arXiv subjects

Viet Tran

Publications and source records attributed to Viet Tran.

9 recordsLinked to original sources

arXiv2025

AI4EOSC: a Federated Cloud Platform for Artificial Intelligence in Scientific Research

The rapid growth of Artificial Intelligence and Machine Learning in scientific research has highlighted a gap between industry-standard MLOps tools and platforms, and the unique requirements of modern and Open Science, particularly regarding the FAIR (Findable, Accessible, Interoperable, and Reusable) principles. This paper presents AI4EOSC, a federated, open-source platform designed to operationalize the full AI/ML lifecycle within the European Open Science Cloud (EOSC) ecosystem. Our methodology tackles the fragmentation of distributed research infrastructures by integrating a modular and distributed architecture comprising an AI development platform, a serverless AI-as-a-Service layer, and a federated orchestration model that is able to integrate heterogeneous compute and storage resources from distributed e-Infrastructures. AI4EOSC also introduces a ``FAIR-by-design'' approach that enforces metadata standardization (via MLDCAT-AP) and W3C PROV-compliant provenance tracking through a platform-integrated CI/CD pipeline. AI4EOSC added value is demonstrated through the delivery of a diverse set of community installations, showing consistent and seamless deployment across heterogeneous cloud providers. These installations are validated by a set of scientific cases, showing how our work reduces the manual burden on researchers while ensuring high levels of reproducibility and interoperability and providing an unified environment for development, training, and production of AI/ML models in the EOSC.

cs.DC↗

arXiv2025

Intervention Efficiency and Perturbation Validation Framework: Capacity-Aware and Robust Clinical Model Selection under the Rashomon Effect

In clinical machine learning, the coexistence of multiple models with comparable performance (a manifestation of the Rashomon Effect) poses fundamental challenges for trustworthy deployment and evaluation. Small, imbalanced, and noisy datasets, coupled with high-dimensional and weakly identified clinical features, amplify this multiplicity and make conventional validation schemes unreliable. As a result, selecting among equally performing models becomes uncertain, particularly when resource constraints and operational priorities are not considered by conventional metrics like F1 score. To address these issues, we propose two complementary tools for robust model assessment and selection: Intervention Efficiency (IE) and the Perturbation Validation Framework (PVF). IE is a capacity-aware metric that quantifies how efficiently a model identifies actionable true positives when only limited interventions are feasible, thereby linking predictive performance with clinical utility. PVF introduces a structured approach to assess the stability of models under data perturbations, identifying models whose performance remains most invariant across noisy or shifted validation sets. Empirical results on synthetic and real-world healthcare datasets show that using these tools facilitates the selection of models that generalize more robustly and align with capacity constraints, offering a new direction for tackling the Rashomon Effect in clinical settings.

cs.LG↗

arXiv2025

Solving quadratic binary optimization problems using quantum SDP methods: Non-asymptotic running time analysis

Quantum computers can solve semidefinite programs (SDPs) using resources that scale better than state-of-the-art classical methods as a function of the problem dimension. At the same time, the known quantum algorithms scale very unfavorably in the precision, which makes it non-trivial to find applications for which the quantum methods are well-suited. Arguably, precision is less crucial for SDP relaxations of combinatorial optimization problems (such as the Goemans-Williamson algorithm), because these include a final rounding step that maps SDP solutions to binary variables. With this in mind, Brand\~ao, Fran\c{c}a, and Kueng have proposed to use quantum SDP solvers in order to achieve an end-to-end speed-up for obtaining approximate solutions to combinatorial optimization problems. They did indeed succeed in identifying an algorithm that realizes a polynomial quantum advantage in terms of its asymptotic running time. However, asymptotic results say little about the problem sizes for which advantages manifest. Here, we present an analysis of the non-asymptotic resource requirements of this algorithm. The work consists of two parts. First, we optimize the original algorithm with a particular emphasis on performance for realistic problem instances. In particular, we formulate a version with adaptive step-sizes, an improved detection criterion for infeasible instances, and a more efficient rounding procedure. In a second step, we benchmark both the classical and the quantum version of the algorithm. The benchmarks did not identify a regime where even the optimized quantum algorithm would beat standard classical approaches for input sizes that can be realistically solved at all. In the absence of further significant improvements, these algorithms therefore fall into a category sometimes called galactic: Unbeaten in their asymptotic scaling behavior, but not practical for realistic problems.

