About

I am currently an AI researcher at TelePIX (Alternative military service: Technical research personnel). I completed my M.S. degree at Yonsei University (Department of Artificial Intelligence), advised by Prof.Noseong Park in the Bigdata Analytics Lab (now at KAIST), and continue to collaborate closely on research. My primary research areas include scientific machine learning, foundation model, implicit neural representations (INR) and satellite technology. I also interested in deep learning frameworks based on meta-learning, and data compression method. Looking ahead, I aim to advance physics simulation techniques that combine numerical analysis with scientific ML (e.g., physics-informed neural networks and neural operators), ultimately building AI systems taht are mathematically and statistically interpretable.

I greatly enjoy collaborating with researchers who share similar interests. If you are interested in my research areas or would like to collaborate, please feel free to contact me!(woojin.py@gmail.com)


Publication

Learning Low Rank Neural Representations of Hyperbolic Wave Dynamics from Data
W Cho, K Lee, N Park, D Rim, G Welper
(Under review)
[Paper]

Sequential Dataset for Satellite Pose Estimation and a Frequency-Space Neural Operator for HIL-Free Generalization Benchmarking
W Cho*, J Park*, S Immanuel, S Chin, J Wang
(Under review)

DRIFT: Dynamics-aware Robust Inference with Latent Filtering for Temporal Satellite Pose Estimation
J Park*, W Cho*, J Park, D Kwon
(Under review)

Meta-learning Structure-Preserving Dynamics
C Jing, U Mudiyanselage, W Cho, M Jo, A Gruber, K Lee
(Under review)
[Paper]

MaD-Scientist: AI-based Scientist solving Parabolic PDEs using Massive Prior Data
M Kang, D Lee, W Cho, J Park, K Lee, A Gruber, Y Hong, N Park
(Under review)
[Paper]

PDEfuncta: Spectrally-Aware Neural Representation for PDE Solution Modeling
M Jo*, W Cho*, U Mudiyanselage, S Lee, N Park, K Lee
NeurIPS 2025
[Paper]

PIANO: Physics-informed Dual Neural Operator for Precipitation Nowcasting
S Chin, W Cho, J Park
NeurIPS Workshop 2025

Fourier-Modulated Implicit Neural Representation for Multispectral Satellite Image Compression
W Cho*, S Immanuel*, J Heo, D Kwon
IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2025 (Oral)
[Paper]

FastLRNR and Sparse Physics Informed Backpropagation
W Cho, K Lee, N Park, D Rim, G Welper
Results in Applied Mathematics 2025
[Paper]

Unveiling the Potential of Superexpressive Neural Networks in Implicit Neural Representations
U Mudiyanselage, W Cho, M Jo, N Park, K Lee
ICLR Workshop 2025
[Openreview]

Tackling Few-Shot Segmentation in Remote Sensing via Inpainting Diffusion Model
S Immanuel, W Cho, J Heo, D Kwon
ICLR Workshop 2025(Best Paper)
[Paper] [Code] [Project]

Neural Functions for Learning Periodic Signal
W Cho*, M Jo*, K Lee, N Park
ICLR 2025
[Paper]

Can we pre-train ICL-based SFMs for the zero-shot inference of the 1D CDR problem with noisy data?
M Kang, D Lee, W Cho, K Lee, A Gruber, N Trask, Y Hong, N Park
NeurIPS Workshop 2024
[Paper]

Neural Compression for Multispectral Satellite Images
W Cho*, S Immanuel*, J Heo, D Kwon
NeurIPS Workshop 2024
[Paper] [Code] [Project]

Promoting Sparsity In Continuous-Time Models To Learn Delayed Dependence Structures
F Wu, W Cho, D Korotky, S Hong, D Rim, N Park, K Lee
CIKM 2024
[Paper]

Parameterized Physics-informed Neural Networks for Solving Parameterized PDEs
W Cho, M Jo, H Lim, K Lee, D Lee, S Hong, N Park
ICML 2024 (Oral, Top 1.52%)
[Paper] [Code] [Presentation]

Extension of Physics-informed Neural Networks to Solving Parameterized PDEs
W Cho, M Jo, H Lim, K Lee, D Lee, S Hong, N Park
ICLR Workshop 2024
[Paper] [Code]

Learning Flexible Body Collision Dynamics with Hierarchical Contact Mesh Transformer
Y Yu, J Choi, W Cho, K Lee, N Kim, K Chang, C Woo, I Kim, S Lee, J Yang, S Yoon, N Park
ICLR 2024
[Paper] [Code]

Operator-learning-inspired Modeling of Neural Ordinary Differential Equations
W Cho*, S Cho*, H Jin, J Jeon, K Lee, S Hong, D Lee, J Choi, N Park
AAAI 2024
[Paper] [Code]

Hypernetwork-based Meta-Learning for Low-Rank Physics-Informed Neural Networks
W Cho, K Lee, D Rim, N Park
NeurIPS 2023 (Spotlight, Top 3.06%)
[Paper] [Code]

   


Education

  • Yonsei University (Aug. 2024)

    M.S in Artificial Intelligence

  • Yonsei University (Aug. 2022)

    B.S in Atmospheric science
    B.S in Electrical electronic engineering

  • Sejong Science High School (Feb. 2017)

Career

  • Telepix ( Jun. 2024 - Present )

    AI research team (Alternative military service)

  • Arizona State University ( Jan. 2024 - Jun. 2024 )

    Visiting Researcher (hosted by Prof.Kookjin Lee)


Academic Activities

Conference Reviewer

  • Conference on Neural Information Processing Systems (NeurIPS)
  • International Conference on Machine Learning (ICML)
  • International Conference on Learning Representations (ICLR)

ESA-NASA International Workshop on AI Foundation Model for Earth Observation

  • A Unified Framework for Multi-resolution and Multi-spectral Satellite Imagery in Foundation Model Training (First author)
  • Multi-modal Foundation Model for EO and SAR Images (First author)

Invited Talk

  • AI for Science: Physics-informed Machine Learning and the Road to Scientific Foundation Models (hoted by ETRI)
  • AI for Computational Science and Space Exploration (hosted by Postech, EFFL)
  • Scientific Machine Learning (hosted by KIAS)
  • Parameterized Physics-informed Neural Networks for Parameterized PDEs (hosted by ML2)
  • Latest Trends in Machine Learning based Physics Simulation (hosted by Samsung Electronics)
  • Physics-informed Neural Networks for Solving PDEs (hosted by Alsemy)

Scholarship