Publications (66)
Benchmarking Large Language Models for Multi-Language Software Vulnerability Detection
Ting Zhang, Chengran Yang, Yindu Su +8
Recent advancements in generative AI have led to the widespread adoption of large language models (LLMs) in software engineering, addressing numerous long-standing challenges. Howe…
Radio-frequency methods for Majorana-based quantum devices: fast charge sensing and phase diagram mapping
Davydas Razmadze, Deividas Sabonis, Filip K. Malinowski +9
Radio-frequency (RF) reflectometry is implemented in hybrid semiconductor-superconductor nanowire systems designed to probe Majorana zero modes. Two approaches are presented. In th…
Compressive Features in Offline Reinforcement Learning for Recommender Systems
Hung Nguyen, Minh Nguyen, Long Pham +1
In this paper, we develop a recommender system for a game that suggests potential items to players based on their interactive behaviors to maximize revenue for the game provider. O…
Long-Term 3D Point Tracking By Cost Volume Fusion
Hung Nguyen, Chanho Kim, Rigved Naukarkar +1
Long-term point tracking is essential to understand non-rigid motion in the physical world better. Deep learning approaches have recently been incorporated into long-term point tra…
Towards Bi-Directional Communication in Human-Swarm Teaming: A Survey
Aya Hussein, Leo Ghignone, Tung Nguyen +4
Swarm systems consist of large numbers of robots that collaborate autonomously. With an appropriate level of human control, swarm systems could be applied in a variety of contexts…
Scalable Edge Blocking Algorithms for Defending Active Directory Style Attack Graphs
Mingyu Guo, Max Ward, Aneta Neumann +2
Active Directory (AD) is the default security management system for Windows domain networks. An AD environment naturally describes an attack graph where nodes represent computers/a…
Social Optimum Equilibrium Selection for Distributed Multi-Agent Optimization
Duong Nguyen, Langford White, Hung Nguyen
We study the open question of how players learn to play a social optimum pure-strategy Nash equilibrium (PSNE) through repeated interactions in general-sum coordination games. A so…
Towards Implementing Energy-aware Data-driven Intelligence for Smart Health Applications on Mobile Platforms
G. Dumindu Samaraweera, Hung Nguyen, Hadi Zanddizari +2
Recent breakthrough technological progressions of powerful mobile computing resources such as low-cost mobile GPUs along with cutting-edge, open-source software architectures have…
Evaluating Marijuana-Related Tweets On Twitter
Anh Nguyen, Quang Hoang, Hung Nguyen +2
This paper studies marijuana-related tweets in social network Twitter. We collected more than 300,000 marijuana related tweets during November 2016 in our study. Our text-mining ba…
Optimizing Cyber Response Time on Temporal Active Directory Networks Using Decoys
Huy Q. Ngo, Mingyu Guo, Hung Nguyen
Microsoft Active Directory (AD) is the default security management system for Window domain network. We study the problem of placing decoys in AD network to detect potential attack…
AutoGAN-based Dimension Reduction for Privacy Preservation
Hung Nguyen, Di Zhuang, Pei-Yuan Wu +1
Protecting sensitive information against data exploiting attacks is an emerging research area in data mining. Over the past, several different methods have been introduced to prote…
Stop-band Energy Constraint for Orthogonal Tunable Wavelet Units in Convolutional Neural Networks for Computer Vision problems
An D. Le, Hung Nguyen, Sungbal Seo +2
This work introduces a stop-band energy constraint for filters in orthogonal tunable wavelet units with a lattice structure, aimed at improving image classification and anomaly det…
DWTGS: Rethinking Frequency Regularization for Sparse-view 3D Gaussian Splatting
Hung Nguyen, Runfa Li, An Le +1
Sparse-view 3D Gaussian Splatting (3DGS) presents significant challenges in reconstructing high-quality novel views, as it often overfits to the widely-varying high-frequency (HF)…