quant-ph↗

arXiv2024

Classification of Single Photons in Higher-Order Spatial Modes via Convolutional Neural Networks

Spatial modes are a promising candidate for encoding information for classical and quantum optical communication due to their potential high information capacity. Unfortunately, compensation of the wavefront upon propagation through the atmosphere is necessary to benefit from advantages spatial modes offer. In this work, we leverage the success of convolutional networks in denoising and classifying images to improve information transfer of spatial modes. Hermite-Gauss, Laguerre-Gauss, and Ince-Gauss modes are experimentally generated using single photons and imaged. A denoising autoencoder corrects for turbulence effects on the wavefront, followed by a convolutional neural network to classify mode orders. The model achieves a 99.2% classification accuracy across all modes, and Hermite-Gauss modes exhibited the highest individual mode accuracy. As the convolutional networks rely solely on intensity, they offer an efficient and cost-effective tool for optical communication systems in the single photon limit.

physics.optics↗

arXiv2024

Manipulating ferroelectric topological polar structures with twisted light

The dynamic control of novel states of matter beyond thermodynamic equilibrium is a fundamental pursuit in condensed matter physics. Intense terahertz fields have enabled metal-insulator transitions, superconductivity, quantum paraelectric ferroelectricity, and room-temperature magnetization via circularly polarized terahertz electric fields. These effects hinge on the excitation of infrared-active soft phonon modes by terahertz fields. Expanding this concept, recent theory suggests that ferroelectric polarization may be manipulated through terahertz twisted light, transferring orbital angular momentum to create ferroelectric skyrmions. Our study experimentally demonstrates that such control is possible in quasi-2D ferroelectric CsBiNb2O7 using twisted UV light with orbital angular momentum (OAM). By resonantly exciting both the ferroelectric mode and the octahedral tilting mode, twisted UV light dynamically modulates the ferroelectric polarization. We employ in-situ X-ray Bragg coherent diffractive imaging, twisted optical Raman spectroscopy, and density functional theory to three-dimensionally resolve ionic displacement fields and polarization texture changes. Our observations reveal deterministic, reversible twisted light-induced strain and ionic displacements within the unit cell, causing substantial microscopic polarization changes. This interaction between twisted photons, phonon modes, and induced ionic displacements breaks symmetry and stabilizes a non-equilibrium ferroelectric phase with topological solitons. These findings offer a new path to control ferroelectricity and magnetism, opening avenues for novel optoelectronic devices such as ultrafast non-volatile memory switches by using light to coherently control ferroic states.

cond-mat.mtrl-sci↗

arXiv2022

CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP

CLIP yielded impressive results on zero-shot transfer learning tasks and is considered as a foundation model like BERT or GPT3. CLIP vision models that have a rich representation are pre-trained using the InfoNCE objective and natural language supervision before they are fine-tuned on particular tasks. Though CLIP excels at zero-shot transfer learning, it suffers from an explaining away problem, that is, it focuses on one or few features, while neglecting other relevant features. This problem is caused by insufficiently extracting the covariance structure in the original multi-modal data. We suggest to use modern Hopfield networks to tackle the problem of explaining away. Their retrieved embeddings have an enriched covariance structure derived from co-occurrences of features in the stored embeddings. However, modern Hopfield networks increase the saturation effect of the InfoNCE objective which hampers learning. We propose to use the InfoLOOB objective to mitigate this saturation effect. We introduce the novel "Contrastive Leave One Out Boost" (CLOOB), which uses modern Hopfield networks for covariance enrichment together with the InfoLOOB objective. In experiments we compare CLOOB to CLIP after pre-training on the Conceptual Captions and the YFCC dataset with respect to their zero-shot transfer learning performance on other datasets. CLOOB consistently outperforms CLIP at zero-shot transfer learning across all considered architectures and datasets.

