Hello, I'm Jinu Choi, Researcher.
Building accessible systems that bring real change to people's lives. Currently researching human-in-the-loop accessibility at KAIST NCLab.
Building accessible systems that matter
Hi, I'm Jinu Choi, a researcher at KAIST NCLab. I'm deeply interested in system design, particularly mobile computing and user interfaces.
Currently, I'm working on human-in-the-loop accessibility systems for visually impaired users and the privacy challenges that come with them.
I dive deep into new problems and prefer learning new technologies for research rather than relying on existing ones. I love bringing real change to people's lives through my work.
2022.09 ~ 2024.08
2017.03 ~ 2022.08
Things I'm thinking about
Sharing thoughts on technology, design, and the future. Hoping these ideas will evolve into projects someday.
AI Agent Memory System
Instead of storing answers, store functions. Extract knowledge inductively from conversations— preserving context like who, when, and under what conditions. Rule-based reasoning over value-based retrieval.
02Spark System
Capture fleeting ideas in 2 seconds, auto-link to existing notes, and build meta-cognition over time. Making Claude an AI that truly knows me through thought pattern analysis.
03Private Music Archive
A private SoundCloud for music clubs—stream, search by lyrics or credits, visualize collaboration networks. Digitize years of CDs gathering dust into a searchable archive.
Projects
Chaperone
A privacy-preserving system for visually impaired users receiving remote assistance. Modified AOSP to filter sensitive information at the framework level before sharing with helpers.
Hivemind Field Trial
Field trial research on instant social control of shared devices in public spaces. Deployed in classrooms and cafeterias to analyze user behavior. Published in IMWUT.
Sidekick AI
A context-aware system that monitors driver status during voice chatbot conversations. Uses T Map SDK to predict road conditions and pauses conversations in high-attention zones.
ButtonTap
Wearable interaction using shirt buttons with embedded microphones to classify object contact sounds. Achieved high accuracy object recognition using SVM-based algorithms.
AR/VR Vocational Training
AR/VR application for students with developmental disabilities to practice car-sharing vehicle inspection. Developed tablet AR and Oculus VR simultaneously using Unity and AR Foundation.
Crosswalk Navigation for VIP
App that recognizes crosswalks via camera and guides walking direction by tracking user position. Designed intuitive vibration patterns and low-vision friendly UI. (Patent filed)