HyunJin, Kim

About Me

Hello! I am a Ph.D. student at Sungkyunkwan University (SKKU), where I am advised by Professor JinYeong Bak in the Human Language Intelligence Lab.

I am also in a Ph.D. Collaborator program with Microsoft, where I have worked under supervision of Dr. Young Jin Kim to explore effective offsite-tuning techniques for generative models.

Currently, I am a research intern at Microsoft Research Asia (MSRA) under the guidance of Dr. Xiaoyuan Yi. My work at MSRA focuses on Superalignment and AI Safety.

My research interests include natural language processing, parameter-efficient fine-tuning, retrieval-augmented generation, superalignment, and deep learning model analysis

Education

• Sungkyunkwan University, South Korea.
  Ph.D., Artificial Intelligence, 2023~Present
• Sungkyunkwan University, South Korea.
  M.S., Artificial Intelligence, 2021~2023
• Kyonggi University, South Korea.
  B.S., Computer Engineering (Transferred), 2019~2021
  B.S., Early Childhood Education, 2015~2019

International Conferences and Journals

1. PEMA: An Offsite-Tunable Plug-in External Memory Adaptation for Language Models
   HyunJin Kim, Young Jin Kim, JinYeong Bak
   [Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)] 2024.
   PDF Code

2. A Transformer-based Function Symbol Name Inference Model from an Assembly Language for Binary Reversing
   HyunJin Kim, JinYeong Bak, Kyunghyun Cho, and Hyungjoon Koo
   [In the 18th ACM Asia Conference on Computer and Communications Security (ASIACCS)] 2023.
   PDF Code

3. Associative Knowledge Graph Using Fuzzy Clustering and Min-Max Normalization in Video Contents
   Hyun-Jin Kim, Ji-Won Baek, Kyungyong Chung
   [IEEE Access] 2021.
   Link PDF

Domestic Conferences and Journals

1. Function Name Prediction using Binary Code with Transformer
   HyunJin Kim and JinYeong Bak
   [The Korean Institute of Information Scientists and Engineers] 2021.

2. Traffic Knowledge Graph using Associative Document Weight
   Hyun-Jin Kim, Min-Jeong Kim, Ju-Chang Kim, Kyungyong Chung
   [International Conference on Convergence Technology] 2020.

3. Association Rule based Video Knowledge Extraction using Object Detection Algorithm
   Hyun-Jin Kim, Hye-Jeong Kwon, Ji-Hye Gwon, Kyungyong Chung [Korean Society for Internet Information] 2020.

4. Data Bias Optimization based Association Reasoning Model for Road Risk Detection.
   Seong-Eun Ryu, Hyun-Jin Kim, Byung-Kook Koo, Hye-Jeong Kwon, Roy C Park, Kyungyong Chung
   [Journal of the Korea Convergence Society] 2020.

Teaching Experience

• Open Source Software Practice, (SKKU)
  Teaching Assistant {Spring 2023, Fall 2023, Spring 2024}

• K-mooc : Mathematics for AI, (SKKU)
  Dev Teaching Assistant (Summer 2021)

Talks

• PEMA: An Offsite-Tunable Plug-in External Memory Adaptation for Language Models
  RIKEN, (Summer 2024 - Expected)

• An Offsite-Tunable Plug-in External Memory Adaptation and Embedding Temporal Awareness for Retrieval-Augmented Generation
  SKT, (Spring 2024)

• A Transformer-based Function Symbol Name Inference Model from an Assembly Language for Binary Reversing
  IBM Research, (Fall 2023)

• A Transformer-based Function Symbol Name Inference Model from an Assembly Language for Binary Reversing
  SKKU AI Colloquium, (Fall 2022)

• Function Name Prediction from Binary Code with Transformer
  New York University, (Fall 2021)

Award

• PEMA: An Offsite-Tunable Plug-in External Memory Adaptation for Language Models, (1st International NLP Workshop @ KAIST 2024)
  Best Poster Award

Work Experience

• Research Intern, Microsoft Research Asia, (Fall, 2024 ~ Present)
  Currently working on research projects focused on superalignment and AI safety.

• Research Intern, Deargen Inc, (Summer, 2022)
  I interned with Dr. Bonggun Shin in Deargen USA. I analyzed the differences in synthetic essentiality (SE) scores by inserting new fingerprint data into a cancer dependency prediction model that contains cancer cell lines (CCLs) with different mutation environments.

Academic Services

• IJCAI 2024
  Student Vounteer

• NAACL 2024
  Student Vounteer

• ACM FAccT 2022
  Student Vounteer

Extracurricular Activities

• Optimistic, Pessimistic and Realistic of Large Language Models
  KOFST, Assistant, 2023

• State, Limitations, and Future of Large Language Models
  KOFST, Assistant, 2022

Reference

• Prof. JinYeong, Bak, SKKU, jy.bak@skku.edu
• Dr. Xiaoyuan Yi, Microsoft Research Asia, xiaoyuanyi@microsoft.com
• Dr. Young Jin, Kim, Microsoft, youki@microsoft.com
• Dr. Bonggun, Shin, Deargen-USA, bonggun.shin@deargen.me
• Prof. Hyungjoon Koo, SKKU, kevin.koo@skku.edu
• Prof. Kyungyong, Chung, KGU, dragonhci@daum.net