Location via proxy:   
[Report a bug]   [Manage cookies]                

Geunwoo Kim

I am a Ph.D. student in Computer Science at UC Irvine, under the supervision of Prof. Michael Franz and Prof. Pierre Baldi.

My research experience includes work at LG AI Research on improving code LLMs with reinforcement learning, and at Coupang where I enhanced search retrieval relevance using large-scale graph neural networks. During my graduate studies, I've been mentored by Dr. Stephen McAleer for my research on LLM-based agents. Also I have collaborated with Prof. Dokyung Song on graph representation learning for binary code analysis. I obtained my B.S. in Computer Science from Pohang University of Science and Technology, where I researched blockchain security with Prof. Jong Kim. My research background also includes blockchain development experience and work on network layer security with Prof. Min Suk Kang at the National University of Singapore.

Email  /  Google Scholar  /  LinkedIn  /  Github

profile photo
Research

My current research interests are centered on the development and application of LLM-based agents.

Deep Learning Assisted Imaging Methods to Facilitate Access to Ophthalmic Telepathology
Geunwoo Kim*, Andrew W. Browne*, Anderson N. Vu, Josiah K. To, Don S. Minckler, Maria Del Valle Estopinal, Narsing A. Rao, Christine A. Curcio, Prof. Pierre F. Baldi
Ophthalmology Science 2023

We propose employing super-resolution imaging techniques, specifically utilizing the Denoising Diffusion Probabilistic Model (DDPM), to create high-fidelity pathology slide images. This approach offers a cost-effective alternative to advanced digital slide scanners for remote telepathology services using commonly available smartphones.

Language Models can Solve Computer Tasks
Geunwoo Kim, Prof. Pierre Baldi, Stephen McAleer
NeurIPS 2023
AI & HCI workshop @ ICML 2023
project page / arXiv

A pre-trained large language model agent can execute computer tasks guided by natural language using a simple prompting scheme, recursively criticizing and improving its output.

Improving Cross-Platform Binary Analysis using Representation Learning via Graph Alignment
Geunwoo Kim, Sanghyun Hong, Prof. Michael Franz, Prof. Dokyung Song
International Symposium on Software Testing and Analysis (ISSTA) 2022
project page / video / paper

We propose XBA that uses a semisupervised approach to generate binary code embeddings which are aligned across platforms by collecting peripheral information of binary code using graph neural network.

The Ticket Price Matters in Sharding Blockchain
Geunwoo Kim, Prof. Michael Franz, Prof. Jong Kim
International Workshop on Cryptocurrencies and Blockchain Technology (ESORICS workshop) 2022
code / paper

We explore the impact of non-democratic environments on the security and scalability of blockchain sharding, proposes metrics to analyze the trade-off between security and scalability.

This webpage template was recycled from here