Tung Nguyen
YOU?
Author Swipe
View article: XTRA: Cross-Lingual Topic Modeling with Topic and Representation Alignments
XTRA: Cross-Lingual Topic Modeling with Topic and Representation Alignments Open
Cross-lingual topic modeling aims to uncover shared semantic themes across languages. Several methods have been proposed to address this problem, leveraging both traditional and neural approaches. While previous methods have achieved some …
View article: Trees and near-linear stable sets
Trees and near-linear stable sets Open
When H is a forest, the Gyárfás-Sumner conjecture implies that every graph G with no induced subgraph isomorphic to H and with bounded clique number has a stable set of linear size. We cannot prove that, but we prove that every such graph …
View article: Line-width and path-width
Line-width and path-width Open
For finite graphs, path-width is an interesting and useful concept, but if we extend it to infinite graphs in the most obvious way (by making the indexing path infinite), it does not work nicely. The simplest extension that works nicely is…
View article: Asymptotic structure. II. Path-width and additive quasi-isometry
Asymptotic structure. II. Path-width and additive quasi-isometry Open
We show that if a graph $G$ admits a quasi-isometry $ϕ$ to a graph $H$ of bounded path-width, then we can assign a non-negative integer length to each edge of $H$, such that the same function $ϕ$ is a quasi-isometry to this weighted versio…
View article: Asymptotic structure. VI. Distant paths across a disc
Asymptotic structure. VI. Distant paths across a disc Open
Menger's theorem says that, for $k\ge0$, if $S, T$ are sets of vertices in a graph $G$, then either there are $k + 1$ vertex-disjoint paths between $S$ and $T$, or there is a set X of at most $k$ vertices such that every $S$-$T$ path passe…
View article: Three-dimensional changes of the mandibular arch after total arch distalization in skeletal Class III malocclusion
Three-dimensional changes of the mandibular arch after total arch distalization in skeletal Class III malocclusion Open
Objectives To assess three-dimensional (3D) changes in tooth position, arch dimensions, and gingival levels after mandibular total arch distalization in skeletal Class III malocclusion. Materials and Methods Skeletal Class III patients tre…
View article: Iceberg: Enhancing HLS Modeling with Synthetic Data
Iceberg: Enhancing HLS Modeling with Synthetic Data Open
Deep learning-based prediction models for High-Level Synthesis (HLS) of hardware designs often struggle to generalize. In this paper, we study how to close the generalizability gap of these models through pretraining on synthetic data and …
View article: Validation of YOLOv8 algorithm in detecting colon polyps in endoscopy videos
Validation of YOLOv8 algorithm in detecting colon polyps in endoscopy videos Open
View article: The impact of foreign direct investment (FDI) attraction on economic development in Vietnam - the mediating role of environmental sustainability and social inequality
The impact of foreign direct investment (FDI) attraction on economic development in Vietnam - the mediating role of environmental sustainability and social inequality Open
Attracting foreign direct investment (FDI) is considered one of the important solutions, contributing to the economic growth and development of Vietnam in recent years. This study aims to test the impact relationship of attracting foreign …
View article: The radius of metric regularity at infinity
The radius of metric regularity at infinity Open
This paper, in the setting at infinity, presents some relationships between the modulus of metric regularity and the radius of (strong) metric regularity that gives a measure of the extent to which a set-valued mapping can be perturbed bef…
View article: Humanity's Last Exam
Humanity's Last Exam Open
Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, lim…
View article: CEO Characteristics and Corporate Emission Releases
CEO Characteristics and Corporate Emission Releases Open
View article: GloCOM: A Short Text Neural Topic Model via Global Clustering Context
GloCOM: A Short Text Neural Topic Model via Global Clustering Context Open
View article: DART: Dynamic Topic Modeling with Decompositional Forecasting and Context-Aware Global Alignment
DART: Dynamic Topic Modeling with Decompositional Forecasting and Context-Aware Global Alignment Open
View article: XTRA: Cross-Lingual Topic Modeling with Topic and Representation Alignments
XTRA: Cross-Lingual Topic Modeling with Topic and Representation Alignments Open
View article: Application of Outlier Detection Methods in GNSS Time Series Analysis
Application of Outlier Detection Methods in GNSS Time Series Analysis Open
In the study of determining vertical displacements of the Earth's crust, GNSS is the technology that enables the highest accuracy in displacement measurement. Moreover, with GNSS time series data, it is possible to identify patterns of dis…
View article: MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants
MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants Open
