Xi Chen (陈熹)

xc.JPG

CoRE 735, Busch Campus

Rutgers University

Piscataway, NJ, 08854

I am a Ph.D. candidate advised by Prof. Shirin Jalali at the Electrical and Computer Engineering Department of Rutgers University. My background is in imaging inverse problems, machine learning, and information theory.

I am particularly interested in characterizing the structures of sources (image/video) by developing priors/regularization (e.g. pre-trained models: VQ-VAE, Diffusion models; implicit priors: DIP, INR; codebook and neural entropy coding on quantized representation), under optimization frameworks (e.g. ADMM, Plug-and-Play), to solve ill-posed inverse problems and restoration tasks, with theoretical understandings of the fundamental limits on the achievable recovery performance from the information theoretic and high-dimensional aspects.

I received my M.Sc. degree in Data Science from Tufts University, MA, worked with Prof. Mike Hughes and Liping Liu. I received my B.Sc. degree in Electrical Engineering from Beijing Institute of Technology, China, worked with Prof. Jie Tian.

Email: firstname.chen15 [at] rutgers [dot] edu

Please feel free to reach out if you want to discuss or collaborate on research!

news

Jun 02, 2025 I joined Nokia Bell Labs as a research intern this summer.
Apr 15, 2025 Presented our work on efficient reconstruction in coherent imaging during the visit to Rice Computational Imaging Group and ISBI conference at Houston.
Nov 04, 2024 Recognized as a Top Reviewer by NeurIPS 2024.
Sep 25, 2024 Our paper on snapshot compressive imaging is accepted by NeurIPS 2024.
Jun 17, 2024 Glad to receive the SPIE student travel award to present our work on novel approach for coherent imaging system in SPIE Optics + Photonics 2024, San Diego.
May 20, 2024 Presented our work on compressive coherent imaging system at Conference on Inverse Problems for Partial Differential Equations.
May 01, 2024 Our paper on multi-look coherent imaging with speckle noise is accepted by ICML 2024.
Apr 04, 2024 Presented our work on image acquisition with speckle noise on Columbia Data Science Day.
Dec 16, 2023 Presented our work in the NeurIPS Deep learning and Inverse Problems workshop.

selected publications

  1. arXiv
    Zero-shot denoising via neural compression: Theoretical and algorithmic framework
    Ali Zafari*, Xi Chen*, and Shirin Jalali
    arXiv preprint arXiv:506.12693, 2025
  2. arXiv
    Multilook Coherent Imaging: Theoretical Guarantees and Algorithms
    Xi Chen*, Soham Jana*, Christopher A Metzler, Arian Maleki, and Shirin Jalali
    arXiv preprint arXiv:2505.23594, 2025
  3. ISIT
    DeCompress: Denoising via Neural Compression
    Ali Zafari*, Xi Chen*, and Shirin Jalali
    IEEE International Symposium on Information Theory, Workshop on Learn to Compress & Compress to Learn, 2025 (Spotlight)
  4. SampTA
    Deep Memory Unrolled Networks for Solving Imaging Linear Inverse Problems
    Eric Chen, Xi Chen, Shirin Jalali, and Arian Maleki
    International Conference on Sampling Theory and Applications, 2025 (Oral)
  5. ISBI
    Monte Carlo efficient image reconstruction in coherent imaging with speckle noise
    Xi Chen, Christopher A Metzler, Arian Maleki, and Shirin Jalali
    In IEEE International Symposium on Biomedical Imaging , 2025 (Oral)
  6. SPIE
    Novel approach to coherent imaging in the presence of speckle noise
    Xi Chen, Christopher A Metzler, Arian Maleki, and Shirin Jalali
    In Unconventional Imaging, Sensing, and Adaptive Optics , 2024 (Oral)
  7. NeurIPS
    Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms
    Mengyu Zhao, Xi Chen, Xin Yuan, and Shirin Jalali
    In Advances in Neural Information Processing Systems , 2024
  8. ICML
    Bagged Deep Image Prior for Recovering Images in the Presence of Speckle Noise
    Xi Chen, Zhewen Hou, Christopher A Metzler, Arian Maleki, and Shirin Jalali
    In International Conference on Machine Learning , 2024
  9. NeurIPSW
    Multilook compressive sensing in the presence of speckle noise
    Xi Chen, Zhewen Hou, Christopher Metzler, Arian Maleki, and Shirin Jalali
    In NeurIPS Workshop on Deep Learning and Inverse Problems , 2023
  10. TMLR
    Interpretable Node Representation with Attribute Decoding
    Xiaohui Chen*, Xi Chen*, and Li-Ping Liu
    Transactions on Machine Learning Research, 2022
  11. Journal
    Radiomics analysis of magnetic resonance imaging improves diagnostic performance of lymph node metastasis in patients with cervical cancer
    Qingxia Wu*, Shuo Wang*, XI Chen*, Yan Wang, Li Dong, and 3 more authors
    Radiotherapy and Oncology, 2019
  12. SPIE
    Radiomics analysis on T2-MR image to predict lymphovascular space invasion in cervical cancer
    Shou Wang*, Xi Chen*, Zhenyu Liu, Qingxia Wu, Yongbei Zhu, and 2 more authors
    In Medical Imaging 2019: Computer-Aided Diagnosis , 2019
  13. ISMRM
    Radiomics Analysis of tumor and peri-tumor tissue on T2-Weighted Imaging Improves Diagnostic Performance of Lymph Node Metastasis in Patients with Cervical Cancer
    Qingxia Wu, Shuo Wang, Xi Chen, Yan Wang, Yusong Lin, and 1 more author
    International Society for Magnetic Resonance in Medicine, 2019
  14. EMBC
    Unsupervised deep learning features for lung cancer overall survival analysis
    Shuo Wang, Zhenyu Liu, Xi Chen, Yongbei Zhu, Hongyu Zhou, and 5 more authors
    In 40th Annual international conference of the IEEE engineering in medicine and biology society (EMBC) , 2018