Mengyao Lyu

I am a Ph.D. candidate in School of Software, Tsinghua University, advised by Prof. Guiguang Ding. My research delves deep into the shadows of established knowledge, aiming to provide comprehensive insights and innovative solutions.


Box-Level Active Detection
Mengyao Lyu, Jundong Zhou, Hui Chen, Yijie Huang, Dongdong Yu, Yaqian Li, Yandong Guo, Yuchen Guo, Liuyu Xiang, Guiguang Ding
CVPR, 2023 (Highlight, 2.5% acceptance rate)

One-dimensional Adapter to Rule Them All
Mengyao Lyu*, Yuhong Yang*, Haiwen Hong, Hui Chen, Xuan Jin, Yuan He, Hui Xue, Jungong Han, Guiguang Ding
CVPR, 2024 (Highlight)


  • 2023.06 ~ 2024.02


    Research intern for Multimodal Perception Safety
    • Precisely erased concepts from Diffusion models while maintaining safe concepts the same.
    • The obtained concept erasures facilitate training-free transfer and multi-concept customization.
    • Achieved SOTA results across ∼40 concepts, 7 Diffusion models and 4 erasing applications.
  • 2021.06 ~ 2023.05

    OPPO Research (Tsinghua-OPPO JCFDT)

    Research intern for Intelligent Perception and Interaction
    • Proposed and implemented a novel active learning algorithm for object detection to improve data and training efficiency.
    • Reimplemented 10+ active detection baselines and SOTAs for a fair evaluation.
    • Achieved SOTA results on two pulic benchmarks and on OPPO private datasets.
  • 2018.07 ~ 2018.08

    Horizon Robotics

    Research intern for ADAS perception
    • Developed conditional generative adversarial networks to synthesize data for different road signs.
    • Achieved a 44% improvement in the accuracy of the road sign classification task.