cv

Ph.D. Candidate

Department of Physics, Harvard University

Machine Learning for the Physical Sciences

• Advisors: Aravinthan Samuel, Hidenori Tanaka, Douglas Finkbeiner, Cecilia Garraffo
• GPA: 3.945/4.0

Graduate Coursework

Department of Physics, Seoul National University

Physics

Exchange Student

Ecole Polytechnique

Physics, Computer Science

Bachelor of Science

Department of Physics, Korea Advanced Institute of Science and Technology

Major in Physics, Self-Designed Minor

• Summa Cum Laude, GPA: 4.08/4.3
• Advisors: Jonghee Yoo, Hawoong Jeong
• Focus: Astro-Particle Physics, Computational Physics
• Thesis: "Real time DAQ setup and dead-time measurement for CAPP 18T Dark Matter Axion search and its first results"

Understanding In-Context Representation Learning

• Emergence
• Compositional Generalization
• Diffusion Models
• Collaborators: Andrew Lee, Ekdeep Singh Lubana, Yongyi Yang, Kento Nishi, Maya Okawa, Martin Wattenberg, Hidenori Tanaka

Understanding Algorithmic Phases of In-Context Learning

• In-Context Learning
• Transformer Mechanisms
• Phase Transition
• Collaborators: Ekdeep Singh Lubana, Hidenori Tanaka

Understanding Emergence of Compositional Capabilities in Deep Learning

• Emergence
• Compositional Generalization
• Diffusion Models
• Collaborators: Maya Okawa, Ekdeep Singh Lubana, Andrew Lee, Yongyi Yang, Hidenori Tanaka

Emulating the Structure of the Universe using Diffusion Models

• Large Scale Structure Emulation
• Probabilistic Debiasing
• Probabilistic Completion
• Collaborators: Carolina Cuesta-Lazaro, Victoria Ono, Yueying Ni, Nayantara Mudur, Francisco Villaescusa-Navarro, Douglas Finkbeiner

Hyperspectral Machine Learning for Tackling Climate Change

• MethaneSAT Cloud Detection
• MethaneSAT Shadow Correction
• Collaborators: Cecilia Garraffo, Maya Nasr, Douglas Finkbeiner, Steven Wofsy

Machine Learning Driven Accelerated Connectomics

• SmartEM: Real Time ML driven Electron Microscopy Acquisition
• VAE EM Compressor
• Collaborators: Yaron Meirovitch, Ishaan Chandok, Aravinthan Samuel, Jeff Lichtman

Whole Brain Imaging

• Neural Imaging of C.elegans Thermotaxis
• Neural Imaging of C.elegans Mating Behavior
• Collaborators: Vladislav Susoy, Helena Casademunt, Aravinthan Samuel

Astro-statistics

• Quantifying the validity of high–dimensional statistics
• Estimating correlations of Large Scale structure and galactic dustmaps:
• Fourier space sparse Wavelet Scattering Transform on the GPU
• Collaborators: Nayantara Mudur, Douglas Finkbeiner, Erwan Allys, Francisco Villaescusa-Navarro

3D Tracking for Confocal Microscopy data

• Tracking neurons in a moving and deforming brain
• Human Interfacing Deep Learning
• Automatic Synthetic Data Generation
• Collaborators: Sahand Rahi, Mahsa Barzegar-Keshteli, Vladislav Susoy, Aravinthan Samuel

Axion Dark Matter Search

• Real-time DAQ system for the CAPP18T Axion Dark Matter Experiment
• Collaborators: Kangheun Kim, Jonghee Yoo

Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Space

[C.F. Park], [M. Okawa], A. Lee, E.S. Lubana, H. Tanaka

NeurIPS 2024 Spotlight

Algorithmic Phases of In-Context Learning

[C.F. Park], E.S. Lubana, H. Tanaka

Under Review

In-Context Learning of Representations

[C.F. Park], [A. Lee], [E.S. Lubana], Y. Yang, M. Okawa, K. Nishi, M. Wattenberg, H. Tanaka

Under Review

Dynamics of Concept Learning and Compositional Generalization

[Y. Yang], C.F. Park, E.S. Lubana, M. Okawa, W. Hu, H. Tanaka

Under Review

Structured In-Context Task Representations

[C.F. Park], [A. Lee], [E.S. Lubana], K. Nishi, M. Okawa, H. Tanaka

Under Review

Understanding the Transient Nature of In-Context Learning: The Window of Generalization

[C.F. Park], E.S. Lubana, H. Tanaka

NeurIPS 2024 Workshop on Scientific Methods for Understanding Deep Learning

Debiasing with Diffusion: Probabilistic reconstruction of Dark Matter fields from galaxies with CAMELS

