Many organizations are increasingly relying on unstructured documents such as PDFs and scanned forms to support downstream large language model (LLM) services, including search, summarization, and recommendation. However, traditional OCR systems struggle with diverse layouts of documents, leading to frequent errors and high costs of labor. So, this study developed DATALUX - a robust document layout system that trans-forms unstructured documents into structured, machine-readable data suitable for automation. Built on a trans-former-based detector, DATALUX incorporates several modules for layout refinement, text-visual fusion, and layer-wise optimization to improve coherence and generalization across diverse layouts. Around January 2025, we successfully deployed DATALUX into one of the largest academic content service firms (Nurimedia) in South Korea. This firm faced the challenge of extracting metadata and references from thousands of academic pa-pers submitted in various formats. Also, the existing LLM-based tools provided unreliable results. So, they needed to process them manually, creating bottlenecks in both labor and time. However, DATALUX enabled the automatic structuring of over 100,000 research papers a year, improving extraction accuracy to over 97%, reducing costs by more than USD 185K annually, and accelerating processing speed by 8.7 times. These deployment results suggest that DATALUX enables scalable and efficient document automation in complex and high-volume environments successfully. We thus believe that our DATALUX has a significant impact on both academia and industry practices.

According to an industry survey, many people miss opportunities to apply for government subsidy programs because they do not know how to apply. People also need to search manually and check whether these programs are suitable for them. To address this issue, our study develops a new generative recommender system with both users’ information and government subsidy documents. Within our recommender system framework, we modify the existing Residual Quantization Variational Auto-Encoder (RQ-VAE) model to capture deep and abstract information from subsidy documents. Using semantic IDs generated for approximately 185,610 user click-stream histories and 240,000 documents, we train our recommender system to predict the semantic IDs of the next subsidy policy documents in which a user might be interested. In 2024, we successfully deploy our generative recommender system in Wello, a Korean Gov-Tech startup. In collaboration with the Korean government, our generative recommender system could save 7.8 million dollar, that might otherwise have gone unused due to a lack of applications. Also, Wello observed a 68% improvement in Click-Through Ratio (CTR), increasing from 41.4% in the third quarter of 2024 to 69.6% in the fourth quarter of 2024. We thus anticipate that our generative recommender system will have a significant impact on both individuals and the government.

The global automobile market experiences quick changes in design preferences. In response to the demand shifts, manufacturers now try to apply new technologies to bring a novel design to market faster. In this paper, we introduce a novel application that performs a similarity verification task of wheel designs using an AI model and cloud computing technology. At Jan 2022, we successfully implemented the application to the wheel design process of Hyundai Motor Company’s design team and shortened the similarity verification time by 90% to a maximum of 10 minutes. We believe that this study is the first to build a wheel image database and empirically prove that the cross-entropy loss does similar tasks as the pairwise losses do in the embedding space. As a result, we successfully automated Hyundai Motor’s verification task of wheel design similarity. With a few clicks, the end-users in Hyundai Motor could take advantage of our application.

We present a decision feedback equalizer (DFE) based on the proposed hybrid structure, which consists of the fast Kalman and LMS algorithm, to guarantee the fast convergence speed, computational complexity and numerical stability on the strong multipath channels. The LMS algorithm recommended by ATSC for HDTV does not guarantee TOV (threshold of visibility) on the strong multipath channels during the training period. Since the fast Kalman algorithm is not only numerically unstable but it also has high computational complexity, we proposed a hybrid structure to solve both of these problems. The fast Kalman algorithm is applied during the training sequence for the fast convergence, and then LMS algorithm is used to reduce the computational complexity and avoid the instability problem for the payload data part. The simulation results demonstrate that our hybrid structure is numerically stable with fast convergence speed and it overcomes the strong multipath channel.