Sangyoon Bae

Sangyoon Bae

Scientific ML · Physics-Informed Architectures · Foundation Models for Dynamical Systems
Ph.D. Candidate · Interdisciplinary Program in Artificial Intelligence
Seoul National University
Email GitHub LinkedIn Scholar

I build physics-informed foundation models for scientific systems — embedding the structure of the data-generating process directly into architecture and training. My focus is scientific time-series: signals acquired indirectly and often unstructured, where physics-grounded inductive biases are what turn latent structure into a learning signal.

2 sole first-author papers (ICLR 2026, Communications Biology) · 2 sole first-author papers under review · 1 co-first-author paper (ICASSP 2024) · 6+ peer-reviewed publications · Models evaluated on datasets up to 49k+ subjects across neural, climate, and population-scale data

News
Publications
🔬
ICLR 20262026

Decoding Dynamic Visual Experience from Calcium Imaging via Cell-Pattern-Aware Pretraining

Bae, S., Azabou, M., Richards, B., Cha, J.
paper
🧠
Communications Biology (Early Access)2026

Learning brain dynamics across distinct scaling regimes reveals psychiatric signatures

Bae, S., Kwon, J., Cha, J., Yoo, S.
paper
🌈
arXiv Preprint2026

Pretraining Shapes Spectral Structure: Architecture- and Strategy-Conditional Prediction of OOD Robustness in Foundation Models

Bae, S., Ahmed, S. M., Yoo, S., Cha, J.
arXiv Preprint
🧩
arXiv Preprint2026

Neural Data Needs Semantic Tokenization: Behavioral Events as Boundaries of Session-Transferable Tokens

Bae, S., Cha, J.
arXiv Preprint
📈
arXiv Preprint2026

PIMSM: Physics-Informed Multi-Scale Mamba for Stable Neural Representations under Distribution Shift

Bae, S., Yoo, S., Cha, J.
arXiv Preprint
🔗
arXiv Preprint2026

Latent-Space Causal Discovery from Indirect Neuroimaging Observations

Bae, S., Oprescu, M., Park, D., Yoo, S., Cha, J.
arXiv Preprint
⚛
IEEE QCE 20252025

Resting-state fMRI Analysis using Quantum Time-series Transformer

Park, J., Bae, S., Seo, J., Chen, S., Tseng, H., Cha, J. & Yoo, S.
paper
🌊
NeurIPS 20232023

SwiFT: Swin 4D fMRI Transformer

Kim, P., Kwon, J., Joo, S., Bae, S., Lee, D., Jung, Y., ... & Moon, T.
paper
🔐
ICASSP 20242024

Quantum Privacy Aggregation of Teacher Ensembles (QPATE) for Privacy-preserving Quantum Machine Learning

Watkins, W., Wang, H., Bae, S., Tseng, H. H., Cha, J., Chen, S. Y. C., & Yoo, S.
paper
🖼
arXiv Preprint2024

Macro2Micro: Cross-modal Magnetic Resonance Imaging Synthesis Leveraging Multi-scale Brain Structures

Kim, S., Kwon, J., Kwon, J., Bae, S., Lin, Y., Yoo, S., & Cha, J.
arXiv Preprint
📡
IBRO Neuroscience Reports 20232023

Resting-state theta phase-gamma amplitude coupling as a biomarker for the transdiagnostic dimensional approach in psychiatric disorders

Kim, M., Shim, Y., Kwon, J., Bae, S., … & Kwon, J. S.
paper
Selected Research
PIMSM

Physics-Informed Multi-Scale Mamba for Dynamical Systems

  • Formalizes temporal kernel mismatch as a failure mode under distribution shift; derives scale-specific SSM discretization from spectrum-estimated knee frequencies with A-scale regularization
  • HCP fMRI: highest representation stability (CKA 0.812) under temporal truncation; strongest low-resource accuracy at 1% supervision
  • Weather-5K: lowest variable-wise MAE across all horizons on held-out-station OOD forecasting (15.2% avg MAE reduction vs. best baseline)
CKA 0.812 on HCP · 15.2% MAE reduction on Weather-5K · ~1% labeled data
POYO-CAP

Curriculum Pretraining for Heterogeneous Scientific Data

  • Identified “scaling collapse” in SSL pretraining on heterogeneous scientific data: indiscriminate training degrades performance as noisy signals dominate the loss
  • Solution: use higher-order statistics (skewness/kurtosis) to identify statistically regular subsets; domain-informed curriculum — pretrain on predictable signals first, fine-tune on stochastic ones
  • Unlocks monotonic scaling and 1.98× data efficiency; validated on 200k+ calcium imaging recordings
SSIM +13% · 1.98× data efficiency · 200k+ sensor recordings · 4×V100
INCAMA

