arXiv subjects

Junghyo Jo

Publications and source records attributed to Junghyo Jo.

At least 19 recordsLinked to original sources

arXiv2026

How Does Science Education Research Respond to Sociopolitical Change? A BERTopic Analysis of Korean Research

Research fields do not evolve in isolation: their questions and priorities shift with policy, curriculum reform, and broader social change. Analyzing published literature can reveal not only how a field matures but also how it responds to these conditions. Prior work in science education has focused on identifying research topics and their trends, but paid less attention to the external conditions in which research is produced. We examine Korean science education research from 2008 to 2025, a case in which centralized curriculum revision, government education initiatives, and demographic decline are prominent. Using BERTopic, an embedding-based topic modeling technique, we identify major topics and temporal trends, and analyze their associations with selected sociopolitical factors. We interpret each topic and distinguish three groups: sociopolitical, subject-specific, and student-related topics. Within the first group, science teacher professionalism and curriculum implementation, science education for gifted students, and STEAM education show the strongest associations with sociopolitical conditions, such as government policy initiatives and declining enrollment in science-gifted education, whereas digital-based science education does not. The subject-specific and student-related groups, by contrast, show no comparable movement and are not linked to the external indicators we examine; this pattern is interpreted as reflecting stronger disciplinary grounding. Taken together, these patterns suggest that a topic's anchoring to policy and practice or to academic disciplines shapes how closely it tracks external change. This helps explain why some research agendas move with their national context while others hold steady, and why the same topic may develop differently across countries.

cs.CY↗

arXiv2026

Reinforcement Learning for Microcanonical Graph Ensemble with Assortativity Constraints

How network structure determines function is a fundamental question, and it can be investigated by graph ensembles with precisely controlled structural properties. Canonical approaches, formulated as exponential random graph models (ERGMs), enforce constraints only in expectation, allowing individual realizations to fluctuate around the target. Conversely, microcanonical ensembles impose hard constraints exactly, but practical sampling methods beyond fixing the degree sequence have remained out of reach. Here we introduce the Deep Microcanonical Graph Generator (DMGG), a reinforcement learning (RL) framework that transforms any given graph through degree-preserving rewirings to exactly reach a prescribed assortativity, which characterizes the degree--degree correlation of adjacent nodes. Instead of relying on the entropically dominated Metropolis--Hastings dynamics of the ERGM, DMGG employs a policy-guided search that maximally alters the joint-degree matrix. This eliminates exhaustive parameter tuning and accelerates generation by at least an order of magnitude while preserving configurational diversity. As DMGG generalizes across various graph sizes, sparsities, and topologies, it provides exact null models that allow for the quantitative isolation of secondary observables, such as the clustering coefficient. These results establish RL as a practical and powerful paradigm for generating hard-constrained graphs, opening avenues to investigate structure-function relationships free from ensemble artifacts.

cs.LG↗

arXiv2026

Variational Garrote for Sparse Inverse Problems

Sparse regularization plays a central role in solving inverse problems arising from incomplete or corrupted measurements. Different regularizers correspond to different prior assumptions about the structure of the unknown signal, and reconstruction performance depends on how well these priors match the intrinsic sparsity of the data. This work investigates the effect of sparsity priors in inverse problems by comparing conventional L1 regularization with the Variational Garrote (VG), a probabilistic method that approximates L0 sparsity through variational binary gating variables. A unified experimental framework is constructed across multiple reconstruction tasks including signal resampling, signal denoising, and sparse-view computed tomography. To enable consistent comparison across models with different parameterizations, regularization strength is swept across wide ranges and reconstruction behavior is analyzed through train-generalization error curves. Experiments reveal characteristic bias-variance tradeoff patterns across tasks and demonstrate that VG frequently achieves lower minimum generalization error and improved stability in strongly underdetermined regimes where accurate support recovery is critical. These results suggest that sparsity priors closer to spike-and-slab structure can provide advantages when the underlying coefficient distribution is strongly sparse. The study highlights the importance of prior-data alignment in sparse inverse problems and provides empirical insights into the behavior of variational L0-type methods across different information bottlenecks.

