Phuc Nguyen

Phuc Nguyen, Nam Tuan Ly, Hideaki Takeda et al.

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.

Nam Tuan Ly, Atsuhiro Takasu, Phuc Nguyen et al.

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.

Phuc Nguyen, Josiah Couch, Rahul Bansal et al.

A canonical step in quantifying a system is to measure its entropy. Shannon entropy and other traditional entropy measures capture only the information encoded in the frequencies of a system's elements. Recently, Leinster, Cobbold, and Reeve (LCR) introduced a method that also captures the rich information encoded in the similarities and differences among elements, yielding similarity-sensitive entropy. More recently, the Vendi score (VS) was introduced as an alternative, raising the question of how LCR and VS compare, and which is preferable. Here we address these questions conceptually, analytically, and experimentally, using 53 machine-learning datasets. We show that LCR and VS can differ by orders of magnitude and can capture complementary information about a system, except in limiting cases. We demonstrate that both LCR and VS depend on how similarities are scaled and introduce the concept of ``half distance'' to parameterize this dependence. We prove that VS provides an upper bound on LCR for several values of the Rényi-Hill order parameter and conjecture that this bound holds for all values. We conclude that VS is preferable only when interpreting elements as linear combinations of a more fundamental set of ``ur-elements'' or when the system or dataset possesses a quantum-mechanical character. In the broader circumstance where one seeks simply to capture the rich information encoded by similarity, LCR is favored; nevertheless, for certain half-distances the two methods can complement each other.

Khiem Le, Youssef Mroueh, Phuc Nguyen et al.

Large language models trained via next-token prediction are fundamentally pattern-matchers: sensitive to superficial phrasing variations even when the underlying problem is identical. Group Relative Policy Optimization (GRPO) was designed to improve reasoning, but in fact it worsens this situation through two failure modes: diversity collapse, where training amplifies a single solution strategy while ignoring alternatives of gradient signal, and gradient diminishing, where a large portion of questions yield zero gradients because all rollouts receive identical rewards. We propose TA-GRPO (Transform-Augmented GRPO), which generates semantically equivalent transformed variants of each question (via paraphrasing, variable renaming, and format changes) and computes advantages by pooling rewards across the entire group. This pooled computation ensures mixed rewards even when the original question is too easy or too hard, while training on diverse phrasings promotes multiple solution strategies. We provide theoretical justification showing that TA-GRPO reduces zero-gradient probability and improves generalization via reduced train-test distribution shift. Experiments on mathematical reasoning benchmarks show consistent Pass@k improvements, with gains up to 9.84 points on competition math (AMC12, AIME24) and 5.05 points on out-of-distribution scientific reasoning (GPQA-Diamond).

Shubham Rohal, Dong Yoon Lee, Phuc Nguyen et al.

Infrastructure-based sensing systems, like Wi-Fi, thermal, vibration-based approaches, provide continuous and unobtrusive indoor human monitoring services. They are often deployed statically for long-term continuous monitoring, which often leads to inefficient sensing/inflexible deployment due to human mobility or high maintenance/data volume for dense deployments. In contrast, autonomous and human carried mobile devices can better adapt to human mobility. However, their physical presence (e.g., drones or robots) may induce observer effects, while their operation often imposes additional burdens, such as wearing (e.g., wearables) and frequent charging. We present GEM, a hybrid scheme that introduces the mobility to infrastructure-based sensing. GEM integrates a matrix of gears into everyday surfaces (e.g., floors, walls) to turn them into "public transportation" for moving infrastructure sensors around. We design and fabricate a 3 x 3 gear matrix prototype that can effectively move sensors from one location to another. We further validate the scalability of the design through simulation of up to 64 x 64 gear matrix with concurrent sensors.

Phuc Nguyen, Benjamin Zelditch, Joyce Chen et al.

