arXiv subjects

Phuc Nguyen

Publications and source records attributed to Phuc Nguyen.

At least 37 records · Page 2Linked to original sources

arXiv2025

Adaptive Spiking with Plasticity for Energy Aware Neuromorphic Systems

This paper presents ASPEN, a novel energy-aware technique for neuromorphic systems that could unleash the future of intelligent, always-on, ultra-low-power, and low-burden wearables. Our main research objectives are to explore the feasibility of neuromorphic computing for wearables, identify open research directions, and demonstrate the feasibility of developing an adaptive spiking technique for energy-aware computation, which can be game-changing for resource-constrained devices in always-on applications. As neuromorphic computing systems operate based on spike events, their energy consumption is closely related to spiking activity, i.e., each spike incurs computational and power costs; consequently, minimizing the number of spikes is a critical strategy for operating under constrained energy budgets. To support this goal, ASPEN utilizes stochastic perturbations to the neuronal threshold during training to not only enhance the network's robustness across varying thresholds, which can be controlled at inference time, but also act as a regularizer that improves generalization, reduces spiking activity, and enables energy control without the need for complex retraining or pruning. More specifically, ASPEN adaptively adjusts intrinsic neuronal parameters as a lightweight and scalable technique for dynamic energy control without reconfiguring the entire model. Our evaluation on neuromorphic emulator and hardware shows that ASPEN significantly reduces spike counts and energy consumption while maintaining accuracy comparable to state-of-the-art methods.

cs.NE↗

arXiv2025

QCResUNet: Joint Subject-level and Voxel-level Segmentation Quality Prediction

Deep learning has made significant strides in automated brain tumor segmentation from magnetic resonance imaging (MRI) scans in recent years. However, the reliability of these tools is hampered by the presence of poor-quality segmentation outliers, particularly in out-of-distribution samples, making their implementation in clinical practice difficult. Therefore, there is a need for quality control (QC) to screen the quality of the segmentation results. Although numerous automatic QC methods have been developed for segmentation quality screening, most were designed for cardiac MRI segmentation, which involves a single modality and a single tissue type. Furthermore, most prior works only provided subject-level predictions of segmentation quality and did not identify erroneous parts segmentation that may require refinement. To address these limitations, we proposed a novel multi-task deep learning architecture, termed QCResUNet, which produces subject-level segmentation-quality measures as well as voxel-level segmentation error maps for each available tissue class. To validate the effectiveness of the proposed method, we conducted experiments on assessing its performance on evaluating the quality of two distinct segmentation tasks. First, we aimed to assess the quality of brain tumor segmentation results. For this task, we performed experiments on one internal and two external datasets. Second, we aimed to evaluate the segmentation quality of cardiac Magnetic Resonance Imaging (MRI) data from the Automated Cardiac Diagnosis Challenge. The proposed method achieved high performance in predicting subject-level segmentation-quality metrics and accurately identifying segmentation errors on a voxel basis. This has the potential to be used to guide human-in-the-loop feedback to improve segmentations in clinical settings.

eess.IV↗

arXiv2025

Grade Inflation in Generative Models

Generative models hold great potential, but only if one can trust the evaluation of the data they generate. We show that many commonly used quality scores for comparing two-dimensional distributions of synthetic vs. ground-truth data give better results than they should, a phenomenon we call the "grade inflation problem." We show that the correlation score, Jaccard score, earth-mover's score, and Kullback-Leibler (relative-entropy) score all suffer grade inflation. We propose that any score that values all datapoints equally, as these do, will also exhibit grade inflation; we refer to such scores as "equipoint" scores. We introduce the concept of "equidensity" scores, and present the Eden score, to our knowledge the first example of such a score. We found that Eden avoids grade inflation and agrees better with human perception of goodness-of-fit than the equipoint scores above. We propose that any reasonable equidensity score will avoid grade inflation. We identify a connection between equidensity scores and Rényi entropy of negative order. We conclude that equidensity scores are likely to outperform equipoint scores for generative models, and for comparing low-dimensional distributions more generally.

