Georgia Institute of Technology – Main Campus

Doctor of Philosophy in Computer Science (2019 – present)

  • GPA: 4.0/4.0
  • Advisor: Dr. James M. Rehg

Georgia Institute of Technology – Main Campus

Bachelor of Science in Computer Science (2015 – 2019)

  • Overall GPA: 3.94/4.0
  • Concentrations: Intelligence and Info Internetworks
  • Graduated with Highest Honors


  • Thai, A., Stojanov, S., Huang, Z., Rehg, I., & Rehg, J. M. (2021). The Surprising Positive Knowledge Transfer in Continual 3D Object Shape Reconstruction. arXiv preprint arXiv:2101.07295.
  • Huang, Z., Stojanov, S., Thai, A., Jampani, V., & Rehg, J. M. (2022). Planes vs. Chairs: Category-guided 3D shape learning without any 3D cues. arXiv preprint arXiv:2204.10235.
  • Stojanov, S., Thai, A., & Rehg, J. M. (2021). Using Shape to Categorize: Low-Shot Learning with an Explicit Shape Bias. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 1798-1808).
  • Thai, A., Stojanov, S., Upadhya, V., & Rehg, J. M. (2021, December). 3d reconstruction of novel object shapes from single images. In 2021 International Conference on 3D Vision (3DV) (pp. 85-95). IEEE.
  • Stefan Stojanov, Samarth Mishra, Ngoc Anh Thai, Nikhil Dhanda, Ahmad Humayun, Chen Yu, Linda B. Smith, James M. Rehg; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 8777-8786


Graduate Research Assistant (Fall 2019 – Present)

  • Current research generally focuses on computer vision problems inspired by developmental psychology
  • Investigating the properties of self-supervised visual representation learning under scenarios that closely resemble infant learning
  • Understanding the relationship between 3D object shapes and categorization in few-shot and continual learning settings

Undergraduate Research Assistant (Fall 2017 – Spring 2019)

  • Advised by Dr. Jim Rehg
  • Published “Incremental Object Learning from Contiguous Views” (CVPR 2019 – Oral, best finalist) as joint second author
  • Investigated domain shift in transfer learning from synthetic to real-world data and the robustness of self-supervised object 3D representation learning


Meta Reality Labs Research

Research Intern (May 2021 – Aug 2021)

  • Incremental learning of object representations


Software Engineering Intern (May 2018 – Aug 2018)

  • Devised a new task assigning algorithm to improve human label quality
  • Formulated new architectures to classify an imbalanced and large-scale dataset of YouTube videos
  • Used: SQL, C++, TensorFlow, and Colab


Software Engineering Intern (May 2017 – Aug 2017)

  • Implemented the client code of the in-app notification screen of Google Ads app
  • Used: Flutter framework and Dart



Python, Java, MATLAB


PyTorch, TensorFlow, Blender, OpenCV


Faculty Honors

Georgia Institute of Technology

Achieved 4.0 GPA in Fall 2015, Spring 2016, Fall 2016, Spring 2017, Spring 2018, Fall 2018, and Spring 2019

Bronze Medal in World CodeSprint 4

HackerRank (June 2016)

Competed against 5236 participants around the world

Second Prize in Vietnam National Mathematical Olympiad (VMO 2014)

Ministry of Education and Training (Jan 2014)