Mia Tang

Mia Tang

Master's Student,
Computer Science Department
Stanford University

I am an incoming CS Ph.D. + current Master's student at Stanford University. I have been fortunate to be advised by Professor Maneesh Agrawala. I have also had the privilege of working at the Stanford Vision and Learning Lab (SVL). Previously, I earned my BCSA (Bachelor of Computer Science and Arts) at Carnegie Mellon University, where I was grateful to be advised by Professor Jun-Yan Zhu on generative systems and Professor Kyuha Shim on computational design.

My research explores the intersection of computer graphics, vision, and AI, with a focus on developing interactive, controllable AI systems for visual expression by aligning machine capabilities with natural creative processes.

Email: miatang at cs.stanford.edu

Links: Google Scholar |

Office: Stanford CoDa Building Room E368

Publications

Instance Segmentation of Scene Sketches Using Natural Image Priors

ACM SIGGRAPH 2025

Instance Segmentation of Scene Sketches Using Natural Image Priors

Mia Tang / Yael Vinker / Chuan Yan / Lvmin Zhang / Maneesh Agrawala

Transform your complex raster scene sketch into individual, complete object layers.

Project Page / arXiv / Code (Coming Soon)
CRAFT: Designing Creative and Functional 3D Objects

WACV 2025

CRAFT: Designing Creative and Functional 3D Objects

Michelle Guo* / Mia Tang* / Hannah Cha / Ruohan Zhang / C. Karen Liu / Jiajun Wu

Generate fabricate-able, customizable, and creative everyday objects.

Project Page / arXiv / Code (Coming Soon)
Block and Detail: Scaffolding Sketch-to-Image Generation

UIST 2024

Block and Detail: Scaffolding Sketch-to-Image Generation

Vishnu Sarukkai / Lu Yuan* / Mia Tang* / Maneesh Agrawala / Kayvon Fatahalian

A novel sketch-to-image tool that aligns with the iterative refinement process of artists.

Content-Based Search for Deep Generative Models

SIGGRAPH Asia 2023

Content-Based Search for Deep Generative Models

Daohan Lu* / Sheng-Yu Wang* / Nupur Kumari* / Rohan Agarwal* / Mia Tang / David Bau / Jun-Yan Zhu

A search algorithm for customized and pre-trained deep generative models.

Research & Development Experiences

With a background in traditional graphic design, I'm passionate about bridging research and product by crafting user-facing applications powered by cutting-edge technologies.

[May - December 2023]
Adobe experience

Adobe

Research Engineer Intern

[May - August 2022]
Cesium experience

Cesium

Software Developer Intern

[May - August 2021]
Jam3 experience

Jam3

Developer Intern

[Sep 2021 - May 2022]
Computational Creativity Lab (CCL) experience

Computational Creativity Lab (CCL)

Research Assistant

[Sep 2021 - Mar 2022 ]
Lunar Gala experience

Lunar Gala

Co-Head of Web

[January - August 2021]
CMU School of Design experience

CMU School of Design

Web Designer & Developer

[Jan 2020 - May 2021]
IRIS experience

IRIS

Frontend Engineer

Educational Comics

Turning complex ideas into playful, approachable visuals is a challenge that continues to inspire me. As a comic artist, that exploration takes shape through educational illustrations on technical topics. In my free time, I also volunteer as a math tutor for preschoolers at local schools in Palo Alto.

Educational Comics Collection
*Click on individual topics for the specific set of comics.

          Recent News

          • Upcoming: Our recent work on sketch segmentation has been accepted to SIGGRAPH 2025. See you in Vancouver!
          • Upcoming: We are teaching and organizing some fun workshops at SIGGRAPH this year. Details coming soon.
          • Upcoming: We are organizing a CVPR Workshop on AI for Creative Visual Content Generation and Editing.
          • I received the Stanford School of Engineering Fellowship as an incoming Ph.D. student. ٩(^‿^)۶ 💛
          • I am giving a talk at Stanford Graphics Café on 04/24/2025. Come join us.

          Conference Involvements

          • Workshop: AI for Creative Visual Content Generation Editing and Understanding (CVPR '25)
          • Course [ Notes] : Introduction to Generative Machine Learning (SIGGRAPH '23, SIGGRAPH Asia '23, SIGGRAPH '24)
          • Course [ Notes] : Generative Models for Visual Content Creation (SIGGRAPH '24)
          • Workshop: The Future of Generative Visual Art (CVPR '24)

          University Teaching

          Stanford University

          Carnegie Mellon University

          Community Engagement

          In my side quests as an artist, I explore ways to connect people through visuals.

          Or sometimes, just for fun. (˶ᵔ ᵕ ᵔ˶)

          Tea Painting
          Father's Tea Set, oil on canvas, 2017