cs.AI↗

arXiv2024

Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking

Existing 3D instance segmentation methods frequently encounter issues with over-segmentation, leading to redundant and inaccurate 3D proposals that complicate downstream tasks. This challenge arises from their unsupervised merging approach, where dense 2D instance masks are lifted across frames into point clouds to form 3D candidate proposals without direct supervision. These candidates are then hierarchically merged based on heuristic criteria, often resulting in numerous redundant segments that fail to combine into precise 3D proposals. To overcome these limitations, we propose a 3D-Aware 2D Mask Tracking module that uses robust 3D priors from a 2D mask segmentation and tracking foundation model (SAM-2) to ensure consistent object masks across video frames. Rather than merging all visible superpoints across views to create a 3D mask, our 3D Mask Optimization module leverages a dynamic programming algorithm to select an optimal set of views, refining the superpoints to produce a final 3D proposal for each object. Our approach achieves comprehensive object coverage within the scene while reducing unnecessary proposals, which could otherwise impair downstream applications. Evaluations on ScanNet200 and ScanNet++ confirm the effectiveness of our method, with improvements across Class-Agnostic, Open-Vocabulary, and Open-Ended 3D Instance Segmentation tasks.

cs.CV↗

arXiv2024

An Unobtrusive and Lightweight Ear-worn System for Continuous Epileptic Seizure Detection

Epilepsy is one of the most common neurological diseases globally (around 50 million people worldwide). Fortunately, up to 70% of people with epilepsy could live seizure-free if properly diagnosed and treated, and a reliable technique to monitor the onset of seizures could improve the quality of life of patients who are constantly facing the fear of random seizure attacks. The scalp-based EEG test, despite being the gold standard for diagnosing epilepsy, is costly, necessitates hospitalization, demands skilled professionals for operation, and is discomforting for users. In this paper, we propose EarSD, a novel lightweight, unobtrusive, and socially acceptable ear-worn system to detect epileptic seizure onsets by measuring the physiological signals from behind the user's ears. EarSD includes an integrated custom-built sensing-computing-communication PCB to collect and amplify the signals of interest, remove the noises caused by motion artifacts and environmental impacts, and stream the data wirelessly to the computer/mobile phone nearby, where data are uploaded to the host computer for further processing. We conducted both in-lab and in-hospital experiments with epileptic seizure patients who were hospitalized for seizure studies.

eess.SP↗

arXiv2024

An Open-Source Data Storage and Visualization Platform for Collaborative Qubit Control

Developing collaborative research platforms for quantum bit control is crucial for driving innovation in the field, as they enable the exchange of ideas, data, and implementation to achieve more impactful outcomes. Furthermore, considering the high costs associated with quantum experimental setups, collaborative environments are vital for maximizing resource utilization efficiently. However, the lack of dedicated data management platforms presents a significant obstacle to progress, highlighting the necessity for essential assistive tools tailored for this purpose. Current qubit control systems are unable to handle complicated management of extensive calibration data and do not support effectively visualizing intricate quantum experiment outcomes. In this paper, we introduce QubiCSV (Qubit Control Storage and Visualization), a platform specifically designed to meet the demands of quantum computing research, focusing on the storage and analysis of calibration and characterization data in qubit control systems. As an open-source tool, QubiCSV facilitates efficient data management of quantum computing, providing data versioning capabilities for data storage and allowing researchers and programmers to interact with qubits in real time. The insightful visualization are developed to interpret complex quantum experiments and optimize qubit performance. QubiCSV not only streamlines the handling of qubit control system data but also improves the user experience with intuitive visualization features, making it a valuable asset for researchers in the quantum computing domain.

quant-ph↗

arXiv2024

$\textit{lucie}$: An Improved Python Package for Loading Datasets from the UCI Machine Learning Repository

The University of California--Irvine (UCI) Machine Learning (ML) Repository (UCIMLR) is consistently cited as one of the most popular dataset repositories, hosting hundreds of high-impact datasets. However, a significant portion, including 28.4% of the top 250, cannot be imported via the $\textit{ucimlrepo}$ package that is provided and recommended by the UCIMLR website. Instead, they are hosted as .zip files, containing nonstandard formats that are difficult to import without additional ad hoc processing. To address this issue, here we present $\textit{lucie}$ -- $\underline{l}oad$ $\underline{U}niversity$ $\underline{C}alifornia$ $\underline{I}rvine$ $\underline{e}xamples$ -- a utility that automatically determines the data format and imports many of these previously non-importable datasets, while preserving as much of a tabular data structure as possible. $\textit{lucie}$ was designed using the top 100 most popular datasets and benchmarked on the next 130, where it resulted in a success rate of 95.4% vs. 73.1% for $\textit{ucimlrepo}$. $\textit{lucie}$ is available as a Python package on PyPI with 98% code coverage.

