RioAguina-Kang

AI systems for human creativity and visual communication.

San Francisco, CA

I build AI systems that support human creativity and visual communication. My work draws from Computer Vision, Computer Graphics, and Cognitive Science to create tools that let users generate, edit, and control visual content in ways that make sense for people.

Hand drawn triangulation and hatching
Portrait of Rio Aguina-Kang

I currently work as a Machine Learning Engineer at Drafted, building systems that support personalized floorplan generation.

I graduated from the University of California, San Diego with a degree in Cognitive Science (Machine Learning & Neural Computation), with minors in Mathematics and Data Science.

During that time, I worked as Research Staff in the Cognitive Tools Lab at Stanford with Prof. Judy Fan, where I designed large-scale web experiments to study human-AI interaction and inform the development of creative tools.

I've also worked as a Research Scientist/Engineer Intern at Adobe Research with Dr. Matheus Gadelha. Before that, I spent a summer with the Visual Computing Group at Brown University, working with Prof. Daniel Ritchie on 3D scene generation systems that leverage LLM program synthesis.

Selected work

Publications

3DV2026

Seeing Through Clutter: Structured 3D Scene Reconstruction via Iterative Object Removal

Rio Aguina-Kang, Kevin James Blackburn-Matzen, Thibault Groueix, Vladimir Kim, Matheus Gadelha

SIGGRAPH Asia2025

Procedural Scene Programs for Open-Universe Scene Generation: LLM-Free Error Correction via Program Search

Maxim Gumin, Do Heon Han, Seung Jean Yoo, Aditya Ganeshan, R. Kenny Jones, Kailiang Fu, Rio Aguina-Kang, Stewart Morris, Daniel Ritchie

Arxiv preprint2024

Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases

Rio Aguina-Kang, Maxim Gumin, Do Heon Han, Stewart Morris, Seung Jean Yoo, Aditya Ganeshan, R. Kenny Jones, Qiuhong Anna Wei, Kailiang Fu, Daniel Ritchie

PDF

NeurIPS Datasets and Benchmarks2023

SEVA: Leveraging sketches to evaluate alignment between human and machine visual abstraction

Kushin Mukherjee, Holly Huey, Xuanchen Lu, Yael Vinker, Rio Aguina-Kang, Ariel Shamir, Judith Fan