Xuan Shen

me.jpeg

I am a Ph.D. student in ECE Department of Northeastern University at Boston, advised by Yanzhi Wang. Previously, I received my M.S. degree at Northeastern University in 2020 and my B.S. degree at Nanjing University of Science and Technology in 2018.

My research interest is Efficient AI including pruning, quantization, NAS, and distillation with Software Hardware Co-Design on Mobile, FGPA, and ASIC.

I work closely with Jiuxiang Gu, Prof. Pu Zhao and Prof. Wei Niu. I was fortunate to work with Ming Lin.

As a final-year Ph.D. candidate, I am actively pursuing post-doctoral and full-time research opportunities. I would welcome the chance to connect and discuss potential collaborations if our research interests align.

News

Dec 09, 2024 Got Adobe Reward: 2024 Key Innovations (Tech Transfer Small LLM on Acrobat).
Dec 09, 2024 Got three papers accepted in AAAI 2025.
Nov 19, 2024 Multimodal Opioid Benchmark released on HuggingFace: opioidarchive/oida-qa.
Oct 30, 2024 Our paper about PTQ of LLMs on Mobile and FPGA has been accepted to TCAD.
Sep 25, 2024 Got two papers accepted in NeurIPS 2024.

Selected Publications

  1. AAAI
    Numerical Pruning for Efficient Autoregressive Models
    Xuan Shen, Zhao Song, Yufa Zhou, Bo Chen, Jing Liu, Ruiyi Zhang, Ryan A Rossi, Hao Tan, Tong Yu, Xiang Chen, Yufan Zhou, Tong Sun, Pu Zhao, Yanzhi Wang†, and Jiuxiang Gu†
    The Association for the Advancement of Artificial Intelligence, 2025
    PDF
  2. AAAI
    LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers
    Xuan Shen, Zhao Song, Yufa Zhou, Bo Chen, Yanyu Li, Yifan Gong, Kai Zhang, Hao Tan, Jason Kuen, Henghui Ding, Zhihao Shu, Wei Niu, Pu Zhao, Yanzhi Wang†, and Jiuxiang Gu†
    The Association for the Advancement of Artificial Intelligence, 2025
    PDF
  3. NeurIPS
    Search for Efficient Large Language Models
    Xuan Shen, Pu Zhao, Yifan Gong, Zhenglun Kong, Zheng Zhan, Yushu Wu, Ming Lin, Chao Wu, Xue Lin, and Yanzhi Wang†
    Conference on Neural Information Processing Systems, 2025
    PDF Code
  4. TCAD
    HotaQ: Hardware Oriented Token Adaptive Quantization for Large Language Models
    Xuan Shen, Zhaoyang Han, Lei Lu, Zhenglun Kong, Peiyan Dong, Zhengang Li, Yanyue Xie, Chao Wu, Miriam Leeser, Pu Zhao, Xue Lin, and Yanzhi Wang†
    IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2024
    PDF
  5. AAAI
    Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge
    Xuan Shen*, Peiyan Dong*, Lei Lu, Zhenglun Kong, Zhengang Li, Ming Lin, Chao Wu, and Yanzhi Wang†
    The Association for the Advancement of Artificial Intelligence, 2024
    PDF Code
  6. CVPR
    DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network
    Xuan Shen*, Yaohua Wang*, Ming Lin, Yilun Huang, Hao Tang, Xiuyu Sun, and Yanzhi Wang†
    Conference on Computer Vision and Pattern Recognition, 2023
    PDF Code
  7. IJCAI
    Data Level Lottery Ticket Hypothesis for Vision Transformers
    Xuan Shen, Zhenglun Kong, Minghai Qin, Peiyan Dong, Geng Yuan, Xin Meng, Hao Tang, Xiaolong Ma, and Yanzhi Wang†
    International Joint Conference on Artificial Intelligence, 2023
    PDF Code