Lele Cao

Sr Principal AI Researcher, Microsoft (ABK) | Ph.D., Tsinghua University

prof_pic_color.jpg

I currently serve as a Senior Principal AI Researcher and Research Lead at Microsoft (Activision Blizzard King). I earned my Ph.D. in Robotics and Artificial Intelligence from Tsinghua University in collaboration with The University of Melbourne in 2016.

With over 16 years of industry experience in Private Equity, Gaming, Telecom, Geoinformatics, and E-commerce, I have published in premier conferences such as CVPR, AAAI, EMNLP, IJCAI, AISTATS and KDD, and regularly serve as a reviewer for these venues. I have supervised more than 10 Master’s students from institutions including KTH, VU, ETH, UU, LiU, and USTC, and currently mentor industrial Ph.D. candidates.

My research focuses on self-supervised representation learning, graph learning, offline reinforcement learning, event streams, and time series modeling. If you are interested in “transforming industries through AI research”, I generally welcome research collaboration inquiries at lelecao@microsoft.com.

news

selected publications

  1. SIGKDD
    Self-Supervised Learning of Time Series Representation via Diffusion Process and Imputation-Interpolation-Forecasting Mask
    Zineb Senane*, Lele Cao*, Valentin Leonhard Buchner, Yusuke Tashiro, Lei You, Pawel Andrzej Herman, Mats Nordahl, Ruibo Tu, and Vilhelm Ehrenheim
    In Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Barcelona, Spain, 2024
  2. CVPR
    Multimodal Token Fusion for Vision Transformers
    Yikai Wang, Xinghao Chen, Lele Cao, Wenbing Huang, Fuchun Sun, and Yunhe Wang
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2022
  3. IJCAI Workshop
    Using Deep Learning to Find the Next Unicorn: A Practical Synthesis on Optimization Target, Feature Selection, Data Split and Evaluation Strategy
    Lele Cao, Vilhelm Ehrenheim, Sebastian Krakowski, Xiaoxue Li, and Alexandra Lutz
    In IJCAI Workshop of Multimodal AI For Financial Forecasting (MuFFin), Aug 2023
  4. AAAI
    Efficient spatio-temporal tactile object recognition with randomized tiling convolutional networks in a hierarchical fusion strategy
    Lele Cao, Ramamohanarao Kotagiri, Fuchun Sun, Hongbo Li, Wenbing Huang, and Zay Maung Maung Aye
    In Proceedings of the AAAI conference on artificial intelligence, Aug 2016
  5. CoG
    Human-Like Playtesting with Deep Learning
    Stefan Freyr Gudmundsson, Philipp Eisen, Erik Poromaa, Alex Nodet, Sami Purmonen, Bartlomiej Kozakowski, Richard Meurling, and Lele Cao
    In 2018 IEEE Conference on Computational Intelligence and Games (CIG, n.k.a. CoG), Aug 2018