Physics-Aware Causal Discovery from Indirect Measurements

  • Recasts causal discovery from indirect neuroimaging as a conditional identifiability problem: physics-aware inversion (HRF deconvolution, EEG source localization) coupled with delay-aware Mamba-based latent causal discovery
  • Proved identifiability reduction with inversion-error propagation bound
  • 2–3× F1 improvement over baselines on TVB simulations; zero-shot transfer to HCP motor-task fMRI recovers canonical visuo-motor pathways with 4× higher recall
>3× improvement vs. DL baselines · zero-shot transfer (arXiv:2602.09034)
MBBN

Physics-Derived Multi-Band Attention for fMRI

  • Derives attention mechanism from the physics of scale-free power-law spectra: decomposes fMRI signals into domain-informed frequency bands, applies specialized self-attention per band
  • Physics-grounded pretraining loss (network communicability) anchors optimization
  • Trained at scale on 49,673 individuals; up to 41.36% AUROC improvement on psychiatric classification
AUROC +41% on ASD classification · 49k+ subjects (Communications Biology)
Work Experience
2026–27

Neurosoft Bioelectronics SA

Machine Learning Scientist Intern · October 2026 – January 2027
Remote (Republic of Korea) · Geneva, Switzerland
Developing neural foundation models and machine learning methods for brain–computer interfaces and large-scale neural recordings; contributing to NeuroAI research and software development for neural decoding applications.
Research Experience
2024

Mila — Quebec AI Institute, Montréal

Visiting Researcher · Foundation Models for Scientific Data
Advised by Prof. Blake Richards
Collaborated on scalable foundation models for scientific data. Developed the data-centric curriculum insight — statistical regularity as a pretraining criterion — that became the core contribution of POYO-CAP (ICLR 2026).
2023

Brookhaven National Laboratory

Visiting Researcher · Quantum Machine Learning Infrastructure
Advised by Dr. Shinjae Yoo
Applied privacy-preserving techniques to federated quantum learning settings; resulted in ICASSP 2024: “Quantum Privacy Aggregation of Teacher Ensembles (QPATE).”
2022

Institut de Neurosciences des Systèmes, Aix-Marseille Université

Visiting Researcher · Biophysical Simulator-Based Modeling
Advised by Prof. Viktor Jirsa
Adapted The Virtual Brain (TVB) biophysical simulation framework; experience with simulator-based forward models directly seeded the inverse-problem formulation of the INCAMA project.
2018

Laboratory of Neurobiology, Seoul National University

Undergraduate Intern · Advised by Prof. Bong-Kiun Kaang
Assisted neurobiology experiments investigating neural circuits in mouse models, including neurosurgical procedures (cranial window implantation) and brain tissue preparation for microscopy.
2017

Laboratory of Genes and Development, Seoul National University

Undergraduate Intern · Advised by Prof. Junho Lee
Forward genetic screening in Caenorhabditis elegans to identify genes regulating dauer developmental pathways.
Education

Ph.D. Candidate — Interdisciplinary Program in Artificial Intelligence

Seoul National University, Seoul, South Korea  ·  September 2021 – Present

B.S. — Biological Sciences

Student-Designed Minor: Computational Neuroscience for Human Behavior and Cognition
Seoul National University, Seoul, South Korea  ·  March 2015 – August 2021
Wet-lab training: neurosurgical procedures (cranial window implantation, brain tissue sectioning), forward genetic screening in C. elegans, PCR, Western blot.

Technical Skills
Scientific Computing
Python, NumPy, SciPy, Pandas
Machine Learning
PyTorch (expert), JAX/Flax (XLA compilation & JIT optimization), distributed & multi-GPU training, state-space models (Mamba/SSM), transformers, self-supervised & contrastive pretraining, foundation model training at scale, inverse problem solvers, physics-informed neural networks, causal discovery; agentic AI for accelerated experimentation and analysis
Scientific ML
Physics-informed neural networks, inverse problem theory, physics-aware inductive biases, state-space models (Mamba/SSM), multifractal signal analysis, biophysical forward models, causal discovery, dynamical systems
Data Modalities
Heterogeneous, indirectly observed measurements (temporal, spatial, population-scale); time-series and signal processing; multifractal and spectral analysis. Demonstrated domains: neuroimaging (fMRI, EEG, calcium imaging), climate time-series (Weather-5K), large-scale population datasets (49k+ subjects, 200k+ recordings)
Systems
Multi-GPU training (8× RTX 3090, 4× H100), HPC clusters, CUDA; biophysical simulators (TVB)
Research Grants, Scholarships & Awards
Mentoring

Mentored 8 undergraduates, master’s students, and high-schoolers across neuroscience and AI. Led weekly reading groups and code reviews; resulted in peer-reviewed publications.