAlloc: Defeating Use-After-Free Bugs by Decoupling Virtual Address Management from Kernel
    Junho Ahn, Jaehyun Lee, Kanghyuk Lee, Wooseok Gwak, Minseong Hwang, and Youngjin Kwon
    In Proceedings of USENIX Security, 2024