stat.ML↗

arXiv2025

Interplay of Fidelity and Diversity in the Evolution of the Genetic Code

The origin and organizing principles of the genetic code remain fundamental puzzles in life science. The vanishingly low probability of the natural codon-to-amino acid mapping arising by chance has spurred the hypothesis that its structure is a solution optimized for robustness against mutations and translational errors. For the construction of effective molecular machines, the dictionary of encoded amino acids must also be diverse enough in physicochemical features. Here, we examine whether the standard genetic code can be understood as a near-optimal solution balancing these two objectives: minimizing error load and aligning codon assignments with the naturally occurring amino acid composition. Using simulated annealing, we explore this trade-off across a broad range of parameters. We find that the standard genetic code lies near local optima within the multidimensional parameter space. It is a highly effective solution that balances fidelity against resource availability constraints. These results suggest that the present genetic code reflects coevolution under conflicting pressures of fidelity and diversity, offering new insight into its emergence and evolution.

q-bio.OT↗

arXiv2025

Stochastic Clock Attention for Aligning Continuous and Ordered Sequences

We formulate an attention mechanism for continuous and ordered sequences that explicitly functions as an alignment model, which serves as the core of many sequence-to-sequence tasks. Standard scaled dot-product attention relies on positional encodings and masks but does not enforce continuity or monotonicity, which are crucial for frame-synchronous targets. We propose learned nonnegative \emph{clocks} to source and target and model attention as the meeting probability of these clocks; a path-integral derivation yields a closed-form, Gaussian-like scoring rule with an intrinsic bias toward causal, smooth, near-diagonal alignments, without external positional regularizers. The framework supports two complementary regimes: normalized clocks for parallel decoding when a global length is available, and unnormalized clocks for autoregressive decoding -- both nearly-parameter-free, drop-in replacements. In a Transformer text-to-speech testbed, this construction produces more stable alignments and improved robustness to global time-scaling while matching or improving accuracy over scaled dot-product baselines. We hypothesize applicability to other continuous targets, including video and temporal signal modeling.

cs.LG↗

arXiv2025

Variational Garrote for Statistical Physics-based Sparse and Robust Variable Selection

Selecting key variables from high-dimensional data is increasingly important in the era of big data. Sparse regression serves as a powerful tool for this purpose by promoting model simplicity and explainability. In this work, we revisit a valuable yet underutilized method, the statistical physics-based Variational Garrote (VG), which introduces explicit feature selection spin variables and leverages variational inference to derive a tractable loss function. We enhance VG by incorporating modern automatic differentiation techniques, enabling scalable and efficient optimization. We evaluate VG on both fully controllable synthetic datasets and complex real-world datasets. Our results demonstrate that VG performs especially well in highly sparse regimes, offering more consistent and robust variable selection than Ridge and LASSO regression across varying levels of sparsity. We also uncover a sharp transition: as superfluous variables are admitted, generalization degrades abruptly and the uncertainty of the selection variables increases. This transition point provides a practical signal for estimating the correct number of relevant variables, an insight we successfully apply to identify key predictors in real-world data. We expect that VG offers strong potential for sparse modeling across a wide range of applications, including compressed sensing and model pruning in machine learning.

cs.LG↗

arXiv2025

Multiplicative learning from observation-prediction ratios

Additive parameter updates, as used in gradient descent and its adaptive extensions, underpin most modern machine-learning optimization. Yet, such additive schemes often demand numerous iterations and intricate learning-rate schedules to cope with scale and curvature of loss functions. Here we introduce Expectation Reflection (ER), a multiplicative learning paradigm that updates parameters based on the ratio of observed to predicted outputs, rather than their differences. ER eliminates the need for ad hoc loss functions or learning-rate tuning while maintaining internal consistency. Extending ER to multilayer networks, we demonstrate its efficacy in image classification, achieving optimal weight determination in a single iteration. We further show that ER can be interpreted as a modified gradient descent incorporating an inverse target-propagation mapping. Together, these results position ER as a fast and scalable alternative to conventional optimization methods for neural-network training.

cs.LG↗

arXiv2025

Data augmentation using diffusion models to enhance inverse Ising inference

Identifying model parameters from observed configurations poses a fundamental challenge in data science, especially with limited data. Recently, diffusion models have emerged as a novel paradigm in generative machine learning, capable of producing new samples that closely mimic observed data. These models learn the gradient of model probabilities, bypassing the need for cumbersome calculations of partition functions across all possible configurations. We explore whether diffusion models can enhance parameter inference by augmenting small datasets. Our findings demonstrate this potential through a synthetic task involving inverse Ising inference and a real-world application of reconstructing missing values in neural activity data. This study serves as a proof-of-concept for using diffusion models for data augmentation in physics-related problems, thereby opening new avenues in data science.

