Research Paper List

2024 🌸

• [IJCAI 2024] Memorizing Documents with Guidance in Large Language Models
  • Bumjin Park and Jaesik Choi [pdf]
• [ICPRAI 2024] Identifying the Source of Generation for Large Language Models
  • Bumjin Park and Jaesik Choi [pdf]
• [Arxiv] Representation Interpretation of Refusal Mechanism In Large Language Models
  • Bumjin Park, Yeonjea Kim, Jinsil Lee, Youngju Joung and Jaesik Choi [html]
• [Arxiv] Incomplete Prompt Jailbreak
  • Yeonjea Kim, Jinsil Lee, Bumjin Park, Youngju Joung and Jaesik Choi [html]
• [Arxiv] Message based Action Adpater Framework in Multiagent Reinforcement Learning
  • Bumjin Park and Jaesik Choi [pdf]
• [Arxiv] Document Memory Allocation with Set Intersections in Large Language Models,
  • Bumjin Park and Jaesik Choi [pdf]
• [Arxiv] ParchGrad: Controlled Internal Gradients for Reliable Saliency Map
  • Bumjin Park , Giyoung Jeon, and Jaesik Choi [pdf]

2022 📖

• Explanation on Pretraining Bias of Finetuned Vision Transformer.
  • Bumjin Park and Jaesik Choi. [pdf]

2021 🌱

• Cooperative multi-robot task allocation with reinforcement learning
  • Bumjin Park , Cheongwoong Kang, and Jaesik Choi
  • Published in Applied Sciences 12.1 (2021): 272.
  • 🔗 [paper link] [project page]
• Generating Multi-agent Patrol Areas by Reinforcement Learning,
  • Bumjin, Park , Cheongwoong Kang, and Jaesik Choi
  • 2021 21st International Conference on Control, Automation and Systems (ICCAS). IEEE, 2021.

---

🇰🇷 Korean

• 자연어 명령어 기반 군집 로봇 제어 프레임워크 [pdf]
  • 박범진, 최재식
  • 군사과학기술학회 종합학술대회 2024 (제출)
• 대형 언어 모델의 문장 표현의 설명가능적 해석,
  • 박범진, 최재식
  • KSC 2023 (Accepted)
• 멀티 에이전트 강화학습에서의 게이트 기반 메시지 교환.[pdf]
  • 박범진, 강천웅 and 최재식
  • 제어.로봇.시스템학회 논문지, 29(11), 847-853.

    [journal]

• 대형언어모델 생성 텍스트의 원천 문서 추적
  • 박범진 , 최재식 [pdf]
  • KCC 특직원고 2023

---