Satisfaction and Regret in Stackelberg Games
Langford White, Duong Nguyen, Hung Nguyen
This paper introduces the new concept of (follower) satisfaction in Stackelberg games and compares the standard Stackelberg game with its satisfaction version. Simulation results a…
Limited Query Graph Connectivity Test
Mingyu Guo, Jialiang Li, Aneta Neumann +2
We propose a combinatorial optimisation model called Limited Query Graph Connectivity Test. We consider a graph whose edges have two possible states (On/Off). The edges' states are…
Style Transfer for 2D Talking Head Animation
Trong-Thang Pham, Nhat Le, Tuong Do +4
Audio-driven talking head animation is a challenging research topic with many real-world applications. Recent works have focused on creating photo-realistic 2D animation, while lea…
DeepFloat: Resource-Efficient Dynamic Management of Vehicular Floating Content
Gaetano Manzo, Sebastian Otalora, Marco Ajmone Marsan +3
Opportunistic communications are expected to playa crucial role in enabling context-aware vehicular services. A widely investigated opportunistic communication paradigm for storing…
Complementary Ensemble Learning
Hung Nguyen, Morris Chang
To achieve high performance of a machine learning (ML) task, a deep learning-based model must implicitly capture the entire distribution from data. Thus, it requires a huge amount…
Speech2Grasp: Data-Efficient Transfer of Text-Conditioned Grasp Detection to Speech in Humanoid Robots
Hung Nguyen, Kim Nhat Minh Nguyen, Van Duc Vu +6
The paper presents Speech2Grasp, a method that efficiently adapts a text‑conditioned grasp‑detection model to work directly with spoken commands, improving performance and speed on…
Pure or Unstable: A Generic Dichotomy for Strong Stackelberg Commitments
Kamil Bulinski, Lang White, Hung Nguyen
We study the robustness of the Strong Stackelberg Equilibrium (SSE) in finite leader--follower games when the follower's best-response correspondence is set-valued. While optimisti…
Practical Fixed-Parameter Algorithms for Defending Active Directory Style Attack Graphs
Mingyu Guo, Jialiang Li, Aneta Neumann +2
Active Directory is the default security management system for Windows domain networks. We study the shortest path edge interdiction problem for defending Active Directory style at…
Catch Me if You Can: Effective Honeypot Placement in Dynamic AD Attack Graphs
Huy Quang Ngo, Mingyu Guo, Hung Nguyen
We study a Stackelberg game between an attacker and a defender on large Active Directory (AD) attack graphs where the defender employs a set of honeypots to stop the attacker from…
Gaussian Processes in Power Systems: Techniques, Applications, and Future Works
Bendong Tan, Tong Su, Yu Weng +6
The increasing integration of renewable energy sources (RESs) and distributed energy resources (DERs) has significantly heightened operational complexity and uncertainty in modern…
Trajectory Planning and Control for Differentially Flat Fixed-Wing Aerial Systems
Luca Morando, Sanket A. Salunkhe, Nishanth Bobbili +5
Efficient real-time trajectory planning and control for fixed-wing unmanned aerial vehicles is challenging due to their non-holonomic nature, complex dynamics, and the additional u…
Adaptive Wizard for Removing Cross-Tier Misconfigurations in Active Directory
Huy Q. Ngo, Mingyu Guo, Hung Nguyen
Security vulnerabilities in Windows Active Directory (AD) systems are typically modeled using an attack graph and hardening AD systems involves an iterative workflow: security team…
Space Time Recurrent Memory Network
Hung Nguyen, Chanho Kim, Fuxin Li
Transformers have recently been popular for learning and inference in the spatial-temporal domain. However, their performance relies on storing and applying attention to the featur…
CBR-to-SQL: Rethinking Retrieval-based Text-to-SQL using Case-based Reasoning in the Healthcare Domain
Hung Nguyen, Hans Moen, Pekka Marttinen
