Publications

2026

1. NeurIPS ’26

   AdaTree: Serving-Aware Adaptive Tree Construction for Speculative Decoding

   Soohyun Cha , Jungi Lee, and Jaewoong Sim

   In The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS) , Sydney, Australia, 2026

   BIB

   @inproceedings{adatree,
     author = {Cha, Soohyun and Lee, Jungi and Sim, Jaewoong},
     title = {AdaTree: Serving-Aware Adaptive Tree Construction for Speculative Decoding},
     year = {2026},
     booktitle = {The Fortieth Annual Conference on Neural Information Processing Systems (NeurIPS)},
     series = {NeurIPS '26},
   }

2. HPCA ’26

   GRTX: Efficient Ray Tracing for 3D Gaussian-Based Rendering

   Junseo Lee , Sangyun Jeon , Jungi Lee, Junyong Park , and Jaewoong Sim

   In Proceedings of the 32nd International Symposium on High Performance Computer Architecture (HPCA) , Sydney, Australia, 2026

   BIB

   @inproceedings{grtx,
     author = {Lee, Junseo and Jeon, Sangyun and Lee, Jungi and Park, Junyong and Sim, Jaewoong},
     title = {GRTX: Efficient Ray Tracing for 3D Gaussian-Based Rendering},
     year = {2026},
     booktitle = {Proceedings of the 32nd International Symposium on High Performance Computer Architecture (HPCA)},
     series = {HPCA '26},
   }

2025

1. MICRO ’25

   MX+: Pushing the Limits of Microscaling Formats for Efficient Large Language Model Serving

   Jungi Lee, Junyong Park , Soohyun Cha , Jaehoon Cho , and Jaewoong Sim

   In Proceedings of the 58th Annual International Symposium on Microarchitecture (MICRO) , Seoul, Korea, 2025

   BIB PAPER Poster Slides

   @inproceedings{mx+,
     author = {Lee, Jungi and Park, Junyong and Cha, Soohyun and Cho, Jaehoon and Sim, Jaewoong},
     title = {MX+: Pushing the Limits of Microscaling Formats for Efficient Large Language Model Serving},
     year = {2025},
     booktitle = {Proceedings of the 58th Annual International Symposium on Microarchitecture (MICRO)},
     series = {MICRO '25},
   }

2024

1. OSDI ’24

   InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management

   Wonbeom Lee* , Jungi Lee*, Junghwan Seo , and Jaewoong Sim

   In Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI) , Santa Clara, CA, USA, 2024

   BIB PAPER Code Poster Slides

   @inproceedings{infinigen,
     author = {Lee*, Wonbeom and Lee*, Jungi and Seo, Junghwan and Sim, Jaewoong},
     title = {InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management},
     year = {2024},
     booktitle = {Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI)},
     series = {OSDI '24},
   }

2. ISCA-51

   Tender: Accelerating Large Language Models via Tensor Decompostion and Runtime Requantization

   Jungi Lee*, Wonbeom Lee* , and Jaewoong Sim

   In Proceedings of the 51st Annual International Symposium on Computer Architecture (ISCA) , Buenos Aires, Argentina, 2024

   BIB PAPER Code Poster Slides

   @inproceedings{tender,
     author = {Lee*, Jungi and Lee*, Wonbeom and Sim, Jaewoong},
     title = {Tender: Accelerating Large Language Models via Tensor Decompostion and Runtime Requantization},
     year = {2024},
     booktitle = {Proceedings of the 51st Annual International Symposium on Computer Architecture (ISCA)},
     series = {ISCA '24},
   }

3. ASPLOS ’24

   GSCore: Efficient Radiance Field Rendering via Architectural Support for 3D Gaussian Splatting

   Junseo Lee , Seokwon Lee , Jungi Lee, Junyong Park , and Jaewoong Sim

   In Proceedings of the 2024 International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS) , San Diego, CA, USA, 2024

   BIB PAPER VIDEO Poster Slides

   @inproceedings{gscore,
     author = {Lee, Junseo and Lee, Seokwon and Lee, Jungi and Park, Junyong and Sim, Jaewoong},
     title = {GSCore: Efficient Radiance Field Rendering via Architectural Support for 3D Gaussian Splatting},
     year = {2024},
     booktitle = {Proceedings of the 2024 International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)},
     series = {ASPLOS '24},
   }

2023

1. ISCA-50

   NeuRex: A Case for Neural Rendering Acceleration

   Junseo Lee , Kwanseok Choi , Jungi Lee, Seokwon Lee , Joonho Whangbo , and Jaewoong Sim

   In Proceedings of the 50th Annual International Symposium on Computer Architecture (ISCA) , Orlando, FL, USA, 2023

   BIB PAPER VIDEO Slides

   @inproceedings{neurex,
     author = {Lee, Junseo and Choi, Kwanseok and Lee, Jungi and Lee, Seokwon and Whangbo, Joonho and Sim, Jaewoong},
     title = {NeuRex: A Case for Neural Rendering Acceleration},
     year = {2023},
     booktitle = {Proceedings of the 50th Annual International Symposium on Computer Architecture (ISCA)},
     series = {ISCA '23},
   }