Recent advancements in mixed-modal generative have opened new avenues for developing unified biomedical assistants capable of analyzing biomedical images, answering complex questions about them, and generating multimodal patient reports. H…
View article: GloCOM: A Short Text Neural Topic Model via Global Clustering Context
GloCOM: A Short Text Neural Topic Model via Global Clustering Context Open
Uncovering hidden topics from short texts is challenging for traditional and neural models due to data sparsity, which limits word co-occurrence patterns, and label sparsity, stemming from incomplete reconstruction targets. Although data a…
View article: CEO age and corporate environmental policies
CEO age and corporate environmental policies Open
This study examines the link between CEO age and firm environmental performance. Building on the upper echelons theory, we predict that a firm is more environmentally friendly if CEOs are younger. Using hand-collected data of a total 12,51…
View article: NeuroMax: Enhancing Neural Topic Modeling via Maximizing Mutual Information and Group Topic Regularization
NeuroMax: Enhancing Neural Topic Modeling via Maximizing Mutual Information and Group Topic Regularization Open
Recent advances in neural topic models have concentrated on two primary directions: the integration of the inference network (encoder) with a pre-trained language model (PLM) and the modeling of the relationship between words and topics in…
View article: Tracking Software Security Topics
Tracking Software Security Topics Open
Software security incidents occur everyday and thousands of software security reports are announced each month. Thus, it is difficult for software security researchers, engineers, and other stakeholders to follow software security topics o…
View article: Defect Prediction with Content-based Features
Defect Prediction with Content-based Features Open
Traditional defect prediction approaches often use metrics that measure the complexity of the design or implementing code of a software system, such as the number of lines of code in a source file. In this paper, we explore a different app…
View article: A novel approach for APT attack detection based on an advanced computing
A novel approach for APT attack detection based on an advanced computing Open
View article: Subdivisions and near-linear stable sets
Subdivisions and near-linear stable sets Open
We prove that for every complete graph $K_t$, all graphs $G$ with no induced subgraph isomorphic to a subdivision of $K_t$ have a stable subset of size at least $|G|/{\rm polylog}|G|$. This is close to best possible, because for $t\ge 7$, …
View article: ClimDetect: A Benchmark Dataset for Climate Change Detection and Attribution
ClimDetect: A Benchmark Dataset for Climate Change Detection and Attribution Open
Detecting and attributing temperature increases driven by climate change is crucial for understanding global warming and informing adaptation strategies. However, distinguishing human-induced climate signals from natural variability remain…
View article: Prediction of Underground Mine’s Surface Subsidence using a Recursive Multi-Step Forecasting Model with an Artificial Neural Network
Prediction of Underground Mine’s Surface Subsidence using a Recursive Multi-Step Forecasting Model with an Artificial Neural Network Open
The subsidence of the surface due to mining activities is a significant issue in mining areas. Therefore, predicting surface subsidence is a necessary task to ensure safety and production efficiency. This article applied an Artificial Neur…
View article: LICO: Large Language Models for In-Context Molecular Optimization
LICO: Large Language Models for In-Context Molecular Optimization Open
Optimizing black-box functions is a fundamental problem in science and engineering. To solve this problem, many approaches learn a surrogate function that estimates the underlying objective from limited historical evaluations. Large Langua…
View article: Probing the Decision Boundaries of In-context Learning in Large Language Models
Probing the Decision Boundaries of In-context Learning in Large Language Models Open
In-context learning is a key paradigm in large language models (LLMs) that enables them to generalize to new tasks and domains by simply prompting these models with a few exemplars without explicit parameter updates. Many attempts have bee…
View article: Development of a Smart Wearable Device for Fall and Slip Detection and Warning for the Elderly People
Development of a Smart Wearable Device for Fall and Slip Detection and Warning for the Elderly People Open
In the elderly, due to the degeneration of the muscles along with visual impairment, mobility becomes more difficult than in other ages. Upon moving, the elderly can be susceptible to several factors such as slips or obstacles which can ca…
View article: Rank-Preference Consistency as the Appropriate Metric for Recommender Systems
Rank-Preference Consistency as the Appropriate Metric for Recommender Systems Open
In this paper we argue that conventional unitary-invariant measures of recommender system (RS) performance based on measuring differences between predicted ratings and actual user ratings fail to assess fundamental RS properties. More spec…