arXiv subjects

Trung Nguyen

Publications and source records attributed to Trung Nguyen.

15 recordsLinked to original sources

arXiv2026

A visual large language foundational model for medical image recognition using clinician-oriented social media

Large language models (LLMs) have demonstrated strong capabilities across diverse domains, showing considerable potential in medicine. However, their application in medical settings remains limited by the scarcity of visual question answering (VQA) datasets that capture clinical reasoning and explicit image-text alignment. Here, we leverage de-identified medical images and expert commentaries shared on clinician-oriented social media. By combining an advanced LLM with clinician-in-the-loop verification, we established a rigorous pipeline to construct ThoughtMed-1M, a long-form medical VQA dataset containing over one million VQA pairs and designed to capture structured clinical logic and medical image-text alignment. To demonstrate its utility, we developed a FOundational LLM Trained on ThoughtMed-1M (FOLTMed). FOLTMed achieved state-of-the-art performance across 42 medical VQA benchmark datasets, with a macro accuracy of 85.4%, and generated more clinically coherent responses on the ThoughtMed-1M test set. It outperformed state-of-the-art models by 3--5% across factuality and similarity metrics, highlighting a scalable paradigm for advancing research on clinically grounded multimodal LLMs.

cs.AI↗

arXiv2026

Revisiting Fazly-Wei-Xu pointwise estimates for the fourth-order H\'enon equation via Bernstein's technique

In a remarkable work published in Analysis and PDE 8 (2015) 1541-1563, M. Fazly, J. Wei, and X. Xu establish the following pointwise estimate \[-\Delta u \geq \frac 2{n-4} \frac{|\nabla u|^2}u + \sqrt{\frac 2{p+1- \frac 8{n(n-4)}}} |x|^{\frac \sigma 2} u^\frac{p+1}2 \quad \text{in } \mathbf R^n\] for any bounded, positive, $C^4$-solution $u$ to the the fourth-order H\'enon equation \[\Delta^2 u = |x|^\sigma u^p \quad \text{in } \mathbf R^n\] with $n \geq 5$, $\sigma \geq 0 $ but implicitly near $0$, and $p>(n+4+2\sigma)/(n-4)$. Their argument relies on a sophisticated iteration argument in the fashion of the standard Moser proof. In this paper, we provide an alternative approach which relies on the Bernstein technique via the maximum principle. The heart of our argument is a suitable choice of an auxiliary function allowing us not only achieving the same pointwise estimate, which still holds even for $p = (n+4+2\sigma)/(n-4)$, but also relaxing the boundedness of solutions. In addition, the pointwise inequality actually holds for any $\sigma \geq 0$. This estimate leads to an interesting consequence of the existence of conformal metric of $\mathbf R^n$ having positive scalar and $Q$ curvatures. We also show that the coefficient $2/(n-4)$ is sharp, hence providing the first answer to the question in the op. cit. paper. Our proof appears to be simpler and constructive.

math.AP↗

arXiv2026

Simulation of Two-qubit Gate Variability and Fidelity of Spin Qubits Built on Nanosheet Technology

Silicon spin qubits are promising for large-scale quantum-computer integration because they can fully leverage the well-developed semiconductor infrastructure. However, the low fidelity of two-qubit entanglement gates remains a key barrier to large-scale integrations. Recent simulations of silicon spin-qubit two-qubit gates have been performed on silicon-on-insulator (SOI) platforms, while nanosheet-based charge-qubit work has been limited to single-qubit operation using a two-dimensional Schr\"odinger approximation. In this work, we study silicon spin-qubit double quantum dots built on nanosheet technology using the Quantum Technology Computer-Aided Design (QTCAD) simulation suite to run three-dimensional Poisson and Schroedinger solvers, followed by a many-body solver to extract exchange interactions. We evaluate the exchange energy sensitivity to process and bias variations and then use QuTiP to solve the master equation for a two-qubit gate. The results show that millivolt-level bias variations at the plunger and middle barrier gates can reduce the gate fidelity below 99%, a common threshold target for many fault-tolerant quantum-computing algorithms. Gate-referred 1/f charge-noise effects are also analyzed through the resulting coherence time.

quant-ph↗

arXiv2026

MMGNN: Multi-level, multi-color graph neural networks for molecular property prediction

Molecular message-passing neural networks commonly propagate chemically diverse interactions through a single graph, which may mix interaction-specific signals and require deep propagation to capture long-range effects. We introduce the Multi-level, Multi-color Graph Neural Network (MMGNN), a hierarchical framework that decomposes a molecular graph into overlapping atom-type-pair-specific subgraphs while preserving atom-level resolution. MMGNN-2D constructs chemical-colored subgraphs from covalent connectivity, whereas MMGNN-3D constructs geometric-colored subgraphs from spatial proximity and augments their edges with distance, angular, and torsional descriptors. Both variants apply a shared communicative message-passing backbone to each subgraph and combine the resulting representations through atom-wise aggregation and molecular readout. We evaluated MMGNN on five classification and three regression benchmarks from MoleculeNet using common scaffold splits and five independent runs. MMGNN-2D achieved the highest macro-average AUC-ROC of 0.838 across the classification datasets and the lowest RMSE on ESOL (0.803). MMGNN-3D obtained the highest mean AUC-ROC on BBBP (0.956) and the lowest RMSE on FreeSolv (1.793), indicating complementary strengths of topological and geometric representations. Structural and leave-one-out analyses further illustrate how the subgraph decomposition affects learned representations and atom-type-pair sensitivities. These results support overlapping interaction-specific graph decomposition as a competitive strategy for molecular property prediction.