[V. Ono], C.F. Park, N. Mudur, Y. Ni, C. Cuesta-Lazaro, F. Villaescusa-Navarro

The Astrophysical Journal

3D Reconstruction of Dark Matter Fields with Diffusion Models: Towards Application to Galaxy Surveys

[C.F. Park], N. Mudur, C. Cuesta-Lazaro, Y. Ni, V. Ono, D.P. Finkbeiner

ICML 2024 Workshop: AI for Science,

Hidden Learning Dynamics: Capability Emerges Before Behavior in Compositional Generalization

[C.F. Park], M. Okawa, A. Lee, E.S. Lubana, H. Tanaka

ICML 2024 Workshop on High-dimensional Learning Dynamics

EM-Compressor: Electron Microscopy Image Compression in Connectomics with Variational Autoencoders

[Y. Li], C.F. Park, D. Xenes, C. Bishop, D.R. Berger, A.D.T. Samuel, B. Wester, J.W. Lichtman, H. Pfister, W. Li, Y. Meirovitch

preprint

Automated neuron tracking inside moving and deforming C. elegans using deep learning and targeted augmentation

[C.F. Park], [M.B. Keshteli], K. Korchagina, A. Delrocq, V. Susoy, C.L. Jones, A.D.T. Samuel, S.J. Rahi

Nature Methods

Hyperspectral shadow removal with iterative logistic regression and latent Parametric Linear Combination of Gaussians

[C.F. Park], M. Nasr, M. Pérez-Carrasco, E. Walker, D. Finkbeiner, C. Garraffo

NeurIPS 2023 Workshop on Tackling Climate Change with Machine Learning

Probabilistic reconstruction of Dark Matter fields from biased tracers using diffusion models

[C.F. Park], [V. Ono], C. Cuesta-Lazaro, Y. Ni, N. Mudur

NeurIPS 2023 Workshop on Machine Learning and the Physical Sciences

SmartEM: machine-learning guided electron microscopy

[Y. Meirovitch], [C.F. Park], [L. Mi], [P. Potocek], S. Sawmya, Y. Li, Y. Wu, R. Schalek, H. Pfister, R. Schoenmakers, M. Peemen, J.W. Lichtman, A.D.T. Samuel, N. Shavit

bioarxiv

mEMbrain: an interactive deep learning MATLAB tool for connectomic segmentation on commodity desktops

[E.C. Pavarino], [E. Yang], N. Dhanyasi, M. Wang, F. Bidel, X. Lu, F. Yang, C.F. Park, M.B. Renuka, B. Drescher, A.D.T. Samuel, B. Hochner, P.S. Katz, M. Zhen, J.W. Lichtman, Y. Meirovitch

Frontiers in Neural Circuits

Stellar Reddening Based Extinction Maps for Cosmological Applications

[N. Mudur], C.F. Park, D.P. Finkbeiner

The Astrophysical Journal

Quantification of high dimensional non–Gaussianities and its implication to Fisher analysis in cosmology

[C.F. Park], E. Allys, F. Villaescusa-Navarro, D.P. Finkbeiner

The Astrophysical Journal

Revisiting Latent-Space Interpolation via a Quantitative Evaluation Framework

[L. Mi], [T. He], C.F. Park, H. Wang, Y. Wang, N. Shavit

arxiv

Natural sensory context drives diverse brain-wide activity during C. elegans mating

[V. Susoy], W. Hung, D. Witvliet, J.E. Whitener, M. Wu, C.F. Park, B.J. Graham, M. Zhen, V. Venkatachalam, A.D.T. Samuel

Cell

Real time DAQ setup and dead-time measurement for CAPP 18T Dark Matter Axion Search and its first results

[C.F. Park]

B.S. Thesis

Emergence of In-Context Learning Beyond Bayesian retrieval: A mechanistic study

New England Mechanistic Interpretability Workshop 2024

Poster

3D Reconstruction of Dark Matter Fields with Diffusion Models: Towards Application to Galaxy Surveys

ICML 2024 Workshop AI for Science, Vienna

Poster

Hidden Learning Dynamics of Capability before Behavior in Diffusion Models

ICML 2024 Workshop on High-Dimensional Learning Dynamics, Vienna

Poster

Scaling and In-Context Learning of Large Language Models

NTT Physics & Informatics Laboratory Journal Club

Slides

Probabilistic Completion of Astrophysical Fields for Robust Statistics with Diffusion Models

EAS 2024, Padova

Slides

3D probabilistic reconstruction of the local dark matter from galaxies

Astro AI Workshop 2024, Center for Astrophysics

Slides

Debiasing with Diffusion: Probabilistic reconstruction of Dark Matter fields from galaxies