Extracting insights from Electronic Health Record (EHR) databases often requires SQL expertise, creating a barrier for clinical decision-making and research. A promising approach i…
DWTNeRF: Boosting Few-shot Neural Radiance Fields via Discrete Wavelet Transform
Hung Nguyen, Blark Runfa Li, Truong Nguyen
Neural Radiance Fields (NeRF) has achieved superior performance in novel view synthesis and 3D scene representation, but its practical applications are hindered by slow convergence…
Heart2Mind: Human-Centered Contestable Psychiatric Disorder Diagnosis System using Wearable ECG Monitors
Hung Nguyen, Alireza Rahimi, Veronica Whitford +4
Psychiatric disorders affect millions globally, yet their diagnosis faces significant challenges in clinical practice due to subjective assessments and accessibility concerns, lead…
Encrypted Observer-based Control for Linear Continuous-Time Systems
Hung Nguyen, Binh Nguyen, Hyung-Gohn Lee +1
This paper is concerned with the stability analysis of encrypted observer-based control for linear continuous-time systems. Since conventional encryption has limited ability to dep…
Cross Project Software Vulnerability Detection via Domain Adaptation and Max-Margin Principle
Van Nguyen, Trung Le, Chakkrit Tantithamthavorn +3
Software vulnerabilities (SVs) have become a common, serious and crucial concern due to the ubiquity of computer software. Many machine learning-based approaches have been proposed…
Dynamic System Identification of Underwater Vehicles Using Multi-Output Gaussian Processes
Wilmer Ariza Ramirez, Jus Kocijan, Zhi Leong +2
Non-parametric system identification with Gaussian Processes for underwater vehicles is explored in this research with the purpose of modelling autonomous underwater vehicle (AUV)…
Gemini: A Family of Highly Capable Multimodal Models
Gemini Team, Rohan Anil, Sebastian Borgeaud +1340
This report introduces a new family of multimodal models, Gemini, that exhibit remarkable capabilities across image, audio, video, and text understanding. The Gemini family consist…
From Coarse to Fine: Learnable Discrete Wavelet Transforms for Efficient 3D Gaussian Splatting
Hung Nguyen, An Le, Runfa Li +1
3D Gaussian Splatting has emerged as a powerful approach in novel view synthesis, delivering rapid training and rendering but at the cost of an ever-growing set of Gaussian primiti…
Story of Two GPUs: Characterizing the Resilience of Hopper H100 and Ampere A100 GPUs
Shengkun Cui, Archit Patke, Hung Nguyen +11
This study characterizes GPU resilience in Delta, a large-scale AI system that consists of 1,056 A100 and H100 GPUs, with over 1,300 petaflops of peak throughput. We used 2.5 years…
Evolving Reinforcement Learning Environment to Minimize Learner's Achievable Reward: An Application on Hardening Active Directory Systems
Diksha Goel, Aneta Neumann, Frank Neumann +2
We study a Stackelberg game between one attacker and one defender in a configurable environment. The defender picks a specific environment configuration. The attacker observes the…
Muse Spark Safety & Preparedness Report
Cristina Menghini, Peter Ney, Hamza Kwisaba +117
Muse Spark is the latest large language model developed by Meta. In this report, we first present evaluations for catastrophic risk domains under Meta's Advanced AI Scaling Framewo…
3D Point World Models: Point Completion Enables More Accurate Dynamics Learning
Skand Peri, Hung Nguyen, Chanho Kim +2
Learning predictive models of the world enables robotic control through planning, potentially allowing robots to improvise solutions on new tasks. However, large video-based dynami…
Tunable Wavelet Unit based Convolutional Neural Network in Optical Coherence Tomography Analysis Enhancement for Classifying Type of Epiretinal Membrane Surgery
An Le, Nehal Mehta, William Freeman +9
In this study, we developed deep learning-based method to classify the type of surgery performed for epiretinal membrane (ERM) removal, either internal limiting membrane (ILM) remo…
Defending Active Directory by Combining Neural Network based Dynamic Program and Evolutionary Diversity Optimisation
