5 papers
Dataset Complexity Shapes Finite-Distance Loss Geometry in Neural Networks
Jaeyong Bae, Hawoong Jeong
Finite datasets can share the same size and low-order statistics while differing strongly in structural complexity. We connect this dataset complexity to loss-landscape geometry by…
Uncovering Spontaneous Physics Representations in In-Context Learning
Yeongwoo Song, Jaeyong Bae, Dong-Kyum Kim +1
In-context learning (ICL) lets large language models (LLMs) solve new tasks from prompts alone, across an ever-widening range of domains, yet the mechanisms underlying this ability…
Exploring how deep learning decodes anomalous diffusion via Grad-CAM
Jaeyong Bae, Yongjoo Baek, Hawoong Jeong
While deep learning has been successfully applied to the data-driven classification of anomalous diffusion mechanisms, how the algorithm achieves the feat still remains a mystery.…
Gaussian Universality in Neural Network Dynamics with Generalized Structured Input Distributions
Jaeyong Bae, Hawoong Jeong
Analyzing neural network dynamics via stochastic gradient descent (SGD) is crucial to building theoretical foundations for deep learning. Previous work has analyzed structured inpu…
Quantitative evaluation of methods to analyze motion changes in single-particle experiments
Gorka Muñoz-Gil, Harshith Bachimanchi, Jesús Pineda +33
The analysis of live-cell single-molecule imaging experiments can reveal valuable information about the heterogeneity of transport processes and interactions between cell component…