PeopleofSuperintelligence

Researcher

Cong Yao

Cong Yao is a computer vision researcher whose work helps machines read text in images and understand documents. He studied electronics and information engineering as an undergraduate and completed a PhD in telecommunication and information systems at Huazhong University of Science and Technology in 2014. His work includes an end-to-end sequence recognizer from 2015 and scene-text systems such as EAST, Mask TextSpotter, and Differentiable Binarization. He is a researcher in the NLP Lab at Alibaba DAMO Academy, where he has worked since 2020 on table structure recognition and document instruction data.

Now at
Alibaba
Works
144
Citations
17,280
h-index
40
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2004–2014

    Education and research visits

    From 2004 to 2008, he studies electronics and information engineering as an undergraduate. He completes a PhD in telecommunication and information systems at Huazhong University of Science and Technology in 2014. He interns at Microsoft Research Asia from April 2011 to May 2012 under Prof. Zhuowen Tu and visits Temple University from January to December 2013 under Prof. Longin Jan Latecki.

  2. 2015–2020

    An end-to-end sequence recognizer

    In 2015, he coauthors a neural network that combines feature extraction, sequence modeling, and transcription for scene-text recognition. From 2016 to 2020, he works as a researcher at Megvii.

  3. 2017

    EAST detects scene text

    In 2017, he coauthors EAST, a single-network detector that predicts words or text lines of arbitrary orientations and quadrilateral shapes from full images.

  4. 2018

    Mask TextSpotter reads curves

    In 2018, he coauthors Mask TextSpotter, an end-to-end model for text detection and recognition that handles curved text.

  5. 2019

    Differentiable binarization

    In 2019, he coauthors Differentiable Binarization (DB), a module that integrates thresholding into a segmentation network for scene-text detection.

  6. Since 2020

    Research at Alibaba DAMO

    He joins Alibaba DAMO Academy's NLP Lab as a researcher in 2020. In 2023, he coauthors LORE, a table-structure recognition framework modeled as logical location regression.

  7. 2025

    Evaluating document instruction data

    In 2025, he coauthors ProcTag, a method that assesses document instruction data by tagging instruction execution. He is affiliated with Alibaba Group.

  8. As of October 2026

    Researcher at Alibaba DAMO Academy

    He is a researcher in Alibaba DAMO Academy's NLP Lab, where he has worked since 2020.

Career

  1. Since 2020AlibabaResearcher
  2. 2022–2024Southwest University
  3. 2022–2025Xidian University
  4. 2020–2023Tongji University
  5. 2017–2020Chongqing University
  6. 2016–2020MegviiResearcher
  7. 2013Temple University
  8. 2011–2012Microsoft Research AsiaIntern

Education

  1. 2014Huazhong University of Science and TechnologyPhD

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

  1. 16% of AI career moves in the 2020s went from a university to a companyIncludes Cong Yao. We estimate that 16% of AI career moves in the 2020s went from a university to a company; 29% of moves starting at a university went to a company, and 76% ended the university role.
  2. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes Alibaba. We estimate that alumni of 17 major AI labs went on to found or lead 350 other organizations, including 226 they founded, and we trace 472 career moves directly between 23 labs since 2010.
  3. Universities (31%) and startups and other companies (25%) employ the largest shares of 2020–2026 entrantsIncludes Alibaba. Among 819 people whose first recorded role started in 2020–2026 and who have a known current organization, 60% work in commercial sectors (25% at startups and other companies, 23% at frontier labs and 13% at big tech, with 9 in two), and 31% work at universities, compared with 66% for earlier entrants.
  4. The top 10 organizations employed 22% of people shaping AI in 2025: 51% of company researchers and 21% of university researchersIncludes Alibaba. We estimate the share of people shaping AI who worked at the top 10 organizations each year from 1955 to 2025, comparing concentration across companies, universities, and institutes and labs.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Cong Yao yet. Send us a free-licensed photo.

  1. Cong Yao | alphaXiv alphaxiv.org. Checked 21 October 2026.
  2. An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition arxiv.org. Checked 21 October 2026.
  3. EAST: An Efficient and Accurate Scene Text Detector arxiv.org. Checked 21 October 2026.
  4. Mask TextSpotter: An End-to-End Trainable Neural Network for Spotting Text with Arbitrary Shapes arxiv.org. Checked 21 October 2026.
  5. Real-time Scene Text Detection with Differentiable Binarization arxiv.org. Checked 21 October 2026.
  6. LORE: Logical Location Regression Network for Table Structure Recognition | Proceedings of the AAAI Conference on Artificial Intelligence ojs.aaai.org. Checked 21 October 2026.
  7. ProcTag: Process Tagging for Assessing the Efficacy of Document Instruction Data | Proceedings of the AAAI Conference on Artificial Intelligence ojs.aaai.org. Checked 21 October 2026.