We present BanditLP, a scalable multi-stakeholder contextual bandit framework that unifies neural Thompson Sampling for learning objective-specific outcomes with a large-scale linear program for constrained action selection at serving time. The methodology is application-agnostic, compatible with arbitrary neural architectures, and deployable at web scale, with an LP solver capable of handling billions of variables. Experiments on public benchmarks and synthetic data show consistent gains over strong baselines. We apply this approach in LinkedIn's email marketing system and demonstrate business win, illustrating the value of integrated exploration and constrained optimization in production.

Francis Engelmann, Ayca Takmaz, Jonas Schult et al.

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.

Abdul Aziz, Nhat Pham, Neel Vora et al.

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.

Phuc Nguyen, Minh Luu, Anh Tran et al.

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.

Peijie Qiu, Satrajit Chakrabarty, Phuc Nguyen et al.

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.

Miao Li, Phuc Nguyen, Christopher Tam et al.

Tabular data dominates data science but poses challenges for generative models, especially when the data is limited or sensitive. We present a novel approach to generating synthetic tabular data based on the principle of maximum entropy -- MaxEnt -- called GEM-T, for ``generative entropy maximization for tables.'' GEM-T directly captures nth-order interactions -- pairwise, third-order, etc. -- among columns of training data. In extensive testing, GEM-T matches or exceeds deep neural network approaches previously regarded as state-of-the-art in 23 of 34 publicly available datasets representing diverse subject domains (68\%). Notably, GEM-T involves orders-of-magnitude fewer trainable parameters, demonstrating that much of the information in real-world data resides in low-dimensional, potentially human-interpretable correlations, provided that the input data is appropriately transformed first. Furthermore, MaxEnt better handles heterogeneous data types (continuous vs. discrete vs. categorical), lack of local structure, and other features of tabular data. GEM-T represents a promising direction for light-weight high-performance generative models for structured data.

Eduardo Calle-Ortiz, Hui Guan, Deepak Ganesan et al.

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.

Qi Li, Shaheer U. Saeed, Yuliang Huang et al.

Trackerless freehand ultrasound reconstruction aims to reconstruct 3D volumes from sequences of 2D ultrasound images without relying on external tracking systems. By eliminating the need for optical or electromagnetic trackers, this approach offers a low-cost, portable, and widely deployable alternative to more expensive volumetric ultrasound imaging systems, particularly valuable in resource-constrained clinical settings. However, predicting long-distance transformations and handling complex probe trajectories remain challenging. The TUS-REC2024 Challenge establishes the first benchmark for trackerless 3D freehand ultrasound reconstruction by providing a large publicly available dataset, along with a baseline model and a rigorous evaluation framework. By the submission deadline, the Challenge had attracted 43 registered teams, of which 6 teams submitted 21 valid dockerized solutions. The submitted methods span a wide range of approaches, including the state space model, the recurrent model, the registration-driven volume refinement, the attention mechanism, and the physics-informed model. This paper provides a comprehensive background introduction and literature review in the field, presents an overview of the challenge design and dataset, and offers a comparative analysis of submitted methods across multiple evaluation metrics. These analyses highlight both the progress and the current limitations of state-of-the-art approaches in this domain and provide insights for future research directions. All data and code are publicly available to facilitate ongoing development and reproducibility. As a live and evolving benchmark, it is designed to be continuously iterated and improved. The Challenge was held at MICCAI 2024 and is organised again at MICCAI 2025, reflecting its sustained commitment to advancing this field.

Changshuai Wei, Phuc Nguyen, Benjamin Zelditch et al.

The standard A/B testing approaches are mostly based on t-test in large scale industry applications. These standard approaches however suffers from low statistical power in business settings, due to nature of small sample-size or non-Gaussian distribution or return-on-investment (ROI) consideration. In this paper, we propose several approaches to addresses these challenges: (i) regression adjustment, generalized estimating equation, Man-Whitney U and Zero-Trimmed U that addresses each of these issues separately, and (ii) a novel doubly robust generalized U that handles ROI consideration, distribution robustness and small samples in one framework. We provide theoretical results on asymptotic normality and efficiency bounds, together with insights on the efficiency gain from theoretical analysis. We further conduct comprehensive simulation studies and apply the methods to multiple real A/B tests.

