arXiv subjects

Sunho Park

Publications and source records attributed to Sunho Park.

5 recordsLinked to original sources

arXiv2025

Exploring OCR-augmented Generation for Bilingual VQA

We investigate OCR-augmented generation with Vision Language Models (VLMs), exploring tasks in Korean and English toward multilingualism. To support research in this domain, we train and release KLOCR, a strong bilingual OCR baseline trained on 100M instances to augment VLMs with OCR ability. To complement existing VQA benchmarks, we curate KOCRBench for Korean VQA, and analyze different prompting methods. Extensive experiments show that OCR-extracted text significantly boosts performance across open source and commercial models. Our work offers new insights into OCR-augmented generation for bilingual VQA. Model, code, and data are available at https://github.com/JHLee0513/KLOCR.

cs.CV↗

arXiv2018

Ultra-Reliable and Low-Latency Communications in 5G Downlink: Physical Layer Aspects

Ultra reliable and low latency communications (URLLC) is a new service category in 5G to accommodate emerging services and applications having stringent latency and reliability requirements. In order to support URLLC, there should be both evolutionary and revolutionary changes in the air interface named 5G new radio (NR). In this article, we provide an up-to-date overview of URLLC with an emphasis on the physical layer challenges and solutions in 5G NR downlink. We highlight key requirements of URLLC and then elaborate the physical layer issues and enabling technologies including packet and frame structure, scheduling schemes, and reliability improvement techniques, which have been discussed in the 3GPP Release 15 standardization.

cs.IT↗

arXiv2018

Sparse Vector Coding for Ultra-Reliable and Low Latency Communications

Ultra reliable and low latency communication (URLLC) is a newly introduced service category in 5G to support delay-sensitive applications. In order to support this new service category, 3rd Generation Partnership Project (3GPP) sets an aggressive requirement that a packet should be delivered with 10^-5 packet error rate within 1 ms transmission period. Since the current wireless transmission scheme designed to maximize the coding gain by transmitting capacity achieving long codeblock is not relevant for this purpose, a new transmission scheme to support URLLC is required. In this paper, we propose a new approach to support the short packet transmission, called sparse vector coding (SVC). Key idea behind the proposed SVC technique is to transmit the information after the sparse vector transformation. By mapping the information into the position of nonzero elements and then transmitting it after the random spreading, we obtain an underdetermined sparse system for which the principle of compressed sensing can be applied. From the numerical evaluations and performance analysis, we demonstrate that the proposed SVC technique is very effective in URLLC transmission and outperforms the 4G LTE and LTE-Advanced scheme.

cs.IT↗

arXiv2017

Bayesian Semi-nonnegative Tri-matrix Factorization to Identify Pathways Associated with Cancer Types

Identifying altered pathways that are associated with specific cancer types can potentially bring a significant impact on cancer patient treatment. Accurate identification of such key altered pathways information can be used to develop novel therapeutic agents as well as to understand the molecular mechanisms of various types of cancers better. Tri-matrix factorization is an efficient tool to learn associations between two different entities (e.g., cancer types and pathways in our case) from data. To successfully apply tri-matrix factorization methods to biomedical problems, biological prior knowledge such as pathway databases or protein-protein interaction (PPI) networks, should be taken into account in the factorization model. However, it is not straightforward in the Bayesian setting even though Bayesian methods are more appealing than point estimate methods, such as a maximum likelihood or a maximum posterior method, in the sense that they calculate distributions over variables and are robust against overfitting. We propose a Bayesian (semi-)nonnegative matrix factorization model for human cancer genomic data, where the biological prior knowledge represented by a pathway database and a PPI network is taken into account in the factorization model through a finite dependent Beta-Bernoulli prior. We tested our method on The Cancer Genome Atlas (TCGA) dataset and found that the pathways identified by our method can be used as a prognostic biomarkers for patient subgroup identification.

stat.ML↗

arXiv2014

Convex Optimization for Binary Classifier Aggregation in Multiclass Problems

Multiclass problems are often decomposed into multiple binary problems that are solved by individual binary classifiers whose results are integrated into a final answer. Various methods, including all-pairs (APs), one-versus-all (OVA), and error correcting output code (ECOC), have been studied, to decompose multiclass problems into binary problems. However, little study has been made to optimally aggregate binary problems to determine a final answer to the multiclass problem. In this paper we present a convex optimization method for an optimal aggregation of binary classifiers to estimate class membership probabilities in multiclass problems. We model the class membership probability as a softmax function which takes a conic combination of discrepancies induced by individual binary classifiers, as an input. With this model, we formulate the regularized maximum likelihood estimation as a convex optimization problem, which is solved by the primal-dual interior point method. Connections of our method to large margin classifiers are presented, showing that the large margin formulation can be considered as a limiting case of our convex formulation. Numerical experiments on synthetic and real-world data sets demonstrate that our method outperforms existing aggregation methods as well as direct methods, in terms of the classification accuracy and the quality of class membership probability estimates.

cs.LG↗