Nguyen H. Tran
YOU?
Author Swipe
View article: Microsecond Federated SVD on Grassmann Manifold for Real-time IoT Intrusion Detection
Microsecond Federated SVD on Grassmann Manifold for Real-time IoT Intrusion Detection Open
This paper introduces FedSVD, a novel unsupervised federated learning framework for real-time anomaly detection in IoT networks. By leveraging Singular Value Decomposition (SVD) and optimization on the Grassmann manifolds, FedSVD enables a…
View article: Nash Policy Gradient: A Policy Gradient Method with Iteratively Refined Regularization for Finding Nash Equilibria
Nash Policy Gradient: A Policy Gradient Method with Iteratively Refined Regularization for Finding Nash Equilibria Open
Finding Nash equilibria in imperfect-information games remains a central challenge in multi-agent reinforcement learning. While regularization-based methods have recently achieved last-iteration convergence to a regularized equilibrium, th…
View article: Targeted Therapy Improves Real-World Survival in Patients with Molecularly Matched Advanced Biliary Tract Cancer
Targeted Therapy Improves Real-World Survival in Patients with Molecularly Matched Advanced Biliary Tract Cancer Open
Molecular profiling reveals that up to 40% of advanced biliary tract cancers (BTCs) harbor actionable genomic alterations amenable to matched targeted therapies. However, conventional trial designs typically evaluate these agents in pretre…
View article: Influence of university service quality on student experiences, academic performance and institutional loyalty: A case study in Vietnam
Influence of university service quality on student experiences, academic performance and institutional loyalty: A case study in Vietnam Open
In an increasingly competitive global higher education landscape, universities are progressively adopting student-centered marketing and management strategies to attract and retain learners. This study investigates the impact of service qu…
View article: First-line atezolizumab/bevacizumab or durvalumab/tremelimumab in advanced hepatocellular carcinoma: a real world, multicenter retrospective study
First-line atezolizumab/bevacizumab or durvalumab/tremelimumab in advanced hepatocellular carcinoma: a real world, multicenter retrospective study Open
Background Unresectable hepatocellular carcinoma (uHCC) is a leading cause of cancer death. FDA-approved first-line systemic therapies include atezolizumab/bevacizumab (atezo/bev) and durvalumab/tremelimumab (durva/treme); however, there i…
View article: InterKey: Cross-modal Intersection Keypoints for Global Localization on OpenStreetMap
InterKey: Cross-modal Intersection Keypoints for Global Localization on OpenStreetMap Open
Reliable global localization is critical for autonomous vehicles, especially in environments where GNSS is degraded or unavailable, such as urban canyons and tunnels. Although high-definition (HD) maps provide accurate priors, the cost of …
View article: Circulating Tumor DNA and Tissue Testing for Pancreatobiliary Tumors
Circulating Tumor DNA and Tissue Testing for Pancreatobiliary Tumors Open
Importance The prognosis of advanced pancreaticobiliary tumors is poor. Next-generation sequencing (NGS) of tissue samples is utilized to identify actionable alterations, but there are occasional limitations due to inadequate tissue acquis…
View article: Convergence Analysis of Aggregation-Broadcast in LoRA-enabled Distributed Fine-Tuning
Convergence Analysis of Aggregation-Broadcast in LoRA-enabled Distributed Fine-Tuning Open
Federated Learning (FL) enables collaborative model training across decentralized data sources while preserving data privacy. However, the growing size of Machine Learning (ML) models poses communication and computation challenges in FL. L…
View article: Stereotactic body radiation therapy in oligometastatic pancreatic cancer: overall survival improvement and SMAD4 as a predictor of progression-free survival
Stereotactic body radiation therapy in oligometastatic pancreatic cancer: overall survival improvement and SMAD4 as a predictor of progression-free survival Open
SBRT plus chemotherapy may have benefits in some patients with oPC. SBRT to primary pancreas lesion led to better OS compared with SBRT to other metastatic sites. SMAD4 alteration in ctDNA testing correlated with higher PFS in oPC p…