Diksha Goel, Max Ward, Aneta Neumann +3
Active Directory (AD) is the default security management system for Windows domain networks. We study a Stackelberg game model between one attacker and one defender on an AD attack…
Acceleration-Based Control of Fixed-Wing UAVs for Guidance Applications
Jixiang Wang, Siyuan Yang, Ziyi Wu +5
Acceleration-commanded guidance laws (e.g., proportional navigation) are attractive for high-level decision making, but their direct deployment on fixed-wing UAVs is challenging be…
Emotion-Aware Classroom Quality Assessment Leveraging IoT-Based Real-Time Student Monitoring
Hai Nguyen, Hieu Dao, Hung Nguyen +2
This study presents high-throughput, real-time multi-agent affective computing framework designed to enhance classroom learning through emotional state monitoring. As large classro…
Synthetic Information towards Maximum Posterior Ratio for deep learning on Imbalanced Data
Hung Nguyen, Morris Chang
This study examines the impact of class-imbalanced data on deep learning models and proposes a technique for data balancing by generating synthetic data for the minority class. Unl…
Apprenticeship Bootstrapping Via Deep Learning with a Safety Net for UAV-UGV Interaction
Hung Nguyen, Vu Tran, Tung Nguyen +5
In apprenticeship learning (AL), agents learn by watching or acquiring human demonstrations on some tasks of interest. However, the lack of human demonstrations in novel tasks wher…
Learnable Multi-level Discrete Wavelet Transforms for 3D Gaussian Splatting Frequency Modulation
Hung Nguyen, An Le, Truong Nguyen
3D Gaussian Splatting (3DGS) has emerged as a powerful approach for novel view synthesis. However, the number of Gaussian primitives often grows substantially during training as fi…
WaveletGaussian: Wavelet-domain Diffusion for Sparse-view 3D Gaussian Object Reconstruction
Hung Nguyen, Runfa Li, An Le +1
3D Gaussian Splatting (3DGS) has become a powerful representation for image-based object reconstruction, yet its performance drops sharply in sparse-view settings. Prior works addr…
Solvability regions of affinely parameterized quadratic equations
Krishnamurthy Dvijotham, Hung Nguyen, Konstantin Turitsyn
Quadratic systems of equations appear in several applications. The results in this paper are motivated by quadratic systems of equations that describe equilibrium behavior of physi…
Context-Aware Orchestration of Energy-Efficient Gossip Learning Schemes
Mina Aghaei Dinani, Adrian Holzer, Hung Nguyen +2
Fully distributed learning schemes such as Gossip Learning (GL) are gaining momentum due to their scalability and effectiveness even in dynamic settings. However, they often imply…
Performance of Distributed File Systems on Cloud Computing Environment: An Evaluation for Small-File Problem
Thanh Duong, Quoc Luu, Hung Nguyen
Various performance characteristics of distributed file systems have been well studied. However, the performance efficiency of distributed file systems on small-file problems with…
Statement-Level Vulnerability Detection: Learning Vulnerability Patterns Through Information Theory and Contrastive Learning
Van Nguyen, Trung Le, Chakkrit Tantithamthavorn +6
Software vulnerabilities are a serious and crucial concern. Typically, in a program or function consisting of hundreds or thousands of source code statements, there are only a few…
Joint Network Coding and Machine Learning for Error-prone Wireless Broadcast
Dong Nguyen, Canh Nguyen, Thuan Duong-Ba +3
Reliable broadcasting data to multiple receivers over lossy wireless channels is challenging due to the heterogeneity of the wireless link conditions. Automatic Repeat-reQuest (ARQ…
AI-accelerated End-to-End Framework for Rapid Professional Upskilling
Tam Nguyen, Hung Nguyen, Robert Ogburn
The paper proposes an AI‑accelerated end‑to‑end framework that streamlines five stages of professional upskilling—from knowledge acquisition to assessment—demonstrated with externa…