ITC Lucheon, Center for Astrophysics

Slides

Reconstruction of the local dark matter using diffusion models

Workshop on AI-driven Discovery in Physics and Astrophysics at Kavli IPMU

Slides

Hyperspectral shadow removal with iterative logistic regression and latent Parametric Linear Combination of Gaussians

NeurIPS 2023 Workshop on Tackling Climate Change with Machine Learning

Poster

Paper

Probabilistic reconstruction of Dark Matter fields from galaxies using diffusion models

NeurIPS 2023 Workshop on Machine Learning and the Physical Sciences

Poster

Paper

Diffusion Models for Cosmology

AstroAI Lunch Talk, Center for Astrophysics

Slides

How is AI used in the Physical Sciences?

Hansung Science High School Mentoring Talk at Harvard University

Slides

Mstar2Mcdm using Diffusion Models: Generating Cold Dark Matter density fields conditioned on stellar mass fields using Denoising Diffusion Probabilistic Models

Camels Virtual Telecoms hosted by the Flatiron Institute

Slides

SmartEM: Faster Connectomics Using Deep Error Prediction Based Rescanning

ICML 2023 Workshop for Computational Biology

Poster

Paper

Freely Moving Whole Brain Imaging of C. elegans under a thermal stimulus

International C.elegans conference 2023

Poster

Automated neuron tracking inside moving and deforming animals using deep learning and targeted augmentation

COSYNE 2023

Automated neuron tracking using deep learning and targeted augmentation allows fast collection of C. elegans whole brain calcium activity during behavior

American Physical Society March Meeting 2023

On the Gaussianity of Non-Gaussian probes of Large Scale Structure

American Astronomical Society 240

Slides

From sensing to behavior, biological information processing in C. elegans

Citadel Ph.D. Summit 2022

Poster

Dark Matter Axion Search Experiment using 18T HTS Magnet

Stockholm International Youth Science Seminar 2018

Data acquisition system for dark matter Axion search experiment using 18 T HTS magnet at CAPP/IBS

Korean Physical Society Meeting 2018

ICLR 2024 Workshop on Tackling Climate Change with Machine Learning

Purcell Fellowship

Harvard University

Doctoral Study Abroad Scholarship

Korea Foundation for Advanced Studies

Physics Department Honorary Scholarship

KAIST

Undergraduate Student Scholarship

Korea Foundation for Advanced Studies

Korea Presidential Science Scholarship

KOSAF

Full Tuition Scholarship

Korea Foundation for Advanced Studies

2nd Place in Citadel Datathon

Citadel Securities and Correlation One

Project: Enhancing analysis and prediction of A/B tests with Bayesian posteriors of the click probability.

Report

Best Project Award at the 10th KIAS CAC Summer school on Scientific Computing & Artificial Intelligence

Korea Institute for Advanced Study

Project: Machine learning for text style analysis and audio composition.

Summa Cum Laude

Korea Advanced Institute of Science and Technology

Best Project Award, KIAS-SNU Physics Winter Camp

Korea Institute for Advanced Study

Project: Can gravitationally biased QCD dipoles explain the early growth of supermassive black holes?

KAIST Physics Dean’s List

Korea Advanced Institute of Science and Technology

Best Buddy Award

KAIST International Office

Best contribution to the buddy program, helping the acclimatization of international students to Korean culture and university life.

Dean’s List

Korea Advanced Institute of Science and Technology

Dean’s List

Korea Advanced Institute of Science and Technology

KITP Neurophysics of Locomotion School

Summer Student

Project: Optogenetic control of haltere motion during flight in Drosophila.

APCTP-POSTECH Biophysics School

Summer Student

KIAS-SNU Physics Winter Camp

Summer Student

Stockholm International Youth Science Seminar

Representative of South Korea

Presentation: Real time DAQ system for Axion Dark Matter Search.

APCTP-NIMS-KISTI-KASI Summer School on Numerical Relativity

Summer Student

APCTP-POSTECH Biophysics School

Summer Student

KAIST International Discovery Program

Team Leader

Proposal: Visit to TUM's astrophysics and particle physics laboratory.

Asian Science Camp

Representative of South Korea

Molecular Frontiers Symposium

School Representative

Physics as a Foundation for Science and Engineering

Teaching Fellow at Harvard University

Physics of Sensory systems

Teaching Fellow at Harvard University

Physics Lab I

Teaching Assistant / Lab Instructor at Seoul National University

General Physics 2

Tutor at KAIST

General Physics 1

Tutor at KAIST

General Physics 1

Tutor at KAIST

General Physics 2

Tutor at KAIST

General Physics 1

Tutor at KAIST