arXiv subjects

Juno Hwang

Publications and source records attributed to Juno Hwang.

5 recordsLinked to original sources

arXiv2026

Leveraging learning analytics to enhance immersive teacher simulations: Challenges and opportunities

This chapter examines how data analytics can be leveraged to enhance immersive teacher simulations, situating this inquiry within the broader learning sciences discourse on embodied cognition, data-informed feedback, and teacher professional learning. It explores both conceptual foundations and empirical cases to illustrate how analytics serve as mediational tools that connect immersive experiences with reflective teaching practice. The chapter unfolds in multiple sections: (1) The Innovation Journey: An Overview of Immersive Teacher Simulations outlines the evolution from traditional simulations to XR-based environments, highlighting the need for professional decision-making under realistic constraints. (2) Innovation in Existing Research and Practice situates teacher analytics within the trajectory from descriptive observation to multimodal and predictive modeling. (3) Study Approach and Design details how multimodal data-discourse, behavior, and gaze-from the TeacherGen@i simulation were collected and organized to reveal cognitive distribution of pedagogical discourse and interaction patterns. (4) Findings present the cognitive distribution of preservice teachers' pedagogical discourse and the sequential interaction patterns that emerge in exchange, illustrating how multimodal analytics make pedagogical reasoning processes visible within immersive simulations. (5) Understanding Innovative Practices in Teacher Education examines teaching analytics to enhance immersive teacher simulation based on the findings of the study. (6) Key Takeaways of the Innovation Journey identifies research challenges and design implications for scalable, analytics-enhanced teacher education. Together, these sections position immersive teacher simulations as a pivotal testbed for aligning learning analytics, professional learning, and next-generation immersive learning environment design.

cs.HC↗

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↗

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↗

arXiv2022

Mirror descent of Hopfield model

Mirror descent is an elegant optimization technique that leverages a dual space of parametric models to perform gradient descent. While originally developed for convex optimization, it has increasingly been applied in the field of machine learning. In this study, we propose a novel approach for utilizing mirror descent to initialize the parameters of neural networks. Specifically, we demonstrate that by using the Hopfield model as a prototype for neural networks, mirror descent can effectively train the model with significantly improved performance compared to traditional gradient descent methods that rely on random parameter initialization. Our findings highlight the potential of mirror descent as a promising initialization technique for enhancing the optimization of machine learning models.

cs.LG↗

arXiv2020

Tractable loss function and color image generation of multinary restricted Boltzmann machine

The restricted Boltzmann machine (RBM) is a representative generative model based on the concept of statistical mechanics. In spite of the strong merit of interpretability, unavailability of backpropagation makes it less competitive than other generative models. Here we derive differentiable loss functions for both binary and multinary RBMs. Then we demonstrate their learnability and performance by generating colored face images.

cs.CV↗