About Me

Yoonsik Park

M.S. Student · KAIST AI · MLILAB

I am an M.S. student in the Kim Jaechul Graduate School of AI at KAIST, working in MLILAB advised by Prof. Eunho Yang.

My current research focuses on visual reasoning in multimodal large language models, with interests in faithfulness, hallucination mitigation, and robust multimodal learning.

Previously, I received a B.S. in Data Science from Hanyang University, graduating early with Summa Cum Laude (Ranked 1st in Dept. of Data Science).

Affiliation
KAIST AI · MLILAB
Research
Visual reasoning in multimodal large language models
Skills
Python · PyTorch

News

2026
📄 BiasEdit accepted to WWW 2026 (Oral Presentation). My first Paper!
Mar. 2026
🎓 Started M.S. at KAIST AI and joined MLILAB.
Dec. 2025
🔬 Joined NAVER Place AI as a research intern.
Aug. 2025
🏅 Graduated early in 7 semesters from Hanyang University with Summa Cum Laude (Ranked 1st in the Department of Data Science).
Thanks, Hanyang! 🦁
Jun. 2025
🧪 Joined KAIST MLILAB as an undergraduate research intern.
Feb. 2024
🌱 Joined BAIKLAB at Hanyang University as an undergraduate research intern.

Education

M.S. in Kim Jaechul Graduate School of AI

KAIST · MLILAB · Advisor: Prof. Eunho Yang

  • Research on visual reasoning in multimodal large language models.

B.S. in Data Science

Hanyang University (Seoul)

  • Cumulative GPA: 4.35/4.5 · Major GPA: 4.38/4.5.
  • Early graduation with Summa Cum Laude (Ranked 1st in Dept. of Data Science).

Experiences

Research Intern

NAVER Place AI

  • Worked on passage-level domain detection for review verification.
  • Designed a classification head and task-specific loss for fine-grained text–metadata alignment.

Undergraduate Research Intern

KAIST · MLILAB · Advisor: Prof. Eunho Yang

  • Investigated methods to mitigate hallucinations in multimodal large language models.
  • Focused on improving visual faithfulness so generated text remains grounded in image evidence.

Undergraduate Research Intern

Hanyang University · BAIKLAB · Advisor: Prof. Sungyong Baik

  • Conducted research on debiasing vision models trained on web-sourced image data.
  • Extended the study to vision-language models such as CLIP, focusing on bias-robust soft prompts and worst-group robustness.

Publication

BiasEdit: A Training-Free Bias-Detect-and-Edit Framework for Learning Fair Visual Classifiers

Jungwook Seo, Yoonsik Park, Changmin Lee, and Sungyong Baik

WWW 2026 Oral Presentation

Projects

HBD (Harnessing Bias for Debiasing)

Graduation Project · Hanyang University · Feb 2025 — Jun 2025

Developed a plug-in debiasing framework with PCA-based class-stratified analysis and bias-aware soft prompt refinement.

Fairness Vision-Language Robustness

Notify: LLM-based Personal Schedule Assistant

DL Application Project · Mar 2025 — Jun 2025

Built a mobile app that predicts personalized departure times by combining schedules, traffic signals, and persona-aware LLM reasoning.

LLM Flutter AWS

The Motivational Organizer & Mentor (M.O.M.)

Google Gemma Sprint · Sep 2024 — Oct 2024

Built a persona-driven conversational agent based on Gemma 2 for empathetic, nudge-based productivity support.

Gemma Personal AI Productivity

F.D.A.: Fine Dining Assistant

HCI Project · Sep 2024 — Dec 2024

Built a RAG-based fine-dining chatbot that simulates professional service personas to deliver personalized, experiential fine-dining previews.

RAG HCI User Study

Cooling with Nature

Time Series Project · Sep 2024 — Dec 2024

Developed a hybrid ARIMAX-Transformer time-series model to forecast data center cooling consumption and optimize locations for energy efficiency.

Time Series ARIMAX Transformer