cs.LG↗

arXiv2024

Approximate Quantum Codes From Long Wormholes

We discuss families of approximate quantum error correcting codes which arise as the nearly-degenerate ground states of certain quantum many-body Hamiltonians composed of non-commuting terms. For exact codes, the conditions for error correction can be formulated in terms of the vanishing of a two-sided mutual information in a low-temperature thermofield double state. We consider a notion of distance for approximate codes obtained by demanding that this mutual information instead be small, and we evaluate this mutual information for the SYK model and for a family of low-rank SYK models. After an extrapolation to nearly zero temperature, we find that both kinds of models produce fermionic codes with constant rate as the number, $N$, of fermions goes to infinity. For SYK, the distance scales as $N^{1/2}$, and for low-rank SYK, the distance can be arbitrarily close to linear scaling, e.g. $N^{.99}$, while maintaining a constant rate. We also consider an analog of the no low-energy trivial states property which we dub the no low-energy adiabatically accessible states property and show that these models do have low-energy states that can be prepared adiabatically in a time that does not scale with system size $N$. We discuss a holographic model of these codes in which the large code distance is a consequence of the emergence of a long wormhole geometry in a simple model of quantum gravity.

quant-ph↗

arXiv2024

OpenSUN3D: 1st Workshop Challenge on Open-Vocabulary 3D Scene Understanding

This report provides an overview of the challenge hosted at the OpenSUN3D Workshop on Open-Vocabulary 3D Scene Understanding held in conjunction with ICCV 2023. The goal of this workshop series is to provide a platform for exploration and discussion of open-vocabulary 3D scene understanding tasks, including but not limited to segmentation, detection and mapping. We provide an overview of the challenge hosted at the workshop, present the challenge dataset, the evaluation methodology, and brief descriptions of the winning methods. For additional details, please see https://opensun3d.github.io/index_iccv23.html.

cs.CV↗

arXiv2024

One-half reflected entropy is not a lower bound for entanglement of purification

In recent work, Akers et al. proved that the entanglement of purification $E_p(A:B)$ is bounded below by half of the $q$-Rényi reflected entropy $S_R^{(q)}(A:B)$ for all $q\geq2$, showing that $E_p(A:B) = \frac{1}{2} S_R^{(q)}(A:B)$ for a class of random tensor network states. Naturally, the authors raise the question of whether a similar bound holds at $q = 1$. Our work answers that question in the negative by finding explicit counter-examples, which we arrive at through numerical optimization. Nevertheless, this result does not preclude the possibility that restricted sets of states, such as CFT states with semi-classical gravity duals, could obey the bound in question.

quant-ph↗

arXiv2024

Real-Time Diagnostic Integrity Meets Efficiency: A Novel Platform-Agnostic Architecture for Physiological Signal Compression

Head-based signals such as EEG, EMG, EOG, and ECG collected by wearable systems will play a pivotal role in clinical diagnosis, monitoring, and treatment of important brain disorder diseases. However, the real-time transmission of the significant corpus physiological signals over extended periods consumes substantial power and time, limiting the viability of battery-dependent physiological monitoring wearables. This paper presents a novel deep-learning framework employing a variational autoencoder (VAE) for physiological signal compression to reduce wearables' computational complexity and energy consumption. Our approach achieves an impressive compression ratio of 1:293 specifically for spectrogram data, surpassing state-of-the-art compression techniques such as JPEG2000, H.264, Direct Cosine Transform (DCT), and Huffman Encoding, which do not excel in handling physiological signals. We validate the efficacy of the compressed algorithms using collected physiological signals from real patients in the Hospital and deploy the solution on commonly used embedded AI chips (i.e., ARM Cortex V8 and Jetson Nano). The proposed framework achieves a 91% seizure detection accuracy using XGBoost, confirming the approach's reliability, practicality, and scalability.

eess.SP↗

arXiv2023

TabIQA: Table Questions Answering on Business Document Images

Table answering questions from business documents has many challenges that require understanding tabular structures, cross-document referencing, and additional numeric computations beyond simple search queries. This paper introduces a novel pipeline, named TabIQA, to answer questions about business document images. TabIQA combines state-of-the-art deep learning techniques 1) to extract table content and structural information from images and 2) to answer various questions related to numerical data, text-based information, and complex queries from structured tables. The evaluation results on VQAonBD 2023 dataset demonstrate the effectiveness of TabIQA in achieving promising performance in answering table-related questions. The TabIQA repository is available at https://github.com/phucty/itabqa.

