Shang Yuzhang (尚玉章)

yshang4@hawk.iit.edu

prof_pic.jpg

Yuzhang is from Dongying,

Shandong Province, China.

BIO

I am currently a third-year Ph.D. candidate in Computer Science at the Illinois Institute of Technology (IIT) under the supervision of Prof. Yan Yan. In the meantime, I am a visiting student at the University of Wisconsin-Madison under the supervision of Prof. Yong Jae Lee working on efficient large multimodal models. My research focuses on Efficient/Scalable AI, particularly for Generative Models and Large Language Models.

Before IIT, I worked as research assistants at Shandong University and Hong Kong University of Science and Technology (HKUST) under the supervision of Prof. Liqiang Nie and Prof. Dan Xu, respectively. Special thanks to Prof. Nie, who continues to co-mentor me during my Ph.D. pursuit journey. I received my bachelor’s degrees in Applied Mathematics and Economics (dual degrees), advised by Prof. Xiliang Lv at Wuhan University.

I regularly serve as PC member, and reviewer for multiple international conferences and journals such as CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, ACM-MM, WSDM, NeuroComputing, Information Sciences, CVIU, TMM, TCSVT, and TKDE.

Besides research, I am a contract photographer for Shutterstock Images and Getty Images, and here is my portfolio.

news

Feb, 2024 Two first-author papers about efficient multitask dense predictor and post-training calibration method got accepted to CVPR 2024! :fist:
Jan, 2024 One paper about efficient point cloud transformer got accepted to ICRA 2024! :fist:
Jan, 2024 I received the Award of Excellence in Dissertation Research for the College of Computing at IIT.
Nov, 2023 I am invited to give a talk about dataset distillation at the IDEAL data science workshop, Northwestern University (News).
Oct, 2023 I am invited to give a talk about data-free and post-training network compression (two works at Cisco Research) at the Michigan AI Lab, U-Mich Ann Arbor (News).
Sep, 2023 One first-author paper about model training efficient got accepted to NeurIPS 2023! :fist:
Sep, 2023 I am invited to give a talk about PTQ for Diffusion Models at ZhiDongXi (in Chinese: 智东西)! :smiley:
Aug, 2023 Third-year Ph.D. candidate! :smile:
Jul, 2023 One first-author paper about using causality to guide data-free quantization got accepted to ICCV 2023! Causal-DFQ will be integrated into Cicso Network Compression Toolbox (Official Blog). :fist:
Apr, 2023 I am invited to give a talk about network comprssion at the ML Workshop at IDEAL! :smiley:
Feb, 2023 One first-author paper about Diffusion Model Acceleration got accepted to CVPR 2023! :fist:
I am open to collaborations on interesting research projects :blush:
Jan, 2023 Proposed to my girlfriend at the Niagara Falls on New Year’s Eve and got a YES! 💑
Aug, 2022 Second-year Ph.D. student! :smile:
Jun, 2022 Two first-author papers about Neural Network Compression got accepted to ECCV 2022! :fist:
Jun, 2021 My first-author paper about Knowledge Distillation has been accepted to ICCV 2021! :fist:

selected publications

  1. LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
    Yuzhang Shang*, Mu Cai*, Bingxin Xu, Yong Jae Lee^, and Yan Yan^
    arXiv Mar. 2024
    arXiv Code
  2. LLM Inference Unveiled: Survey and Roofline Model Insights
    Zhihang Yuan*, Yuzhang Shang*, Yang Zhou*, Zhen Dong, Chenhao Xue, Bingzhe Wu, Zhikai Li, and 6 more authors
    arXiv Feb. (Survey Paper) 2024
    arXiv Code
  3. Efficient Multitask Dense Predictor via Binarization
    Yuzhang Shang, Dan Xu, Gaowen Liu, Ramana Kompella, and Yan Yan
    Computer Vision and Pattern Recognition (CVPR) 2024
  4. ASVD: Activation-aware Singular Value Decomposition for Compressing Large Language Models
    Zhihang Yuan*, Yuzhang Shang*, Yue Song, Qiang Wu, Yan Yan, and Guangyu Sun
    arXiv Dec. 2023
    arXiv Code
  5. MIM4DD: Mutual Information Maximization for Dataset Distillation
    Yuzhang Shang, Zhihang Yuan, and Yan Yan
    Conference on Neural Information Processing Systems (NeurIPS) 2023
    arXiv
  6. Causal-DFQ: Causality Guided Data-free Network Quantization
    Yuzhang Shang, Bingxin Xu, Gaowen Liu, Ramana Kompella, and Yan Yan
    International Conference on Computer Vision (ICCV) 2023
    arXiv Code
  7. Post-training Quantization on Diffusion Models
    Yuzhang Shang*, Zhihang Yuan*, Bin Xie, Bingzhe Wu, and Yan Yan
    Computer Vision and Pattern Recognition (CVPR) 2023
    arXiv Code
  8. Network Binarization via Contrastive Learning
    Yuzhang Shang, Dan Xu, Ziliang Zong, Liqiang Nie, and Yan Yan
    European Conference on Computer Vision (ECCV) 2022
    arXiv Code
  9. Lipschitz Continuity Retained Binary Neural Network
    Yuzhang Shang, Dan Xu, Bin Duan, Ziliang Zong, Liqiang Nie, and Yan Yan
    European Conference on Computer Vision (ECCV) 2022
    arXiv Code
  10. Lipschitz Continuity Guided Knowledge Distillation
    Yuzhang Shang, Bin Duan, Ziliang Zong, Liqiang Nie, and Yan Yan
    International Conference on Computer Vision (ICCV) 2021
    arXiv Code