physics.data-an↗

arXiv2024

Neural Graph Simulator for Complex Systems

Numerical simulation is a predominant tool for studying the dynamics in complex systems, but large-scale simulations are often intractable due to computational limitations. Here, we introduce the Neural Graph Simulator (NGS) for simulating time-invariant autonomous systems on graphs. Utilizing a graph neural network, the NGS provides a unified framework to simulate diverse dynamical systems with varying topologies and sizes without constraints on evaluation times through its non-uniform time step and autoregressive approach. The NGS offers significant advantages over numerical solvers by not requiring prior knowledge of governing equations and effectively handling noisy or missing data with a robust training scheme. It demonstrates superior computational efficiency over conventional methods, improving performance by over $10^5$ times in stiff problems. Furthermore, it is applied to real traffic data, forecasting traffic flow with state-of-the-art accuracy. The versatility of the NGS extends beyond the presented cases, offering numerous potential avenues for enhancement.

cs.LG↗

arXiv2024

Annealing approach to root-finding

The Newton-Raphson method is a fundamental root-finding technique with numerous applications in physics. In this study, we propose a parameterized variant of the Newton-Raphson method, inspired by principles from physics. Through analytical and empirical validation, we demonstrate that this novel approach offers increased robustness and faster convergence during root-finding iterations. Furthermore, we establish connections to the Adomian series method and provide a natural interpretation within a series framework. Remarkably, the introduced parameter, akin to a temperature variable, enables an annealing approach. This advancement sets the stage for a fresh exploration of numerical iterative root-finding methodologies.

math.NA↗

arXiv2024

Geometric Remove-and-Retrain (GOAR): Coordinate-Invariant eXplainable AI Assessment

Identifying the relevant input features that have a critical influence on the output results is indispensable for the development of explainable artificial intelligence (XAI). Remove-and-Retrain (ROAR) is a widely accepted approach for assessing the importance of individual pixels by measuring changes in accuracy following their removal and subsequent retraining of the modified dataset. However, we uncover notable limitations in pixel-perturbation strategies. When viewed from a geometric perspective, we discover that these metrics fail to discriminate between differences among feature attribution methods, thereby compromising the reliability of the evaluation. To address this challenge, we introduce an alternative feature-perturbation approach named Geometric Remove-and-Retrain (GOAR). Through a series of experiments with both synthetic and real datasets, we substantiate that GOAR transcends the limitations of pixel-centric metrics.

cs.LG↗

arXiv2024

Direct Unlearning Optimization for Robust and Safe Text-to-Image Models

Recent advancements in text-to-image (T2I) models have unlocked a wide range of applications but also present significant risks, particularly in their potential to generate unsafe content. To mitigate this issue, researchers have developed unlearning techniques to remove the model's ability to generate potentially harmful content. However, these methods are easily bypassed by adversarial attacks, making them unreliable for ensuring the safety of generated images. In this paper, we propose Direct Unlearning Optimization (DUO), a novel framework for removing Not Safe For Work (NSFW) content from T2I models while preserving their performance on unrelated topics. DUO employs a preference optimization approach using curated paired image data, ensuring that the model learns to remove unsafe visual concepts while retaining unrelated features. Furthermore, we introduce an output-preserving regularization term to maintain the model's generative capabilities on safe content. Extensive experiments demonstrate that DUO can robustly defend against various state-of-the-art red teaming methods without significant performance degradation on unrelated topics, as measured by FID and CLIP scores. Our work contributes to the development of safer and more reliable T2I models, paving the way for their responsible deployment in both closed-source and open-source scenarios.

cs.CV↗

arXiv2024

Upsample Guidance: Scale Up Diffusion Models without Training

Diffusion models have demonstrated superior performance across various generative tasks including images, videos, and audio. However, they encounter difficulties in directly generating high-resolution samples. Previously proposed solutions to this issue involve modifying the architecture, further training, or partitioning the sampling process into multiple stages. These methods have the limitation of not being able to directly utilize pre-trained models as-is, requiring additional work. In this paper, we introduce upsample guidance, a technique that adapts pretrained diffusion model (e.g., $512^2$) to generate higher-resolution images (e.g., $1536^2$) by adding only a single term in the sampling process. Remarkably, this technique does not necessitate any additional training or relying on external models. We demonstrate that upsample guidance can be applied to various models, such as pixel-space, latent space, and video diffusion models. We also observed that the proper selection of guidance scale can improve image quality, fidelity, and prompt alignment.

cs.CV↗

arXiv2024

Broad cross-reactivity of the T-cell repertoire achieves specific and sufficiently rapid target searching

