Yang Yang

Deep Learning Researcher/Engineer


I work as Sr. Staff Deep Learning Engineer at Qualcomm AI Research in San Diego. My research interests include deep generative models, neural data compression (image/video/speech compression), and machine learning for combinatorial optimization (e.g., graph-level compiler optimization). I am passionate about designing deep learning solutions to challenging problems and deploying them to edge devices.

I received my Ph.D. from the Ohio State University in 2015 on wireless networking. Before joining AI Research, I worked on wireless physical layer design (reference signal, channel estimation, tracking loop), channel coding design, and standardization for 5G NR (patent).


Mar 18, 2022 Completed Chapter 2 Normalizing Flows of our deep generative models book :fire:
Mar 5, 2022 :checkered_flag: Post Quantization for Neural Networks is up! :checkered_flag:
Aug 1, 2021 My research focus is transitioned from neural data compression to MLCO. :thinking:
Jun 19, 2021 Checkout my team’s demo: Real-time on-device neural video decoding (CVPR 2021); More
May 7, 2021 Co-organized ICLR 2021 Neural Compression Workshop :book:
Apr 3, 2021 :checkered_flag: Post on how to enforce Lipschitz constant in neural networks is up! :checkered_flag:

selected publications

  1. ICLR
    Transformer-based Transform Coding
    Zhu, Yinhao*Yang, Yang*, and Cohen, Taco
    In International Conference on Learning Representations (ICLR) 2022
  2. ICIP
    Progressive Neural Image Compression With Nested Quantization And Latent Ordering
    In IEEE International Conference on Image Processing (ICIP) 2021
  3. JSP
    Transform Network Architectures for Deep Learning Based End-to-End Image/Video Coding in Subsampled Color Spaces
    Egilmez, Hilmi, Singh, Ankitesh Kumar, Coban, Muhammed, Karczewicz, Marta, Zhu, YinhaoYang, YangSaid, Amir, and Cohen, Taco
    In IEEE Open Journal of Signal Processing 2021
    Feedback Recurrent Autoencoder
    In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2020
  5. ACCV
    Feedback Recurrent Autoencoder for Video Compression
    In Asian Conference on Computer Vision (ACCV) 2020
  6. CVPR
    Guided Variational Autoencoder for Disentanglement Learning
    Ding, Zheng*, Xu, Yifan*Xu, Weijian, Parmar, Gaurav,  Yang, YangWelling, Max, and Tu, Zhuowen
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2020
    Automatic Grammar Augmentation for Robust Voice Command Recognition
    Yang, YangLalitha, AnushaLee, Jinwon, and Lott, Chris
    In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019
  8. CVPR-W
    Phase Selective Convolution
    Lin, Jamie Menjay, Noorzad, Parham,  Yang, Yang, Kwak, Nojun, and Porikli, Fatih
    In IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops on Embedded Vision 2021