Linye Wei (韦临烨)

I am currently a first-year Ph.D. student at Institute for Artificial Intelligence & School of Integrated Circuits, Peking University (PKU), advised by Prof. Meng Li. Prior to that, I received my B.S. degree from Chien-Shiung Wu College and School of Future Technology, Southeast University, majoring in Electronic Science and Engineering.

My current research focuses on Efficient AI Systems, with particular emphasis on LLM Inference Acceleration, Algorithm-System Co-design and Multimodal Synthesis.

My resumes are available here: [EN] [CN] Feel free to contact me at lywei25@stu.pku.edu.cn. I look forward to potential collaborations and academic exchanges.

🎓 Educations

  • [2025.09-Now] Ph.D., School of Integrated Circuits, Peking University (PKU)

  • [2021.09-2025.06] B.S., Chien-Shiung Wu College (with Honors), Southeast University (SEU)

🔥 News

  • May 01, 2026 🎉 Our work TEAM is accepted by ICML 2026!

  • Feb 24, 2026 🎉 Our work ODB-dLLM is accepted by DAC 2026!

  • Oct 23, 2025 🏆 I receive Presidential Scholarship for Ph.D. Students from Peking University!

  • Sep 02, 2025 🏆 I receive Dean’s Scholarship for Ph.D. Students from Institute for Artificial Intelligence, Peking University!

  • Jul 01, 2025 🎉 Our work LS-Gaussian is accepted by ICCAD 2025!

  • Jun 26, 2025 🥇 Our Team win the first place in the System Design Contest of DAC 2025!

  • Feb 15, 2025 🎉 Our work SpecASR is accepted by DAC 2025!

  • Sep 29, 2024 🎓 I receive my Ph.D. offer from Peking University!

🎉 Publications

  • TEAM: Temporal-Spatial Consistency Guided Expert Activation for MoE Diffusion Language Model Acceleration
    Linye Wei, Zixiang Luo, Pingzhi Tang, Meng Li
    ICML 2026, CCF-A, [Paper] [Github]

  • Orchestrating Dual-Boundaries: An Arithmetic Intensity Inspired Acceleration Framework for Diffusion Language Models
    Linye Wei, Wenjue Chen, Pingzhi Tang, Xiaotian Guo, Le Ye, Runsheng Wang, Meng Li
    DAC 2026, CCF-A, [Paper] [Github]

  • No Redundancy, No Stall: Lightweight Streaming 3D Gaussian Splatting for Real-time Rendering
    Linye Wei, Jiajun Tang, Fan Fei, Boxin Shi, Runsheng Wang, Meng Li
    ICCAD 2025, CCF-B, [Paper]

  • SpecASR: Accelerating LLM-based Automatic Speech Recognition via Speculative Decoding
    Linye Wei, Shuzhang Zhong, Songqiang Xu, Runsheng Wang, Ru Huang, Meng Li
    DAC 2025, CCF-A, [Paper]

  • VR-YOLO: Enhancing PCB Defect Detection with Viewpoint Robustness Based on YOLO
    Hengyi Zhu*, Linye Wei*, He Li
    WF-IoT 2025, [Paper] [Github]

🏆 Honors and Awards

  • [2025.11] Presidential Scholarship for Ph.D. Students, Peking University
  • [2025.10] Dean’s Scholarship for Ph.D. Students, Peking University
  • [2024.09] Merit Student, Southeast University
  • [2023.12] Future Technology TAIHU Scholarship, Southeast University
  • [2023.09] Merit Student, Southeast University
  • [2023.05] Outstanding Youth League Member, Southeast University
  • [2022.12] ZHISHAN Scholarship, Southeast University
  • [2022.10] Presidential Scholarship, Southeast University
  • [2022.09] Merit Student, Southeast University

🎖️ Competition Awards

  • [2025.06] First place in the System Design Contest of DAC 2025
    Linye Wei, Wenxuan Zeng, Jiangrui Yu, Zizhuo Fu, Ziyu Tang, Tianjian Yang, Meng Li
  • [2023.09] Second Prize, 2023 National Undergraduate Electronic Design Competition
  • [2023.09] First Prize (Jiangsu Division), 2023 National Undergraduate Electronic Design Competition
  • [2023.01] First Prize, 14th National College Student Mathematics Competition
  • [2022.11] Second Prize, 19th Jiangsu Province Advanced Mathematics Competition
  • [2022.10] First Prize (Jiangsu Division), 2022 National Undergraduate Mathematical Contest in Modeling