arXiv subjects

Yonghyun Park

Publications and source records attributed to Yonghyun Park.

3 recordsLinked to original sources

arXiv2026

Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution

While diffusion models excel at image generation, their growing adoption raises critical concerns about copyright issues and model transparency. Existing attribution methods identify training examples influencing an entire image, but fall short in isolating contributions to specific elements, such as styles or objects, that are of primary concern to stakeholders. To address this gap, we introduce concept-level attribution through a novel method called Concept-TRAK, which extends influence functions with a key innovation: specialized training and utility loss functions designed to isolate concept-specific influences rather than overall reconstruction quality. We evaluate Concept-TRAK on novel concept attribution benchmarks using Synthetic and CelebA-HQ datasets, as well as the established AbC benchmark, showing substantial improvements over prior methods in concept-level attribution scenarios. We further demonstrate its versatility on real-world text-to-image generation with compositional and multi-concept prompts.

cs.CV↗

arXiv2022

MonaCoBERT: Monotonic attention based ConvBERT for Knowledge Tracing

Knowledge tracing (KT) is a field of study that predicts the future performance of students based on prior performance datasets collected from educational applications such as intelligent tutoring systems, learning management systems, and online courses. Some previous studies on KT have concentrated only on the interpretability of the model, whereas others have focused on enhancing the performance. Models that consider both interpretability and the performance improvement have been insufficient. Moreover, models that focus on performance improvements have not shown an overwhelming performance compared with existing models. In this study, we propose MonaCoBERT, which achieves the best performance on most benchmark datasets and has significant interpretability. MonaCoBERT uses a BERT-based architecture with monotonic convolutional multihead attention, which reflects forgetting behavior of the students and increases the representation power of the model. We can also increase the performance and interpretability using a classical test-theory-based (CTT-based) embedding strategy that considers the difficulty of the question. To determine why MonaCoBERT achieved the best performance and interpret the results quantitatively, we conducted ablation studies and additional analyses using Grad-CAM, UMAP, and various visualization techniques. The analysis results demonstrate that both attention components complement one another and that CTT-based embedding represents information on both global and local difficulties. We also demonstrate that our model represents the relationship between concepts.

cs.CY↗

arXiv2021

A Sensor Fusion-based Cutting Device Attitude Control to Improve the Accuracy of Korean Cabbage Harvesting

Korean cabbage harvesting lacks mechanization and depends on human power; thus, conducting research on Korean cabbage harvesters is of immense importance. Although these harvesters have been developed in various forms, they have not yet attained commercialization. Most Korean cabbage fields have slopes; thus there are several challenges, that can prevent accurate harvesting. Therefore, to address these challenges at the site, we adopt two cylinders in this study, develop a mechanism that enables attitude control of the cutting device, not driving platform body, to cope with slopes. By maintaining the level, angle, height of cutting, we can reduce loss and improve harvest performance. It is difficult to find examples where these mechanisms have been applied. For basic research, sensor fusion has been carried out based on the Kalman filter, which is commonly utilized for attitude control. The hydraulic cylinder was controlled using the data obtained for maintaining the attitude. Furthermore, field tests were conducted to validate this system, and the root mean square error (RMSE) was obtained and verified to quantitatively assess the presence or absence of attitude control. Therefore, the purpose of this study is to suggest a development direction for Korean cabbage harvesters via the proposed attitude control system.

eess.SY↗