cs.LG↗

arXiv2025

Institutional Research Computing Capabilities in Australia: 2024

Institutional research computing infrastructure plays a vital role in Australia's research ecosystem, complementing and extending national facilities. This paper analyses research computing capabilities across Australian universities and organisations, showing how institutional systems support research excellence through local compute resources, specialised hardware, and cluster solutions. Our study finds that nearly 112,258 CPU cores and 2,241 GPUs serve over 6,000 researchers as essential bridges between desktops and national facilities, enabling workflows from development to large-scale computations. The estimated replacement value of this infrastructure is $144M AUD. Drawing on detailed data from multiple institutions, we identify key patterns in deployment, utilisation, and strategic alignment with research priorities. Institutional resources provide critical support for data-intensive projects, facilitate training and higher-degree student research, enable prototyping and development, and ensure data sovereignty compliance when required. The analysis shows how these facilities leverage national investments while addressing institution-specific needs that national systems cannot meet. We present evidence that strategic investment in institutional capabilities yields significant returns through greater research productivity, enhanced graduate training, and improved outcomes. The study offers insights for organisations planning computing strategies and highlights the importance of maintaining robust institutional resources alongside national facilities.

cs.DC↗

arXiv2025

Geometric Multi-color Message Passing Graph Neural Networks for Blood-brain Barrier Permeability Prediction

Accurate prediction of blood-brain barrier permeability (BBBP) is essential for central nervous system (CNS) drug development. While graph neural networks (GNNs) have advanced molecular property prediction, they often rely on molecular topology and neglect the three-dimensional geometric information crucial for modeling transport mechanisms. This paper introduces the geometric multi-color message-passing graph neural network (GMC-MPNN), a novel framework that enhances standard message-passing architectures by explicitly incorporating atomic-level geometric features and long-range interactions. Our model constructs weighted colored subgraphs based on atom types to capture the spatial relationships and chemical context that govern BBB permeability. We evaluated GMC-MPNN on three benchmark datasets for both classification and regression tasks, using rigorous scaffold-based splitting to ensure a robust assessment of generalization. The results demonstrate that GMC-MPNN consistently outperforms existing state-of-the-art models, achieving superior performance in both classifying compounds as permeable/non-permeable (AUC-ROC of 0.947 and 0.9212) and in regressing continuous permeability values (RMSE of 0.5628, Pearson correlation of 0.6947). An ablation study further quantified the impact of specific atom-pair interactions, revealing that the model's predictive power derives from its ability to learn from both common and rare, but chemically significant, functional motifs. By integrating spatial geometry into the graph representation, GMC-MPNN sets a new performance benchmark and offers a more accurate and generalizable tool for drug discovery pipelines.

cs.LG↗

arXiv2025

Near-Polynomially Competitive Active Logistic Regression

We address the problem of active logistic regression in the realizable setting. It is well known that active learning can require exponentially fewer label queries compared to passive learning, in some cases using $\log \frac{1}{\eps}$ rather than $\poly(1/\eps)$ labels to get error $\eps$ larger than the optimum. We present the first algorithm that is polynomially competitive with the optimal algorithm on every input instance, up to factors polylogarithmic in the error and domain size. In particular, if any algorithm achieves label complexity polylogarithmic in $\eps$, so does ours. Our algorithm is based on efficient sampling and can be extended to learn more general class of functions. We further support our theoretical results with experiments demonstrating performance gains for logistic regression compared to existing active learning algorithms.

cs.LG↗

arXiv2025

Toward a Flexible Framework for Linear Representation Hypothesis Using Maximum Likelihood Estimation

Linear representation hypothesis posits that high-level concepts are encoded as linear directions in the representation spaces of LLMs. Park et al. (2024) formalize this notion by unifying multiple interpretations of linear representation, such as 1-dimensional subspace representation and interventions, using a causal inner product. However, their framework relies on single-token counterfactual pairs and cannot handle ambiguous contrasting pairs, limiting its applicability to complex or context-dependent concepts. We introduce a new notion of binary concepts as unit vectors in a canonical representation space, and utilize LLMs' (neural) activation differences along with maximum likelihood estimation (MLE) to compute concept directions (i.e., steering vectors). Our method, Sum of Activation-base Normalized Difference (SAND), formalizes the use of activation differences modeled as samples from a von Mises-Fisher (vMF) distribution, providing a principled approach to derive concept directions. We extend the applicability of Park et al. (2024) by eliminating the dependency on unembedding representations and single-token pairs. Through experiments with LLaMA models across diverse concepts and benchmarks, we demonstrate that our lightweight approach offers greater flexibility, superior performance in activation engineering tasks like monitoring and manipulation.

