Juhyun (Simon) Park

profile.png

I am a second-year masters student in the Department of Computer Science at Princeton University, being advised by Prof. Sanjeev Arora. Previously, I graduated with a Bachelor of Arts in Mathematics at Princeton University.

news

2025-01 Instruct-SkillMix is accepted as a poster at ICLR 2025! See you in Singapore!
2025-01 Announced a new paper Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
2024-10 Instruct-SkillMix is accepted as an Oral presentation at NeurIPS 2024 Workshop in Compositional Learning and as a poster at NeurIPS 2024 Workshop in Fine-Tuning in Modern Machine Learning.
2024-08 Announced Instruct-SkillMix!
2023-05 Graduated Cum Laude from Princeton with a Bachelor’s degree in Mathematics. Thesis: “Infinite-Width 1-Layer ReLU Networks with L2 Regularization on 2D Data” (advised by Prof. Boris Hanin).

selected publications

  1. vlm_s2h.png
    Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?
    Simon Park*, Abhishek Panigrahi*, Yun Cheng*, Dingli Yu, Anirudh Goyal, and 1 more author
    2025
  2. instruct-skillmix.png
    Instruct-SkillMix: A Powerful Pipeline for LLM Instruction Tuning
    Simran Kaur*Simon Park*, Anirudh Goyal, and Sanjeev Arora
    ICLR 2025, 2024
  3. math2.png
    AI-Assisted Generation of Difficult Math Questions
    Vedant Shah, Dingli Yu, Kaifeng Lyu, Simon Park, Jiatong Yu, and 6 more authors
    Math-AI Workshop at NeurIPS 2024, 2024
  4. ug_thesis.png
    Infinite-Width 1-Layer ReLU Networks with L2 Regularization on 2D Data
    Simon Park
    2023
  5. cos324.png
    Introduction to Machine Learning: Lecture Notes for COS324 at Princeton University
    Sanjeev Arora, Simon Park, Dennis Jacob, and Danqi Chen
    2022