Curriculum Vitae

Korea Advanced Institute of Science and Technology (KAIST)

Brain and Cognitive Sciences

Thesis: Artificial intelligence models inspired by developmental neuroscience for improved efficiency, robustness, and reliability

Best Thesis Award

Korea Advanced Institute of Science and Technology (KAIST)

Bio and Brain Engineering

Magna Cum Laude, Excellence in Leadership and Volunteering

J. Cheon, S.-B. Paik.

Brain-inspired warm-up training with random noise for uncertainty calibration

Nature Machine Intelligence 8, 602–613 (2026)

* Featured in News & Views: T. Isomura, Learning to be uncertain before learning from data

J. Cheon, M. Vogelsang, L. Vogelsang, P. Sinha.

Spectral stratification of semantic abstraction in vision-language models

Advances in Neural Information Processing Systems 39 (NeurIPS 2026)

* Also presented in Mechanistic Interpretability Workshop @ ICML 2026

J. Cheon, M. Vogelsang, L. Vogelsang, P. Sinha.

Early visual experience scaffolds hierarchical visual representations

Advances in Neural Information Processing Systems 39 (NeurIPS 2026)

H. C. Nam*, J. Cheon*, J. M. Shin, H. Kwon (* Co-first).

Energy-based neural operator learning for function space

Advances in Neural Information Processing Systems 39 (NeurIPS 2026)

* Also presented in AI for Science Workshop @ ICML 2026

J. Cheon, J. Bae, S.-B. Paik.

One-time soft alignment enables resilient learning without weight transport

Advances in Neural Information Processing Systems 39 (NeurIPS 2026)

J. Cheon, S. W. Lee, S.-B. Paik.

Pretraining with random noise for fast and robust learning without weight transport

Advances in Neural Information Processing Systems 37, 13748–13768 (NeurIPS 2024)

J. Cheon*, S. Baek*, S.-B. Paik (* Co-first).

Invariance of object detection in untrained deep neural networks

Frontiers in Computational Neuroscience 16, 1030707 (2022)

C. Shin, J. Cheon, B. M. Lake.

Coarse-to-fine category structure in child's-view model representations

Developmental Perspectives on AI Workshop @ NeurIPS 2026

J. Cheon, M. Vogelsang, L. Vogelsang, P. Sinha.

Early visual degradation facilitates few-shot word learning from a child's egocentric input

Developmental Perspectives on AI Workshop @ NeurIPS 2026

J. Cheon, S.-B. Paik.

Gradual sensory maturation promotes abstract representation learning

bioRxiv Preprint 2025.06.24.661295 (2025)

• Developed a cognitive science-inspired LLM interpretability framework for agentic AI safety.
• Awarded KRW 15 million in research and development funding.

• Awarded KRW 18 million annually.
• 50 master’s students selected nationwide annually.

• Full tuition, awarded KRW 12 million annually.
• 137 undergraduate students selected nationwide annually.

J. Cheon, J. Bae, S.-B. Paik.

One-shot initial alignment guides resilient learning without weight transport

Society for Neuroscience (SfN), Nov 2025, San Diego, California, US.

J. Cheon, S.-B. Paik.

Uncertainty-calibrated network initialization via pretraining with random noise

Computational Neuroscience Meeting (CNS), July 2025, Florence, IT.

J. Cheon, S.-B. Paik.

Training with degraded data for debiased representation in neural networks

Vision Sciences Society (VSS), May 2025, St. Pete Beach, Florida, US.

J. Cheon, S.-B. Paik.

Uncertainty calibration through pretraining with random noise

Computational and Systems Neuroscience (COSYNE), Mar 2025, Montreal, Quebec, CA.

J. Cheon, S.-B. Paik.

Emergence of functional maps from neuronal interference in auditory cortex

Society for Neuroscience (SfN), Oct 2024, Chicago, Illinois, US.

J. Cheon, S. W. Lee, S.-B. Paik.

Random noise enables reliable learning without weight transport

CSHL Meeting “From Neuroscience to Artificially Intelligent Systems” (NAISys), Sep 2024, Cold Spring Harbor, New York, US.

J. Cheon, S.-B. Paik.

Spontaneous emergence of periodotopic map through neuronal interference in auditory cortex

Cognitive Computational Neuroscience (CCN), Aug 2024, Boston, Massachusetts, US.

S.-B. Paik, J. Cheon.

Method and apparatus for pretraining neural network based on random noise

KR Application 10-2025-0064473

S.-B. Paik, J. Cheon.

Method for pretraining with random noise for uncertainty calibration in deep neural networks

KR Application 10-2025-0099243

Reviewer

CCN 2024, NeurIPS 2025, 2026, Mechanistic Interpretability Workshop @ ICML 2026

Teaching Assistant

Theoretical Neuroscience (KAIST BCS503, 2025 Spring)

Multidisciplinary Capstone Design Class (KAIST CD401, 2022 Spring; CD402, 2021 Fall, 2022 Fall)