cs.LG↗

arXiv2022

An Effective Deep Network for Head Pose Estimation without Keypoints

Human head pose estimation is an essential problem in facial analysis in recent years that has a lot of computer vision applications such as gaze estimation, virtual reality, and driver assistance. Because of the importance of the head pose estimation problem, it is necessary to design a compact model to resolve this task in order to reduce the computational cost when deploying on facial analysis-based applications such as large camera surveillance systems, AI cameras while maintaining accuracy. In this work, we propose a lightweight model that effectively addresses the head pose estimation problem. Our approach has two main steps. 1) We first train many teacher models on the synthesis dataset - 300W-LPA to get the head pose pseudo labels. 2) We design an architecture with the ResNet18 backbone and train our proposed model with the ensemble of these pseudo labels via the knowledge distillation process. To evaluate the effectiveness of our model, we use AFLW-2000 and BIWI - two real-world head pose datasets. Experimental results show that our proposed model significantly improves the accuracy in comparison with the state-of-the-art head pose estimation methods. Furthermore, our model has the real-time speed of $\sim$300 FPS when inferring on Tesla V100.

cs.CV↗

arXiv2020

Unsupervised Anomaly Detection for X-Ray Images

Obtaining labels for medical (image) data requires scarce and expensive experts. Moreover, due to ambiguous symptoms, single images rarely suffice to correctly diagnose a medical condition. Instead, it often requires to take additional background information such as the patient's medical history or test results into account. Hence, instead of focusing on uninterpretable black-box systems delivering an uncertain final diagnosis in an end-to-end-fashion, we investigate how unsupervised methods trained on images without anomalies can be used to assist doctors in evaluating X-ray images of hands. Our method increases the efficiency of making a diagnosis and reduces the risk of missing important regions. Therefore, we adopt state-of-the-art approaches for unsupervised learning to detect anomalies and show how the outputs of these methods can be explained. To reduce the effect of noise, which often can be mistaken for an anomaly, we introduce a powerful preprocessing pipeline. We provide an extensive evaluation of different approaches and demonstrate empirically that even without labels it is possible to achieve satisfying results on a real-world dataset of X-ray images of hands. We also evaluate the importance of preprocessing and one of our main findings is that without it, most of our approaches perform not better than random. To foster reproducibility and accelerate research we make our code publicly available at https://github.com/Valentyn1997/xray

eess.IV↗

arXiv2018

Influence of symmetry breaking on Fano-like resonances in high Figure of Merit planar terahertz metafilms

It is well established that nearly all high-quality (Q) Fano-like resonances in terahertz (THz) metasurfaces broaden as asymmetry increases, resulting in a decline of Q-factor and an increase in the resonance intensity. Therefore, in order to determine the optimal design for applications in THz sensing, a Figure of Merit (FoM) is required. Previous studies have identified the asymmetry regimes at which the peak FoM occurs for various, specific unit cell geometries. However to date, there is no systematic comparison of the resulting FoMs for common and novel geometries. Here, a THz planar metafilm featuring split ring resonators with four distributed capacitive gaps is investigated to compare three unique methods of implementing asymmetry: (1) adjacent L-bracket translation, (2) capacitive gap translation and (3) increasing gap width. The results obtained find that by translating two gaps and increasing the bottom gap width of the unit cell, the high-Q Fano-like resonances are $6 \times$ higher than the FoM for the fundamental dipole mode. This work further informs the design process for THz metasurfaces and as such will help to define their applications in photonics and sensing.

physics.app-ph↗