Rio Aguina-Kang

I’m a Research Engineer passionate about building AI systems that support human creativity and visual communication. I work at the intersection of Computer Vision, Computer Graphics, and Cognitive Science, specializing in generative modeling for 3D scenes and images. My research focuses on creating tools that help people generate, edit, and manipulate visual content in ways that align with human intent. I’m particularly interested in how large generative models can empower users to create complex 3D content they can guide and control. I graduated from the University of California, San Diego in Cognitive Science (Machine Learning & Neural Computation), with minors in Mathematics and Data Science.

I currently work as Research Staff in the Cognitive Tools Lab @ Stanford with Prof. Judy Fan, studying how people engage in creative tasks and interact with AI systems. I develop large-scale web experiments to collect multimodal datasets that benchmark AI performance and inform AI tool design for creative workflows.

Previously, I was a Research Scientist/Engineer Intern at Adobe Research with Dr. Matheus Gadelha, where I developed methods to generate 3D scenes with single images using various foundation models. I also worked at the Visual Computing Group @ Brown University with Prof. Daniel Ritchie, building 3D scene generation systems that leverage LLM program synthesis.

I’m currently seeking full-time roles as a Research Engineer, AI/ML Engineer, or Data Scientist, focusing on AI/ML applications for creative tools.

If you’d like to chat, feel free to shoot me an email at raguinakangus@gmail.com. Looking forward to meeting you!