cs.LG↗

arXiv2021

The convergence of the Regula Falsi method

Regula Falsi, or the method of false position, is a numerical method for finding an approximate solution to f(x) = 0 on a finite interval [a, b], where f is a real-valued continuous function on [a, b] and satisfies f(a)f(b) < 0. Previous studies proved the convergence of this method under certain assumptions about the function f, such as both the first and second derivatives of f do not change the sign on the interval [a, b]. In this paper, we remove those assumptions and prove the convergence of the method for all continuous functions.

math.NA↗

arXiv2021

Point-set Distances for Learning Representations of 3D Point Clouds

Learning an effective representation of 3D point clouds requires a good metric to measure the discrepancy between two 3D point sets, which is non-trivial due to their irregularity. Most of the previous works resort to using the Chamfer discrepancy or Earth Mover's distance, but those metrics are either ineffective in measuring the differences between point clouds or computationally expensive. In this paper, we conduct a systematic study with extensive experiments on distance metrics for 3D point clouds. From this study, we propose to use sliced Wasserstein distance and its variants for learning representations of 3D point clouds. In addition, we introduce a new algorithm to estimate sliced Wasserstein distance that guarantees that the estimated value is close enough to the true one. Experiments show that the sliced Wasserstein distance and its variants allow the neural network to learn a more efficient representation compared to the Chamfer discrepancy. We demonstrate the efficiency of the sliced Wasserstein metric and its variants on several tasks in 3D computer vision including training a point cloud autoencoder, generative modeling, transfer learning, and point cloud registration.

cs.CV↗

arXiv2020

Detecting Hands and Recognizing Physical Contact in the Wild

We investigate a new problem of detecting hands and recognizing their physical contact state in unconstrained conditions. This is a challenging inference task given the need to reason beyond the local appearance of hands. The lack of training annotations indicating which object or parts of an object the hand is in contact with further complicates the task. We propose a novel convolutional network based on Mask-RCNN that can jointly learn to localize hands and predict their physical contact to address this problem. The network uses outputs from another object detector to obtain locations of objects present in the scene. It uses these outputs and hand locations to recognize the hand's contact state using two attention mechanisms. The first attention mechanism is based on the hand and a region's affinity, enclosing the hand and the object, and densely pools features from this region to the hand region. The second attention module adaptively selects salient features from this plausible region of contact. To develop and evaluate our method's performance, we introduce a large-scale dataset called ContactHands, containing unconstrained images annotated with hand locations and contact states. The proposed network, including the parameters of attention modules, is end-to-end trainable. This network achieves approximately 7\% relative improvement over a baseline network that was built on the vanilla Mask-RCNN architecture and trained for recognizing hand contact states.

cs.CV↗

arXiv2019

Reducibility of Schrödinger equation on a Zoll manifold with unbounded potential

In this article we prove a reducibility result for the linear Schrödinger equation on a Zoll manifold with quasi-periodic in time pseudo-differential perturbation of order less or equal than $1/2$. As far as we know, this is the first reducibility results for an unbounded perturbation of a linear system which is not integrable.

math.AP↗

arXiv2019

An unstable three dimensional KAM torus for the quintic NLS

We consider the quintic nonlinear Schr{ö}dinger on the circle. By applying a Birkhoff procedure and a KAM theorem, we exihibit a three dimension invariant torus that is linearly unstable. In comparison, we also prove that two dimensional tori are always linearly stable.

math.DS↗

arXiv2018

A Smart Security System with Face Recognition

Web-based technology has improved drastically in the past decade. As a result, security technology has become a major help to protect our daily life. In this paper, we propose a robust security based on face recognition system (SoF). In particular, we develop this system to giving access into a home for authenticated users. The classifier is trained by using a new adaptive learning method. The training data are initially collected from social networks. The accuracy of the classifier is incrementally improved as the user starts using the system. A novel method has been introduced to improve the classifier model by human interaction and social media. By using a deep learning framework - TensorFlow, it will be easy to reuse the framework to adopt with many devices and applications.

cs.MM↗

arXiv2006

A disk-covering problem with application in optical interferometry

Given a disk O in the plane called the objective, we want to find n small disks P_1,...,P_n called the pupils such that $\bigcup_{i,j=1}^n P_i \ominus P_j \supseteq O$, where $\ominus$ denotes the Minkowski difference operator, while minimizing the number of pupils, the sum of the radii or the total area of the pupils. This problem is motivated by the construction of very large telescopes from several smaller ones by so-called Optical Aperture Synthesis. In this paper, we provide exact, approximate and heuristic solutions to several variations of the problem.

cs.CG↗