cs.CV↗

arXiv2023

Rethinking Image-based Table Recognition Using Weakly Supervised Methods

Most of the previous methods for table recognition rely on training datasets containing many richly annotated table images. Detailed table image annotation, e.g., cell or text bounding box annotation, however, is costly and often subjective. In this paper, we propose a weakly supervised model named WSTabNet for table recognition that relies only on HTML (or LaTeX) code-level annotations of table images. The proposed model consists of three main parts: an encoder for feature extraction, a structure decoder for generating table structure, and a cell decoder for predicting the content of each cell in the table. Our system is trained end-to-end by stochastic gradient descent algorithms, requiring only table images and their ground-truth HTML (or LaTeX) representations. To facilitate table recognition with deep learning, we create and release WikiTableSet, the largest publicly available image-based table recognition dataset built from Wikipedia. WikiTableSet contains nearly 4 million English table images, 590K Japanese table images, and 640k French table images with corresponding HTML representation and cell bounding boxes. The extensive experiments on WikiTableSet and two large-scale datasets: FinTabNet and PubTabNet demonstrate that the proposed weakly supervised model achieves better, or similar accuracies compared to the state-of-the-art models on all benchmark datasets.

cs.CV↗

arXiv2022

Wikidata-lite for Knowledge Extraction and Exploration

Wikidata is the largest collaborative general knowledge graph supported by a worldwide community. It includes many helpful topics for knowledge exploration and data science applications. However, due to the enormous size of Wikidata, it is challenging to retrieve a large amount of data with millions of results, make complex queries requiring large aggregation operations, or access too many statement references. This paper introduces our preliminary works on Wikidata-lite, a toolkit to build a database offline for knowledge extraction and exploration, e.g., retrieving item information, statements, provenances, or searching entities by their keywords and attributes. Wikidata-lite has high performance and memory efficiency, much faster than the official Wikidata SPARQL endpoint for big queries. The Wikidata-lite repository is available at https://github.com/phucty/wikidb.

cs.DB↗

arXiv2022

Tree Representations of Brain Structural Connectivity via Persistent Homology

The brain structural connectome is generated by a collection of white matter fiber bundles constructed from diffusion weighted MRI (dMRI), acting as highways for neural activity. There has been abundant interest in studying how the structural connectome varies across individuals in relation to their traits, ranging from age and gender to neuropsychiatric outcomes. After applying tractography to dMRI to get white matter fiber bundles, a key question is how to represent the brain connectome to facilitate statistical analyses relating connectomes to traits. The current standard divides the brain into regions of interest (ROIs), and then relies on an adjacency matrix (AM) representation. Each cell in the AM is a measure of connectivity, e.g., number of fiber curves, between a pair of ROIs. Although the AM representation is intuitive, a disadvantage is the high-dimensionality due to the large number of cells in the matrix. This article proposes a simpler tree representation of the brain connectome, which is motivated by ideas in computational topology and takes topological and biological information on the cortical surface into consideration. We demonstrate that our tree representation preserves useful information and interpretability, while reducing dimensionality to improve statistical and computational efficiency. Applications to data from the Human Connectome Project (HCP) are considered and code is provided for reproducing our analyses.

stat.ME↗

arXiv2022

Checking volume-law entropy with HRT surfaces

We check formally that the Hubeny-Rangamani-Takayanagi prescription for holographic entanglement entropy -- when applied to a static black brane spacetime and to a wide class of subregions that do not lie on a constant time slice -- gives rise to volume-law entropy in the limit of large subregion. By volume-law entropy, we mean that the entanglement entropy scales with the volume of the projection of the boundary subregion onto a static time slice with respect to the boundary thermal state (with the same coefficient as in the volume law on the static time slice). Our result applies to subregions that have reflection symmetry as well as strips, and we also present field-theoretic arguments in support of our holographic findings.

hep-th↗

arXiv2021

Quantum chaos in a weakly-coupled field theory with nonlocality

In order to study the chaotic behavior of a system with non-local interactions, we will consider weakly coupled non-commutative field theories. We compute the Lyapunov exponent of this exponential growth in the large Moyal-scale limit to leading order in the t'Hooft coupling and $1/N$. We found that in this limit, the Lyapunov exponent remains comparable in magnitude to (and somewhat smaller than) the exponent in the commutative case. This can possibly be explained by the infrared sensitivity of the Lyapunov exponent. Another possible explanation is that in examples of weakly coupled non-commutative field theories, non-local contributions to various thermodynamic quantities are sub-dominant.

hep-th↗

arXiv2021

Scrambling and the black hole atmosphere

We argue that the scrambling time is the same, up to a numerical factor in three or more spacetime dimensions, as the time for the atmosphere to fall across the horizon or escape, to be replaced by new atmosphere. We propose that these times agree because the physical scrambling process is part and parcel of the atmosphere refreshment process. We provide some support for this relation also in two dimensions, but the atmosphere is not as localized, so the argument is less justified.

hep-th↗