Shang Yuzhang (尚玉章)
yshang4@hawk.iit.edu
Yuzhang is from Dongying,
Shandong Province, China.
BIO
I am a final-year Ph.D. candidate in Computer Science at the Illinois Institute of Technology (Illinois Tech) 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.
[I’m on the 24/25 academic job market. Feel free to contact me.]
My research focuses on Efficient and Scalable AI Systems, with specific emphasis on
- Neural Network Compression: LONDON (ICCV’2021), CMIM (ECCV’2022), LCR-BNN (ECCV’2022),Causal-DFQ (ICCV’2023), CL-Calib (CVPR’2024)
- Visual Generative Model Acceleration: PTQ4DM (CVPR’2023), QuEST, DKDM, PTQ4DiT (NeurIPS’2024).
- Efficient (Visual, Language, and Multimodal) Large Models: Bi-MTDP (CVPR’2024), RPTQ, ASVD, PB-LLM, LLM-Viewer (Efficient LLM Survey), LLaVA-PruMerge, INTP-Video-LLMs.
- Fast Optimization for Neural Networks: MIM4DD (NeurIPS’2023), DQAS (ECCV’2024), LTDD.
I was a Research Scientist (Intern) at Google DeepMind supervised by Daniele Moro and Andrew Howard, working on training inference-efficient large language models. Additionally, I interned as a Research Scientist at Cisco Research supervised by Gaowen Liu and Ramana Kompella, where I developed efficient computer vision models and created the model slimming toolbox for Cisco.
Before Ph.D., 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. 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
Sep, 2024 | Two papers, one about diffusion transformer quantization and one about efficient confidential training, got accepted to NeurIPS 2024! |
---|---|
Jul, 2024 | One paper about dataset condensation got accepted to ECCV 2024! |
Feb, 2024 | Two first-author papers about efficient multitask dense predictor and post-training calibration method got accepted to CVPR 2024! |
Jan, 2024 | One paper about efficient point cloud transformer got accepted to ICRA 2024! |
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! |
Sep, 2023 | I am invited to give a talk about PTQ for Diffusion Models at ZhiDongXi (in Chinese: 智东西)! |
Aug, 2023 | Third-year Ph.D. candidate! |
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). |
Apr, 2023 | I am invited to give a talk about network comprssion at the ML Workshop at IDEAL! |
Feb, 2023 | One first-author paper about Diffusion Model Acceleration got accepted to CVPR 2023! I am open to collaborations on interesting research projects |
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! |
Jun, 2022 | Two first-author papers about Neural Network Compression got accepted to ECCV 2022! |
Jun, 2021 | My first-author paper about Knowledge Distillation has been accepted to ICCV 2021! |
selected publications
- MIM4DD: Mutual Information Maximization for Dataset DistillationConference on Neural Information Processing Systems (NeurIPS) 2023