The molecular recognition of T-cell receptors is the hallmark of the adaptive immunity. Given the finiteness of the T-cell repertoire, individual T-cell receptors are necessary to be cross-reactive to multiple antigenic peptides. In this study, we quantify the variability of the cross-reactivity by using a string model that estimates the binding affinity between two sequences of amino acids. We examine sequences of 10,000 human T-cell receptors and 10,000 antigenic peptides, and obtain a full spectrum of cross-reactivity of the receptor-peptide binding. Then, we find that the cross-reactivity spectrum is broad. Some T cells are reactive to 1,000 peptides, but some T cells are reactive to only one or two peptides. Since the degree of cross-reactivity has a correlation with the (un)binding affinity of receptors, we further investigate how the broad crossreactivity affects the target searching of T cells. High cross-reactive T cells may not require many trials for searching correct targets, but they may spend long time to unbind from incorrect targets. In contrast, low cross-reactive T cells may not spend long time to ignore incorrect targets, but they require many trials for screening correct targets. We evaluate this hypothesis, and show that the broad cross-reactivity of the natural T-cell repertoire can balance the trade-off between the rapid screening and unbinding penalty.

q-bio.CB↗

arXiv2024

A Local Counter-Regulatory Motif Modulates the Global Phase of Hormonal Oscillations

Counter-regulatory elements maintain dynamic equilibrium ubiquitously in living systems. The most prominent example, which is critical to mammalian survival, is that of pancreatic α and β cells producing glucagon and insulin for glucose homeostasis. These cells are not found in a single gland but are dispersed in multiple micro-organs known as the islets of Langerhans. Within an islet, these two reciprocal cell types interact with each other and with an additional cell type: the δ cell. By testing all possible motifs governing the interactions of these three cell types, we found that a unique set of positive/negative intra-islet interactions between different islet cell types functions not only to reduce the superficially wasteful zero-sum action of glucagon and insulin but also to enhance/suppress the synchronization of hormone secretions between islets under high/normal glucose conditions. This anti-symmetric interaction motif confers effective controllability for network (de)synchronization.

q-bio.TO↗

arXiv2024

Local complexity predicts global synchronization of hierarchically networked oscillators

We study the global synchronization of hierarchically-organized Stuart-Landau oscillators, where each subsystem consists of three oscillators with activity-dependent couplings. We consider all possible coupling signs between the three oscillators, and find that they can generate different numbers of phase attractors depending on the network motif. Here, the subsystems are coupled through mean activities of total oscillators. Under weak inter-subsystem couplings, we demonstrate that the synchronization between subsystems is highly correlated with the number of attractors in uncoupled subsystems. Among the network motifs, perfect anti-symmetric ones are unique to generate both single and multiple attractors depending on the activities of oscillators. The flexible local complexity can make global synchronization controllable.

nlin.AO↗

arXiv2024

Immunological recognition by artificial neural networks

The binding affinity between the T-cell receptors (TCRs) and antigenic peptides mainly determines immunological recognition. It is not a trivial task that T cells identify the digital sequences of peptide amino acids by simply relying on the integrated binding affinity between TCRs and antigenic peptides. To address this problem, we examine whether the affinity-based discrimination of peptide sequences is learnable and generalizable by artificial neural networks (ANNs) that process the digital experimental amino acid sequence information of receptors and peptides. A pair of TCR and peptide sequences correspond to the input for ANNs, while the success or failure of the immunological recognition correspond to the output. The output is obtained by both theoretical model and experimental data. In either case, we confirmed that ANNs could learn the immunological recognition. We also found that a homogenized encoding of amino acid sequence was more effective for the supervised learning task.

q-bio.CB↗

arXiv2023

Resolution Chromatography of Diffusion Models

Diffusion models generate high-resolution images through iterative stochastic processes. In particular, the denoising method is one of the most popular approaches that predicts the noise in samples and denoises it at each time step. It has been commonly observed that the resolution of generated samples changes over time, starting off blurry and coarse, and becoming sharper and finer. In this paper, we introduce "resolution chromatography" that indicates the signal generation rate of each resolution, which is very helpful concept to mathematically explain this coarse-to-fine behavior in generation process, to understand the role of noise schedule, and to design time-dependent modulation. Using resolution chromatography, we determine which resolution level becomes dominant at a specific time step, and experimentally verify our theory with text-to-image diffusion models. We also propose some direct applications utilizing the concept: upscaling pre-trained models to higher resolutions and time-dependent prompt composing. Our theory not only enables a better understanding of numerous pre-existing techniques for manipulating image generation, but also suggests the potential for designing better noise schedules.

cs.CV↗