avatar

Seunghwan Lee

M.S. Student
Sungkyunkwan Univ.
nommis911@gmail.com


about me

I am a machine learning researcher focused on model compression, multi-task model merging, and test-time adaptation. I received my M.S. from Sungkyunkwan University (2026), advised by Prof. Sungeun Hong. I am currently seeking research or engineering positions in machine learning.

educations

publications

Equal contribution are denoted by *

  1. MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Model
    Youngwan Lee, Soojin Jang, Yoorhim Cho, Seunghwan Lee, Yong-Ju Lee, Sung Ju Hwang
    preprint
    PDF Code Project Page

  2. ICML
    SyMerge: From Non-Interference to Synergistic Merging via Single-Layer Adaptation
    Aecheon Jung, Seunghwan Lee, Dongyoon Han, Sungeun Hong
    International Conference on Machine Learning (ICML), 2026.
    PDF Code Project Page

  3. ICCV
    Task Vector Quantization for Memory-Efficient Model Merging
    Youngeun Kim*, Seunghwan Lee*, Aecheon Jung*, Bogon Ryu, Sungeun Hong
    International Conference on Computer Vision (ICCV), 2025.
    PDF Code Project Page

  4. Instance-Aware Test-Time Segmentation for Continual Domain Shifts
    Seunghwan Lee*, Inyoung Jung*, Hojoon Lee, Eunil Park, Sungeun Hong
    preprint
    PDF

  5. PRL
    Prototypical class-wise test-time adaptation
    Hojoon Lee, Seunghwan Lee*, Inyoung Jung*, Sungeun Hong
    Pattern Recognition Letters, 2025.
    PDF

projects

honors and awards

internships


Powered by Jekyll and Minimal Light theme.