Bumjini

Hi, my name is Bumjin Park, a Ph.D student in the Graduate School of AI in KAIST. My research is focused on the understanding of mechanisms of Artificial Neural Networks motivated by the cognitive mechanism of humans. Feel free to contact for discussions on discovering the secrets of ANNs 🤗.

Currently,
  • 🧑🏻‍🎓 Ph.D Student in KAIST
  • Working on Document Memory Structure in LLMs...

    • Research / Project

    Korean Channels


    News

    Jun 28, 2024 My work, Memorizing Documents with Guidance in Large Language Models , is achieved the best paper award in KCC 2024 XAI Workshop!
    Apr 17, 2024
  • The paper is accepted at IJCAI 2024 🍊
  • [ Memorizing Documents with Guidance in Large Language Models ]
    • Apr 3, 2024
  • The paper is accepted at ICPRAI 2024 🍊
  • [ Identifying the Source of Generation for Large Language Models]
    • Mar 8, 2024 I started youtube to discuss with myself and help other researchers 🙂.
    if you are interested in, visit [link]
    Nov 17, 2023
  • Jan E. Gerken visits our lab to present diffeomorphic counterfactual.
  • KSC 2023 is accepted, yet the score is worse than expected.
  • CVPR 2024 submission is failed because I miss paper registration day.
    		•
    Sep 27, 2023 📃 Paper is published in ICROS journal.
    Title: Message Passing With Gating Mechanisms in Multi-agent Reinforcement Learning
    Sep 1, 2023 🫧 Project with Kolmar is started (viscosity prediction)
    Sep 1, 2023 🧑‍🔬 Becomes SAIL Lab’s representative (1 year)
    Sep 1, 2023 👨‍🎓 KAIST Ph.D Student Begin!
    Nov 12, 2022 Paper is accepted in KAIA 2022 Korea AI Association & Naver
    Title: Explanation on Pretraining Bias of Finetuned Vision Transformer
    Nov 6, 2022 Paper published in KRoC 2023 Korea Robotics Society
    Title: Sample Filtering for Efficient Online Distillation in Reinforcement Learning
    Jun 9, 2022 Paper is published in KIMST 2022 Korea Institute of military science and Technology
    Title: Automatic Analysis of Mobile Robot Decision Process with Layer-wise Relevance Propagation in Reinforcement Learning
    Dec 28, 2021 🌟 Paper is published in MDPI Applied Science Journal
    Title: Cooperative Multi-Robot Task Allocation with Reinforcement Learning
    Dec 27, 2021 🌟 Paper is published in MDPI Sensors Journal
    Title: Scheduling PID Attitude and Position Control Frequencies under Unknown External Disturbances
    Nov 11, 2021 Paper is published in KIMST 2021 Korea Institute of military science and Technology
    Title: Analyzing Conflicting Objectives in Deep Reinforcement Learning-based Target Tracking System
    Oct 12, 2021 📜 Paper is published in ICCAS 2021 International Conference on Control, Automation and Systems
    Title: Generating Multi-agent Patrol Areas by Reinforcement Learning
    Sep 1, 2021 👨‍🎓 KAIST Master Student Begin!

    Feel free to contact me 😄