8000 GitHub - the-jb/profile: AI Researcher
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

the-jb/profile

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 

Repository files navigation

JB is currently a research assistant at the Algorithmic Intelligence Lab at the Korea Advanced Institute of Science and Technology (KAIST), under the guidance of Jinwoo Shin. He delves into the true nature of deep learning through the lens of human cognitive systems, specifically focusing on how humans acquire, process, and apply knowledge. Before joining KAIST, JB led AI research for patent analysis and retrieval systems at Tanalysis. He obtained a Master’s Degree in Artificial Intelligence from Yonsei University, where he explored neural architectures and their foundation in formal language, advised by Yo-Sub Han. Prior to his journey into AI research, JB worked as a Software Engineer at Samsung Electronics.


Research Interests

  • Designing Neural Architectures Modeled on Human Cognitive Systems
    Cognitive systems play a pivotal role in advancing neural architectures for perception, cognition and reasoning. Research aims to reach optimal neural architectures by aligning them with human cognition.

  • Advancing Knowledge Access to Deep Models
    Despite the vast knowledge stored in deep models, accessing and leveraging those knowledge remains a challenge. Research encompasses broad spectrum of knowledge for neural models, from information retrieval to understanding dynamics of complex reasoning.

  • Deep Learning for Language Acquisition with Minimal Data
    Large language models (LLMs) achieve language comprehension through vast amounts of data, whereas humans can acquire language from only a small amount of experience, known as the "poverty of the stimulus" argument. Research seeks deep learning methods that can effectively learn language with limited data by leveraging linguistic features.


Publications

For further information, please refer to Google Scholar.

  • ATHENA: Mathematical Reasoning with Thought Expansion. [arXiv] [emnlp-23] [code]
    JB. Kim, Hazel Kim, Joonghyuk Hahn, Yo-Sub Han.
    In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023), 16315–16327, 2023

Experience

  • Research Assistant, Algorithmic Intelligence Lab, KAIST. (Advisor: Jinwoo Shin) Jan '25 ~ Present

  • AI Research Scientist, Tanalysis. Nov '23 ~ Dec '24

  • Master of Artificial Intelligence, Yonsei University. (Advisor: Yo-Sub Han) Sep '21 ~ Aug '23

  • Software Engineer, Samsung Electronics. Feb '17 ~ Aug '19


Contact

About

AI Researcher

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published
0