arXiv subjects

Tien-Cuong Nguyen

Publications and source records attributed to Tien-Cuong Nguyen.

6 recordsLinked to original sources

arXiv2026

DeepHSIC: Deep Learning-based Signal Detector for Hybrid Downlink IM-NOMA

DeepHSIC is introduced as a neural receiver for hybrid downlink IM-NOMA transmission. The considered scheme combines power-domain NOMA with a composite OFDM/OFDM-IM waveform, so that user information is mapped jointly onto constellation symbols, subcarrier-index patterns, and different power levels. Although maximum-likelihood detection can achieve strong reliability for this model, its search space grows rapidly with the number of users and subcarriers. Conventional SIC reduces part of this burden, but its sequential cancellation may still accumulate errors and does not fully exploit the structure of IM-NOMA signals. To address this limitation, the proposed detector embeds dedicated deep neural network modules into the receiver and replaces the most computationally demanding SIC operations with learned inference blocks. The receiver is trained for Rayleigh fading channels and uses preprocessed channel-output features to recover user symbols. Simulation results show that DeepHSIC reaches BER performance close to model-based detectors under both perfect and imperfect CSI while requiring substantially lower detection time. These results indicate that learned SIC-style detection is a practical candidate for scalable hybrid downlink IM-NOMA receivers.

cs.IT↗

arXiv2026

Enhancing Explainable Cardiac Diagnosis with Guide-Grounded Multimodal LLMs

The electrocardiogram (ECG) is a cornerstone of cardiac as- sessment, yet clinical deployment of deep learning models remains con- strained by limited interpretability and the hallucination risk of large language models (LLMs). Existing CNN+Grad-CAM+multimodal LLM frameworks can generate ECG reports, but their explanations are often only weakly grounded in established diagnostic criteria, reducing trust- worthiness and reproducibility. We propose a guide-grounded multimodal framework that explicitly anchors report generation in curated clinical knowledge. A convolutional neural network (CNN) and Grad-CAM first produce class probabilities and class-specific heatmaps from 12-lead ECG images. In parallel, authoritative ECG textbooks and guideline materials are distilled offline into a structured ECG Interpretation Guide, which is injected as a fixed knowledge block for every sample. Conditioned on the ECG image, Grad-CAM overlay, CNN-derived fact pack, and the in- jected guide, a multimodal LLM generates structured diagnostic reports with guideline-consistent terminology and criteria usage. Experiments on the full PTB-XL test set demonstrate that guide grounding improves se- mantic quality and perceived consistency of generated reports while pre- serving competitive classification performance. In particular, our method increases the average BERTScore of generated impressions from 0.818 to 0.953 relative to a strong CNN+Grad-CAM+MLLM baseline, indicat- ing closer alignment with reference reports. These findings suggest that injecting a distilled interpretation guide into the multimodal prompting pipeline offers a practical pathway to reduce hallucinations and enhance the clinical plausibility of LLM-based ECG explanations, bringing ex- plainable cardiac diagnosis closer to real-world deployment.

cs.AI↗

arXiv2026

HERMES: Contrast-Aware Knowledge Graph Reasoning from Clinical Notes for Patient Outcome Prediction

Clinical predictive models often rely on structured Electronic Health Record data, such as time-series and procedure codes. While recent approaches have begun leveraging unstructured clinical notes, they typically encode them as flat sequences, which may lose explicit relational and temporal structure present in clinical narratives. In response, we propose HERMES, a graph-based framework that operates exclusively on clinical text while preserving clinical relationships. This approach builds on two key ideas. First, personalized Knowledge Graphs (KGs) are constructed through Large-Language-Model-guided extraction from clinical notes with Contrastive Logic Modeling that explicitly captures temporal dynamics and treatment failures and changes in outcomes. Second, a Graph Attention Network synthesizes patient representations through graph-based learning over the KGs. Experiments on MIMIC-III and MIMIC-IV for in-hospital mortality and 30-day readmission prediction show that HERMES consistently outperforms strong text-only baselines. Our findings demonstrate that explicit relational modeling with Contrastive Logic Modeling significantly advances predictive performance.

cs.CL↗

arXiv2026

A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge Graphs

Multi-Document Summarization (MDS) plays a critical role in distilling essential information from collections of textual data. Existing approaches often struggle to capture complex inter-document relationships, rely heavily on large amounts of labeled data for supervised training, or exhibit limited generalization across domains and languages. To address these limitations, we present a training-free mixture-of-agents framework for MDS that leverages the complementary strengths of large language models (LLMs) and knowledge graphs. Our approach decomposes summarization into specialized agent tasks: extractive selection, knowledge-aware abstraction, and iterative refinement, each operating without task-specific fine-tuning. We unify their outputs using a multi-perspective consistency mechanism guided by LLMs. Experiments across four datasets in English and Vietnamese demonstrate state-of-the-art or competitive performance, validating the effectiveness and adaptability of our modular design.

cs.CL↗

arXiv2021

Pairwise interactions for Potential energy surfaces and Atomic forces with Deep Neural network

Molecular dynamics (MD) simulation, which is considered an important tool for studying physical and chemical processes at the atomic scale, requires accurate calculations of energies and forces. Although reliable energies and forces can be obtained by electronic structure calculations such as those based on density functional theory (DFT), this approach is computationally expensive. In this work, we propose a full-stack model using deep neural network (NN) to enhance the calculation of force and energy, in which the NN is designed to extract the embedding feature of pairwise interactions of an atom and its neighbors, which are aggregated to obtain its feature vector for predicting atomic force and potential energy. By designing the features of the pairwise interactions, we can control the performance of models and take into account the many-body effects and other physics of the atomic interactions. Moreover, we demonstrated that using the Coulomb matrix of the local structures in complement to the pairwise information, we can improve the prediction of force and energy for silicon systems and the transferability of our models is confirmed to larger systems, with high accuracy.

cond-mat.mtrl-sci↗

arXiv2021

Learning Hidden Chemistry with Deep Neural Networks

We demonstrate a machine learning approach designed to extract hidden chemistry/physics to facilitate new materials discovery. In particular, we propose a novel method for learning latent knowledge from material structure data in which machine learning models are developed to present the possibility that an atom can be paired with a chemical environment in an observed materials. For this purpose, we trained deep neural networks acquiring information from the atom of interest and its environment to estimate the possibility. The models were then used to establish recommendation systems, which can suggest a list of atoms for an environment within a structure. The center atom of that environment was then replaced with the various recommended atoms to generate new structures. Based on these recommendations, we also propose a method of dissimilarity measurement between the atoms and, through hierarchical cluster analysis and visualization using the multidimensional scaling algorithm, illustrate that this dissimilarity can reflect the chemistry of the elements. Finally, our models were applied to the discovery of new structures in the well-known magnetic material Nd$_2$Fe$_{14}$B. Our models propose 108 new structures, 71 of which are confirmed to converge to local-minimum-energy structures with formation energy less than 0.1 eV by first-principles calculations.

cond-mat.mtrl-sci↗