Kookmin University Student Kim Chan-joong Takes Second Place at the International AI Hackathon “IBM Bob Hackathon”
- 26.06.30 / 홍유민
Kim Chan-joong, a student in the Department of Artificial Intelligence at the College of Software Convergence at Kookmin University (President Jeong Seung Ryul), took second place at the international AI hackathon “IBM Bob Hackathon” on Thursday, June 11.
This international hackathon was co-hosted by NativelyAI, which operates the AI hackathon platform lablab.ai, and IBM. Participants were tasked with developing software within a limited timeframe using the AI development tool “Bob.” The event attracted 5,628 participants and 1,672 teams from around the world, with a total of 503 entries submitted.
Kim Chan-joong, who participated as an individual, developed “Atlas,” a web application that visualizes the structure of a code repository like a city map. “Atlas” is a tool that displays the structure of a code repository as a single image; it addresses the challenge—where large-scale software inevitably contains numerous folders and files, making it difficult for first-time viewers to grasp the overall structure—by drawing an analogy to a city map.
When users enter the URL of a repository published on GitHub—a platform where developers share code—the top-level folders are displayed as color-coded zones, and files are represented as buildings of varying sizes based on the amount of code they contain. Key files are highlighted like major landmarks on a map, allowing users to intuitively grasp the overall structure and identify important files even when viewing a code repository for the first time.
The map is automatically generated by analyzing the repository structure, and the layout calculations are processed on the server. As a result, users can view the results in a web browser without any separate installation. The completed map can be zoomed in on or panned; hovering over a specific file displays its information; and there is also a feature to download the entire map as an image.
Student Kim Chan-joong said, “I wanted to try something fresh, moving away from the topics commonly covered in AI projects,” adding, “I often found that it took a long time to understand the structure of code I’d never seen before, so I wanted to address that inconvenience in an intuitive way, like a city map.”
He continued, “I scaled back my ambitions and focused on getting the core functionality right,” adding, “I want to use this experience as a stepping stone to continue exploring new ideas in the future.”
△ (From left) Presentation of results from the IBM Bob Hackathon; Kim Chan-joong, a student in the Department of Artificial Intelligence
|
This content is translated from Korean to English using the AI translation service DeepL and may contain translation errors such as jargon/pronouns. If you find any, please send your feedback to kookminpr@kookmin.ac.kr so we can correct them.
|
|
Kookmin University Student Kim Chan-joong Takes Second Place at the International AI Hackathon “IBM Bob Hackathon” |
||||
|---|---|---|---|---|
|
2026-06-30
140
Kim Chan-joong, a student in the Department of Artificial Intelligence at the College of Software Convergence at Kookmin University (President Jeong Seung Ryul), took second place at the international AI hackathon “IBM Bob Hackathon” on Thursday, June 11. This international hackathon was co-hosted by NativelyAI, which operates the AI hackathon platform lablab.ai, and IBM. Participants were tasked with developing software within a limited timeframe using the AI development tool “Bob.” The event attracted 5,628 participants and 1,672 teams from around the world, with a total of 503 entries submitted. Kim Chan-joong, who participated as an individual, developed “Atlas,” a web application that visualizes the structure of a code repository like a city map. “Atlas” is a tool that displays the structure of a code repository as a single image; it addresses the challenge—where large-scale software inevitably contains numerous folders and files, making it difficult for first-time viewers to grasp the overall structure—by drawing an analogy to a city map. When users enter the URL of a repository published on GitHub—a platform where developers share code—the top-level folders are displayed as color-coded zones, and files are represented as buildings of varying sizes based on the amount of code they contain. Key files are highlighted like major landmarks on a map, allowing users to intuitively grasp the overall structure and identify important files even when viewing a code repository for the first time. The map is automatically generated by analyzing the repository structure, and the layout calculations are processed on the server. As a result, users can view the results in a web browser without any separate installation. The completed map can be zoomed in on or panned; hovering over a specific file displays its information; and there is also a feature to download the entire map as an image. Student Kim Chan-joong said, “I wanted to try something fresh, moving away from the topics commonly covered in AI projects,” adding, “I often found that it took a long time to understand the structure of code I’d never seen before, so I wanted to address that inconvenience in an intuitive way, like a city map.” He continued, “I scaled back my ambitions and focused on getting the core functionality right,” adding, “I want to use this experience as a stepping stone to continue exploring new ideas in the future.”
△ (From left) Presentation of results from the IBM Bob Hackathon; Kim Chan-joong, a student in the Department of Artificial Intelligence
|
||||