Biorthogonal Tunable Wavelet Unit with Lifting Scheme in Convolutional Neural Network
An Le, Hung Nguyen, Sungbal Seo +2
This work introduces a novel biorthogonal tunable wavelet unit constructed using a lifting scheme that relaxes both the orthogonality and equal filter length constraints, providing…
The Generalized Langevin Equation with a power-law memory in a nonlinear potential well
Nathan Glatt-Holtz, David Herzog, Scott McKinley +1
The generalized Langevin equation (GLE) is a stochastic integro-differential equation that has been used to describe the velocity of microparticles in viscoelastic fluids. In this…
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Gheorghe Comanici, Eric Bieber, Mike Schaekermann +3431
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our…
Federated Learning for distribution skewed data using sample weights
Hung Nguyen, Peiyuan Wu, Morris Chang
One of the most challenging issues in federated learning is that the data is often not independent and identically distributed (nonIID). Clients are expected to contribute the same…
Maximal Cliques on Multi-Frame Proposal Graph for Unsupervised Video Object Segmentation
Jialin Yuan, Jay Patravali, Hung Nguyen +2
Unsupervised Video Object Segmentation (UVOS) aims at discovering objects and tracking them through videos. For accurate UVOS, we observe if one can locate precise segment proposal…
SwiftTry: Fast and Consistent Video Virtual Try-On with Diffusion Models
Hung Nguyen, Quang Qui-Vinh Nguyen, Khoi Nguyen +1
Given an input video of a person and a new garment, the objective of this paper is to synthesize a new video where the person is wearing the specified garment while maintaining spa…
Numerical Polynomial Homotopy Continuation Method to Locate All The Power Flow Solutions
Dhagash Mehta, Hung Nguyen, Konstantin Turitsyn
The manuscript addresses the problem of finding all solutions of power flow equations or other similar nonlinear system of algebraic equations. This problem arises naturally in a n…
Taming Treewidth DP with Modulators: A General Booster for Graph Heuristics
Jialiang Li, Aneta Neumann, Frank Neumann +2
Treewidth is a fundamental graph invariant that quantifies how tree-like a given graph is. It is extensively used with dynamic programming to design fixed-parameter tractable algor…
Universal Wavelet Units in 3D Retinal Layer Segmentation
An D. Le, Hung Nguyen, Melanie Tran +6
This paper presents the first study to apply tunable wavelet units (UwUs) for 3D retinal layer segmentation from Optical Coherence Tomography (OCT) volumes. To overcome the limitat…
United We Stand: Decentralized Multi-Agent Planning With Attrition
Nhat Nguyen, Duong Nguyen, Gianluca Rizzo +1
Decentralized planning is a key element of cooperative multi-agent systems for information gathering tasks. However, despite the high frequency of agent failures in realistic large…
Continual Rare-Class Recognition with Emerging Novel Subclasses
Hung Nguyen, Xuejian Wang, Leman Akoglu
Given a labeled dataset that contains a rare (or minority) class of of-interest instances, as well as a large class of instances that are not of interest, how can we learn to recog…
Approximate k-Cover in Hypergraphs: Efficient Algorithms, and Applications
Hung Nguyen, Phuc Thai, My Thai +2
Given a weighted hypergraph , the approximate -cover problem seeks for a size- subset of that has the maximum weighted cover…
Bayesian Rationality in Satisfaction Games
Langford White, Oskar Rynkiewicz, Duong Nguyen +1
We introduce a new paradigm for game theory -- Bayesian satisfaction. This novel approach is a synthesis of the idea of Bayesian rationality introduced by Aumann, and satisfaction…
Defending SDN against packet injection attacks using deep learning
Anh Tuan Phu, Bo Li, Faheem Ullah +4
The (logically) centralised architecture of the software-defined networks makes them an easy target for packet injection attacks. In these attacks, the attacker injects malicious p…