View article: Managing hepatocellular carcinoma recurrence after liver transplantation: emerging role of immune checkpoint inhibitors
Managing hepatocellular carcinoma recurrence after liver transplantation: emerging role of immune checkpoint inhibitors Open
View article: Knowledge Abstraction for Knowledge-based Semantic Communication: A Generative Causality Invariant Approach
Knowledge Abstraction for Knowledge-based Semantic Communication: A Generative Causality Invariant Approach Open
In this study, we design a low-complexity and generalized AI model that can capture common knowledge to improve data reconstruction of the channel decoder for semantic communication. Specifically, we propose a generative adversarial networ…
View article: 31. PHÂN TÍCH CÁC MỐI LIÊN QUAN ĐẾN CHỈ ĐỊNH KẾT HỢP Y HỌC CỔ TRUYỀN VÀ Y HỌC HIỆN ĐẠI TRONG ĐIỀU TRỊ RỐI LOẠN GIẤC NGỦ TẠI BỆNH VIỆN ĐẠI HỌC Y DƯỢC THÀNH PHỐ HỒ CHÍ MINH - CƠ SỞ 3 VÀ BỆNH VIỆN Y HỌC CỔ TRUYỀN THÀNH PHỐ HỒ CHÍ MINH
31. PHÂN TÍCH CÁC MỐI LIÊN QUAN ĐẾN CHỈ ĐỊNH KẾT HỢP Y HỌC CỔ TRUYỀN VÀ Y HỌC HIỆN ĐẠI TRONG ĐIỀU TRỊ RỐI LOẠN GIẤC NGỦ TẠI BỆNH VIỆN ĐẠI HỌC Y DƯỢC THÀNH PHỐ HỒ CHÍ MINH - CƠ SỞ 3 VÀ BỆNH VIỆN Y HỌC CỔ TRUYỀN THÀNH PHỐ HỒ CHÍ MINH Open
Mục tiêu: Phân tích các mối liên quan đến chỉ định kết hợp phương pháp y học cổ truyền và y học hiện đại trong điều trị rối loạn giấc ngủ trên lâm sàng. Đối tượng và phương pháp: Nghiên cứu cắt ngang mô tả được thực hiện trên 902 hồ sơ bện…
View article: Distributionally Robust Wireless Semantic Communication with Large AI Models
Distributionally Robust Wireless Semantic Communication with Large AI Models Open
Semantic communication (SemCom) has emerged as a promising paradigm for 6G wireless systems by transmitting task-relevant information rather than raw bits, yet existing approaches remain vulnerable to dual sources of uncertainty: semantic …
View article: OccCylindrical: Multi-Modal Fusion with Cylindrical Representation for 3D Semantic Occupancy Prediction
OccCylindrical: Multi-Modal Fusion with Cylindrical Representation for 3D Semantic Occupancy Prediction Open
The safe operation of autonomous vehicles (AVs) is highly dependent on their understanding of the surroundings. For this, the task of 3D semantic occupancy prediction divides the space around the sensors into voxels, and labels each voxel …
View article: Interactive Medical Image Analysis with Concept-based Similarity Reasoning
Interactive Medical Image Analysis with Concept-based Similarity Reasoning Open
The ability to interpret and intervene model decisions is important for the adoption of computer-aided diagnosis methods in clinical workflows. Recent concept-based methods link the model predictions with interpretable concepts and modify …
View article: NGHIÊN CỨU ẢNH HƯỞNG CỦA MỘT SỐ YẾU TỐ BỔ SUNG ĐẾN QUÁ TRÌNH CHẾ BIẾN SẢN PHẨM SỮA CHUA
NGHIÊN CỨU ẢNH HƯỞNG CỦA MỘT SỐ YẾU TỐ BỔ SUNG ĐẾN QUÁ TRÌNH CHẾ BIẾN SẢN PHẨM SỮA CHUA Open
Nghiên cứu này được tiến hành nhằm xác định hàm lượng và loại yến mạch, vi khuẩn và carrageenan bổ sung vào sữa chua. Trong thí nghiệm, yến mạch cán dẹp hoặc cán vỡ (theo các tỷ lệ lần lượt là 1%; 1,2%; 1,5%) được phối trộn với sữa tươi, s…
View article: Revisiting LARS for Large Batch Training Generalization of Neural Networks
Revisiting LARS for Large Batch Training Generalization of Neural Networks Open
This paper investigates Large Batch Training techniques using layer-wise adaptive scaling ratio (LARS) across diverse settings. In particular, we first show that a state-of-the-art technique, called LARS with the warm-up, tends to be trapp…
View article: Enhancing Research Methodology and Academic Publishing: A Structured Framework for Quality and Integrity
Enhancing Research Methodology and Academic Publishing: A Structured Framework for Quality and Integrity Open
Following a brief introduction to research, research processes, research types, papers, reviews, and evaluations, this paper presents a structured framework for addressing inconsistencies in research methodology, technical writing, quality…
View article: Immunohistochemical basis for FAP as a candidate theranostic target across a broad range of cholangiocarcinoma subtypes
