hoyun (3).jpg

$$ \Huge \textbf {Hoyun Youm} \\ \newline \small Graduate \space Student - South \space Korea $$

Hello! My name is Hoyun Youm, a Ph.D. student at the Compiler Research Laboratory (Corelab) at Yonsei University, Seoul, South Korea.

My research interests include compilers, machine learning systems, and privacy-preserving computing. I am particularly interested in hardware-aware optimization techniques for AI/ML workloads, with current work focusing on compiler infrastructures for Fully Homomorphic Encryption and encrypted machine learning systems.

CONTACT


📩 [email protected]

🌐 corelab@yonsei

🗺️ Seoul, South Korea

CV


http://corelab.or.kr/CV/hoyun-full.pdf**_CV**

INTERESTS


SOCIALS


<aside> <img src="https://prod-files-secure.s3.us-west-2.amazonaws.com/822ffd51-d4b1-4f8b-a024-c0a5310887ad/46a01e87-8cf8-4ca8-98b3-f6bc18fbef39/linkedin_480px.png" alt="https://prod-files-secure.s3.us-west-2.amazonaws.com/822ffd51-d4b1-4f8b-a024-c0a5310887ad/46a01e87-8cf8-4ca8-98b3-f6bc18fbef39/linkedin_480px.png" width="40px" /> @hoyun-corelab

</aside>

https://embed.notionlytics.com/wt/ZXlKM2IzSnJjM0JoWTJWVWNtRmphMlZ5U1dRaU9pSnJNVlkxVUVGblpITk9XbEY1Tm1rNFExbEhTQ0lzSW5CaFoyVkpaQ0k2SWpRNU1HSTVZVGN5TmpBNVpEUmxNMk5pWmpGbVltRTJOVFkyTW1Vd01XWmlJbjA9

EDUCATION


2024.03 - Present

Student | Yonsei University, Seoul, Republic of Korea

M.S./Ph.D. Student, Advisor: Prof. Hanjun Kim

Research Project: Compiler Optimization for Fully Homomorphic Encryption

2018.03 - 2024.03

Student | Yonsei University, Seoul, Republic of Korea

Bachelor’s Degree in Electrical and Electronic Engineering

EXPERIENCE


2024.03 - Present

Working Position | Graduate Student

Compiler Research Laboratory (Corelab), Yonsei University, Seoul, Republic of Korea

2023.01 - 2024.03

Working Position | Undergraduate Intern

Compiler Research Laboratory (Corelab), Yonsei University, Seoul, Republic of Korea

RECOGNITION


Award | 🥇 1st Place, Google Graph Scheduling Competition at MLSys 2026

Title: Pre-detecting Structural Opportunities for Gemini-Driven DAG Scheduling [Photo][Link]

Award | 🥉 Bronze, Samsung Humantech Paper Awards 2026

Title: Compiler-Runtime Co-operative Chain of Verification for LLM-Based Code Optimization [Photo][Link]

Award | 🥉 3rd Place: ASPLOS / EuroSys 2025 Contest Track

Title: Optimized Neuron Kernel Interface (NKI) Implementation of Llama 3.2 1B (Inference) [Photo] [Link]

Award | 🥇 1st Place: Student Research Competition at CGO 2025

Title: Range Analysis Compiler for Encrypted Vector Computation [Link]

Award | 🥇 Grand Prize: ICT Challenge hosted by Ministry of Science and ICT September 2023

Title: Fully Homomorphic Encryption Compiler for Privacy-Preserving Machine Learning [Link]

Scholarship | The National Scholarship for Science and Engineering March 2018 ~ March 2024

Full funding for a bachelor's degree

PUBLICATIONS


Compiler-Runtime Co-operative Chain of Verification for LLM-Based Code Optimization [Abstract] [IEEE Xplore]

Hyunho Kwon, Sanggyu Shin, Ju Min Lee, Hoyun Youm, Seungbin Song, Seongho Kim, Hanwoong Jung, Seungwon Lee, and Hanjun Kim Proceedings of the 2026 International Symposium on Code Generation and Optimization (CGO), January 2026

**Approximation-based Inter-PE Communication-free Image Filtering for Commodity PIM (Poster) [Abstract]

****Chan Lee, Shinnung Jeong, Heelim Choi, Jaeho Lee, Haeeun Jeong, Hoyun Youm, Ju Min Lee, and Hanjun Kim Proceedings of the 62nd Annual Design Automation Conference 2025 (DAC)

HALO: Loop-aware Bootstrapping Management for Fully Homomorphic Encryption [Abstract] [ACM]

****Seonyoung Cheon, Yongwoo Lee, Hoyun Youm, Dongkwan Kim, Sungwoo Yun, Kunmo Jeong, Dongyoon Lee, and Hanjun Kim ACM International Conference on Architectural Support for Programming Languages and Operating Systems 2025 (ASPLOS) Accept Rate: 12% (65/510)

Privacy Set: Privacy Authority-Aware Compiler for Homomorphic Encryption on Edge-Cloud System [Abstract] [IEEE Xplore]

Dongkwan Kim, Yongwoo Lee, Seonyoung Cheon, Heelim Choi, Jaeho Lee, Hoyun Youm, Dongyoon Lee, and Hanjun Kim IEEE Internet of Things Journal, August 2024 IF=8.2, Q1 (JCR 2023)