Kunyu Shi

prof_pic.jpg

I’m a Senior Staff Applied Scientist at Alibaba, developing foundational models (LLM, VLM, reasoning, copilot/agent) for B2B trading platforms Alibaba.com and Accio.com. We are hiring!

I was a Senior Applied Scientist at AWS AI Labs (2020–2024), working in VP Stefano Soatto’s team at Caltech, focusing on document understanding and large foundational models (LLM and VLM). I have worked on several AWS AI services in Amazon Textract and Bedrock.

I received my Master in Computer Science from the University of California, San Diego (UCSD) in 2020, and Bachelor of Electrical Engineering from the University of Electronic Science and Technology of China (UESTC) in 2018.

Before joining Amazon, I have worked as research assistant at Machine Learning, Perception, and Cognition Laboratory (mlPC) in UCSD (2019-2020 with Prof. Zhuowen Tu) and Big Data Research Center in UESTC (in 2016 with Prof. Tao Zhou). I worked as research intern at MEDATC in 2018 and Ayers group at McMaster University in 2017 with Prof. Paul W. Ayers.

My academic and industrial research interest includes detection, segmentation, large scale multi-modality learning, large language model and document understanding.

News

Dec 01, 2024 I joined Alibaba as a Senior Staff Applied Scientist.
Feb 28, 2024 2 papers accepted to the CVPR 2024 conference!
Nov 06, 2023 We launched service Custom Queries in Amazon Textract that allows customers to customize their own model specifically trained for their business-specific documents AWS Machine Learning Blog
Aug 28, 2023 AWS generative AI Bedrock service that I contributed to is now generally available. Bedrock Official Introduction Video
Jun 07, 2023 AWS Textract-Tables service has announced new features. Official Release Note

Products

AWS Bedrock provides generative AI foundational models.
Amazon Textract provides ML based intelligent document processing services.

Publications

  1. narvl.png
    Non-autoregressive Sequence-to-Sequence Vision-Language Models
    Kunyu Shi, Qi Dong , Luis Goncalves , Zhuowen Tu , and Stefano Soatto
    In Computer Vision and Pattern Recognition (CVPR) , 2024
    arXiv Code
  2. s4.png
    Enhancing Vision-Language Pre-training with Rich Supervisions
    Yuan Gao* , Kunyu Shi*, Pengkai Zhu , Edouard Belval , Oren Nuriel , Srikar Appalaraju , Shabnam Ghadar , Vijay Mahadevan , Zhuowen Tu , and Stefano Soatto
    In Computer Vision and Pattern Recognition (CVPR) , 2024
    arXiv
  3. ocfusion.png
    Learning Instance Occlusion for Panoptic Segmentation
    Justin Lazarow* , Kwonjoon Lee* , Kunyu Shi*, and Zhuowen Tu
    In Computer Vision and Pattern Recognition (CVPR) , Jun 2020
    arXiv Code