Immunohistochemical basis for FAP as a candidate theranostic target across a broad range of cholangiocarcinoma subtypes Open
Purpose The aims of this study were to evaluate and compare fibroblast activation protein (FAP) expression and localization in surgically resected cholangiocarcinoma (CCA), primary and metastatic hepatocellular carcinoma (HCC), hepatocellu…
View article: 653 Phase I/II clinical trial for radiation and dendritic cell combination immunotherapy in patients with unresectable hepatocellular carcinoma and cholangiocarcinoma
653 Phase I/II clinical trial for radiation and dendritic cell combination immunotherapy in patients with unresectable hepatocellular carcinoma and cholangiocarcinoma Open
View article: Federated Deep Equilibrium Learning: Harnessing Compact Global Representations to Enhance Personalization
Federated Deep Equilibrium Learning: Harnessing Compact Global Representations to Enhance Personalization Open
View article: Towards Layer-Wise Personalized Federated Learning: Adaptive Layer Disentanglement via Conflicting Gradients
Towards Layer-Wise Personalized Federated Learning: Adaptive Layer Disentanglement via Conflicting Gradients Open
In personalized Federated Learning (pFL), high data heterogeneity can cause significant gradient divergence across devices, adversely affecting the learning process. This divergence, especially when gradients from different users form an o…
View article: Federated PCA on Grassmann Manifold for IoT Anomaly Detection
Federated PCA on Grassmann Manifold for IoT Anomaly Detection Open
With the proliferation of the Internet of Things (IoT) and the rising interconnectedness of devices, network security faces significant challenges, especially from anomalous activities. While traditional machine learning-based intrusion de…
View article: Atezolizumab plus bevacizumab as first-line systemic therapy for hepatocellular carcinoma: a multi-institutional cohort study
Atezolizumab plus bevacizumab as first-line systemic therapy for hepatocellular carcinoma: a multi-institutional cohort study Open
Background Atezolizumab plus bevacizumab is the standard of care for advanced hepatocellular carcinoma (HCC) in the first-line setting, although was only evaluated in patients with Child-Pugh (CP) A liver function in the IMbrave150 trial. …
View article: $i$REPO: $i$mplicit Reward Pairwise Difference based Empirical Preference Optimization
$i$REPO: $i$mplicit Reward Pairwise Difference based Empirical Preference Optimization Open
While astonishingly capable, large Language Models (LLM) can sometimes produce outputs that deviate from human expectations. Such deviations necessitate an alignment phase to prevent disseminating untruthful, toxic, or biased information. …
View article: PAT: Pixel-wise Adaptive Training for Long-tailed Segmentation
PAT: Pixel-wise Adaptive Training for Long-tailed Segmentation Open
Beyond class frequency, we recognize the impact of class-wise relationships among various class-specific predictions and the imbalance in label masks on long-tailed segmentation learning. To address these challenges, we propose an innovati…
View article: Risk Factors for Severe Seafood Allergy Among Adults in an Urban City in Vietnam
Risk Factors for Severe Seafood Allergy Among Adults in an Urban City in Vietnam Open
Features of causative, coexisting seafood allergy, and risk factors for severe SFA were demonstrated, which can provide a reference for future studies.
View article: Pat: Pixel-Wise Adaptive Training for Long-Tailed Segmentation
Pat: Pixel-Wise Adaptive Training for Long-Tailed Segmentation Open
View article: Federated Deep Equilibrium Learning: Harnessing Compact Global Representations to Enhance Personalization
Federated Deep Equilibrium Learning: Harnessing Compact Global Representations to Enhance Personalization Open
Federated Learning (FL) has emerged as a groundbreaking distributed learning paradigm enabling clients to train a global model collaboratively without exchanging data. Despite enhancing privacy and efficiency in information retrieval and k…
View article: Social determinants of health: a need for better data capture in Asian American patients with hepatocellular cancer
Social determinants of health: a need for better data capture in Asian American patients with hepatocellular cancer Open