avatar

Junyi Wu (吴俊毅)

Ph.D. Student
Illinois Institute of Technology
jwu125 (at) hawk.iit.edu


Short Bio

I am a Ph.D. student in Computer Science advised by Prof. Yan Yan at Illinois Institute of Technology since 2023 Spring. Before that, I received my bachelor’s degree in Mathematics (Information and Computing Science) from Sun Yat-sen University in 2022.

My research focuses on building Effective, Efficient, and Explainable machine learning systems.

News

Publications [Google Scholar]

  1. PTQ4DiT NeurIPS 2024
    PTQ4DiT: Post-training Quantization for Diffusion Transformers
    Junyi Wu*, Haoxuan Wang*, Yuzhang Shang, Mubarak Shah, Yan Yan
    Conference on Neural Information Processing Systems (NeurIPS), 2024.
    Paper Code BibTex
  2. DQAS ECCV 2024
    Dataset Quantization with Active Learning based Adaptive Sampling
    Zhenghao Zhao, Yuzhang Shang, Junyi Wu, Yan Yan
    European Conference on Computer Vision (ECCV), 2024.
    Paper Code BibTex
  3. att arXiv
    AttBalance: Visual Grounding with Attention-Driven Constraint Balancing
    Weitai Kang, Luowei Zhou, Junyi Wu, Changchang Sun, Yan Yan
    arXiv, July 2024.
    Paper BibTex
  4. Quest arXiv
    QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning
    Haoxuan Wang, Yuzhang Shang, Zhihang Yuan, Junyi Wu, Yan Yan
    arXiv, Feb. 2024.
    Paper Code BibTex
  5. SaCo CVPR 2024
    On the Faithfulness of Vision Transformer Explanations
    Junyi Wu, Weitai Kang, Hao Tang, Yuan Hong, Yan Yan
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
    Paper Code BibTex
  6. TokenTM CVPR 2024
    Token Transformation Matters: Towards Faithful Post-hoc Explanation for Vision Transformer
    Junyi Wu, Bin Duan, Weitai Kang, Hao Tang, Yan Yan
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
    Paper BibTex

    7. Teaching

    • Teaching Assistant, CS 577: Deep Learning, Illinois Institute of Technology, 2023 Fall

Last Update: