Milin Kodnongbua

Milin is a Ph.D. student in Computer Science at the University of Washington (UW), Seattle. He is advised by Professor Adriana Schulz and is a part of Graphics and Imaging Laboratory Lab (GRAIL). Milin’s interests are in the domain of computational design and fabrication, where we use computational tools to complement advanced manufacturing techniques, like CNC machines, knitting machines, and 3D printing, to build novel physical artifacts. Currently, his research focuses on representations for computer-aided design (CAD) for optimization and editing.

Milin is currently looking for an internship opportunity as a research assistant. You can take a look at my CV. Please don’t hesitate to email me at [email protected].

Milin is also an active competitive programmers since 2017 with multiple honors. His team, representing the University of Washington, placed in the top 10 in the ICPC North America Championship 2022 and received honorable mention in the ICPC World Finals 2022 in Luxor, Egypt. Currently, Milin is the coach for future UW ICPC teams.

Milin’s personal interests includes photography, playing musical instruments, language learning, badminton, graphics design, and content creation. Milin is an intermediate Korean learner and likes to watch Korean dramas in his free time. Also checkout his piano and guitar performance on his YouTube channel.

Selected Publications

ReparamCAD: Zero-shot CAD Re-Parameterization for Interactive Manipulation

Milin Kodnongbua, Benjamin Jones, Maaz Bin Safeer Ahmad, Vladimir Kim, and Adriana Schulz

In SIGGRAPH Asia 2023 Conference Papers 2023

Abs PDF

Parametric CAD models encode entire families of shapes that should, in principle, be easy for designers to explore. However, in practice, parametric CAD models can be difficult to manipulate due to implicit semantic constraints among parameter values. Finding and enforcing these semantic constraints solely from geometry or programmatic shape representations is not possible because these constraints ultimately reflect design intent. They are informed by the designer’s experience and semantics in the real world. To address this challenge, we introduce ReparamCAD, a zero-shot pipeline that leverages pre-trained large language and image model to infer meaningful space of variations for a shape We then re-parameterize a new constrained parametric CAD program that captures these variations, enabling effortless exploration of the design space along meaningful design axes. We evaluated our approach through five examples and a user study. The result showed that the inferred spaces are meaningful and comparable to those defined by experts. Code and data are at: https://github.com/milmillin/ReparamCAD.
B-Rep Matching for Collaborating Across CAD Systems

Benjamin Jones, James Noeckel, Milin Kodnongbua, Ilya Baran, and Adriana Schulz

ACM Trans. Graph. (SIGGRAPH) Jul 2023

PDF
Self-Supervised Representation Learning for CAD

Benjamin T. Jones, Michael Hu, Milin Kodnongbua, Vladimir G. Kim, and Adriana Schulz

IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR) Jul 2023

PDF
Computational Design of Passive Grippers

Milin Kodnongbua, Ian Good, Yu Lou, Jeffrey Lipton, and Adriana Schulz

ACM Trans. Graph. (SIGGRAPH). Jul 2022

HTML PDF Code

Selected Projects

Competitive Programming

My long journey and achievement in programming competitions.

Emnote

The nicest handwritten note-taking application on Windows.

Loop Termination Buffer

A SystemVerilog implementation of Loop Termination Buffer, an extension to branch predictor, on BlackParrot processor.