Phuc Nguyen, Miao Li, Alexandra Morgan et al.

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.

Phuc Nguyen, Natthawut Kertkeidkachorn, Ryutaro Ichise et al.

In the Open Data era, a large number of table resources have been made available on the Web and data portals. However, it is difficult to directly utilize such data due to the ambiguity of entities, name variations, heterogeneous schema, missing, or incomplete metadata. To address these issues, we propose a novel approach, namely TabEAno, to semantically annotate table rows toward knowledge graph entities. Specifically, we introduce a "two-cells" lookup strategy bases on the assumption that there is an existing logical relation occurring in the knowledge graph between the two closed cells in the same row of the table. Despite the simplicity of the approach, TabEAno outperforms the state of the art approaches in the two standard datasets e.g, T2D, Limaye with, and in the large-scale Wikipedia tables dataset.

Phuc Nguyen, Natthawut Kertkeidkachorn, Ryutaro Ichise et al.

This paper presents the design of our system, namely MTab, for Semantic Web Challenge on Tabular Data to Knowledge Graph Matching (SemTab 2019). MTab combines the voting algorithm and the probability models to solve critical problems of the matching tasks. Results on SemTab 2019 show that MTab obtains promising performance for the three matching tasks.

Phuc Nguyen, Deva Ramanan, Charless Fowlkes

Much recent work on visual recognition aims to scale up learning to massive, noisily-annotated datasets. We address the problem of scaling- up the evaluation of such models to large-scale datasets with noisy labels. Current protocols for doing so require a human user to either vet (re-annotate) a small fraction of the test set and ignore the rest, or else correct errors in annotation as they are found through manual inspection of results. In this work, we re-formulate the problem as one of active testing, and examine strategies for efficiently querying a user so as to obtain an accu- rate performance estimate with minimal vetting. We demonstrate the effectiveness of our proposed active testing framework on estimating two performance metrics, Precision@K and mean Average Precision, for two popular computer vision tasks, multi-label classification and instance segmentation. We further show that our approach is able to save significant human annotation effort and is more robust than alternative evaluation protocols.

Phuc Nguyen, Khai Nguyen, Ryutaro Ichise et al.

Semantic labeling for numerical values is a task of assigning semantic labels to unknown numerical attributes. The semantic labels could be numerical properties in ontologies, instances in knowledge bases, or labeled data that are manually annotated by domain experts. In this paper, we refer to semantic labeling as a retrieval setting where the label of an unknown attribute is assigned by the label of the most relevant attribute in labeled data. One of the greatest challenges is that an unknown attribute rarely has the same set of values with the similar one in the labeled data. To overcome the issue, statistical interpretation of value distribution is taken into account. However, the existing studies assume a specific form of distribution. It is not appropriate in particular to apply open data where there is no knowledge of data in advance. To address these problems, we propose a neural numerical embedding model (EmbNum) to learn useful representation vectors for numerical attributes without prior assumptions on the distribution of data. Then, the "semantic similarities" between the attributes are measured on these representation vectors by the Euclidean distance. Our empirical experiments on City Data and Open Data show that EmbNum significantly outperforms state-of-the-art methods for the task of numerical attribute semantic labeling regarding effectiveness and efficiency.

Phuc Nguyen, Ting Liu, Gautam Prasad et al.

We propose a weakly supervised temporal action localization algorithm on untrimmed videos using convolutional neural networks. Our algorithm learns from video-level class labels and predicts temporal intervals of human actions with no requirement of temporal localization annotations. We design our network to identify a sparse subset of key segments associated with target actions in a video using an attention module and fuse the key segments through adaptive temporal pooling. Our loss function is comprised of two terms that minimize the video-level action classification error and enforce the sparsity of the segment selection. At inference time, we extract and score temporal proposals using temporal class activations and class-agnostic attentions to estimate the time intervals that correspond to target actions. The proposed algorithm attains state-of-the-art results on the THUMOS14 dataset and outstanding performance on ActivityNet1.3 even with its weak supervision.