papers

Publications (104)

stat.ML2022

Unified Framework for Spectral Dimensionality Reduction, Maximum Variance Unfolding, and Kernel Learning By Semidefinite Programming: Tutorial and Survey

Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray +1

This is a tutorial and survey paper on unification of spectral dimensionality reduction methods, kernel learning by Semidefinite Programming (SDP), Maximum Variance Unfolding (MVU)…

stat.ML2022

Laplacian-Based Dimensionality Reduction Including Spectral Clustering, Laplacian Eigenmap, Locality Preserving Projection, Graph Embedding, and Diffusion Map: Tutorial and Survey

Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray +1

This is a tutorial and survey paper for nonlinear dimensionality and feature extraction methods which are based on the Laplacian of graph of data. We first introduce adjacency matr…

cs.CL2025

A Comprehensive Survey of Machine Unlearning Techniques for Large Language Models

Jiahui Geng, Qing Li, Herbert Woisetschlaeger +6

This study investigates the machine unlearning techniques within the context of large language models (LLMs), referred to as \textit{LLM unlearning}. LLM unlearning offers a princi…

stat.ML2021

Generative Locally Linear Embedding

Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray +1

Locally Linear Embedding (LLE) is a nonlinear spectral dimensionality reduction and manifold learning method. It has two main steps which are linear reconstruction and linear embed…

cs.LG2014

Embed and Conquer: Scalable Embeddings for Kernel k-Means on MapReduce

Ahmed Elgohary, Ahmed K. Farahat, Mohamed S. Kamel +1

The kernel -means is an effective method for data clustering which extends the commonly-used -means algorithm to work on a similarity matrix over complex data structures. The…

cs.CV2025

ADAM-Dehaze: Adaptive Density-Aware Multi-Stage Dehazing for Improved Object Detection in Foggy Conditions

Fatmah AlHindaassi, Mohammed Talha Alam, Fakhri Karray

Adverse weather conditions, particularly fog, pose a significant challenge to autonomous vehicles, surveillance systems, and other safety-critical applications by severely degradin…

math.OC2020

Distributed Nonlinear Model Predictive Control and Metric Learning for Heterogeneous Vehicle Platooning with Cut-in/Cut-out Maneuvers

Mohammad Hossein Basiri, Benyamin Ghojogh, Nasser L. Azad +3

Vehicle platooning has been shown to be quite fruitful in the transportation industry to enhance fuel economy, road throughput, and driving comfort. Model Predictive Control (MPC)…

cs.AI2018

New Results on Multi-Step Traffic Flow Prediction

Arief Koesdwiady, Fakhri Karray

In its simplest form, the traffic flow prediction problem is restricted to predicting a single time-step into the future. Multi-step traffic flow prediction extends this set-up to…

cs.CV2025

SAUCE: Selective Concept Unlearning in Vision-Language Models with Sparse Autoencoders

Qing Li, Jiahui Geng, Derui Zhu +3

Unlearning methods for vision-language models (VLMs) have primarily adapted techniques from large language models (LLMs), relying on weight updates that demand extensive annotated…

cs.IR2025

FilterLLM: Text-To-Distribution LLM for Billion-Scale Cold-Start Recommendation

Ruochen Liu, Hao Chen, Yuanchen Bei +6

Large Language Model (LLM)-based cold-start recommendation systems continue to face significant computational challenges in billion-scale scenarios, as they follow a "Text-to-Judgm…

cs.LG2023

Clip21: Error Feedback for Gradient Clipping

Sarit Khirirat, Eduard Gorbunov, Samuel Horváth +3

Motivated by the increasing popularity and importance of large-scale training under differential privacy (DP) constraints, we study distributed gradient methods with gradient clipp…

cs.AI2025

Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities

Yuanchen Bei, Weizhi Zhang, Siwen Wang +10

AI agents have experienced a paradigm shift, from early dominance by reinforcement learning (RL) to the rise of agents powered by large language models (LLMs), and now further adva…

cs.LG2020

Acceleration of Large Margin Metric Learning for Nearest Neighbor Classification Using Triplet Mining and Stratified Sampling

Parisa Abdolrahim Poorheravi, Benyamin Ghojogh, Vincent Gaudet +2

Metric learning is one of the techniques in manifold learning with the goal of finding a projection subspace for increasing and decreasing the inter- and intra-class variances, res…

cs.CV2020

Roweisposes, Including Eigenposes, Supervised Eigenposes, and Fisherposes, for 3D Action Recognition

Benyamin Ghojogh, Fakhri Karray, Mark Crowley

Human action recognition is one of the important fields of computer vision and machine learning. Although various methods have been proposed for 3D action recognition, some of whic…

eess.IV2019

Principal Component Analysis Using Structural Similarity Index for Images

Benyamin Ghojogh, Fakhri Karray, Mark Crowley

Despite the advances of deep learning in specific tasks using images, the principled assessment of image fidelity and similarity is still a critical ability to develop. As it has b…

stat.OT2020

Fitting A Mixture Distribution to Data: Tutorial

Benyamin Ghojogh, Aydin Ghojogh, Mark Crowley +1

This paper is a step-by-step tutorial for fitting a mixture distribution to data. It merely assumes the reader has the background of calculus and linear algebra. Other required bac…

cs.CV2026

CAST: Channel-Aware Spatial Transfer Learning with Pseudo-Image Radar for Sign Language Recognition

Md. Shakhoyat Rahman Shujon, Sheikh Md. Galib Mahim, Md. Milon Islam +4

We propose CAST, a dual-stream architecture that utilizes channel-aware spatial transfer learning for isolated sign language recognition addressing the challenges of magnitude-only…

cs.LG2026

Y-Shaped Generative Flows

Arip Asadulaev, Semyon Semenov, Abduragim Shtanchaev +3

Modern continuous-time generative models typically induce \emph{V-shaped} flows: each sample travels independently along a nearly straight trajectory from the prior to the data. Al…

cs.RO2026

KineVLA: Towards Kinematics-Aware Vision-Language-Action Models with Bi-Level Action Decomposition

Gaoge Han, Zhengqing Gao, Ziwen Li +5

In this paper, we introduce a novel kinematics-rich vision-language-action (VLA) task, in which language commands densely encode diverse kinematic attributes (such as direction, tr…

cs.LG2022

On Manifold Hypothesis: Hypersurface Submanifold Embedding Using Osculating Hyperspheres

Benyamin Ghojogh, Fakhri Karray, Mark Crowley

Consider a set of data points in the Euclidean space . This set is called dataset in machine learning and data science. Manifold hypothesis states that the datase…

cs.HC2023

Internet of Things Device Capabilities, Architectures, Protocols, and Smart Applications in Healthcare Domain: A Review

Md. Milon Islam, Sheikh Nooruddin, Fakhri Karray +1

Nowadays, the Internet has spread to practically every country around the world and is having unprecedented effects on people's lives. The Internet of Things (IoT) is getting more…

cs.CR2026

VulnScout-C: A Lightweight Transformer for C Code Vulnerability Detection

Aymen Lassoued, Nacef Mbarek, Bechir Dardouri +3

Vulnerability detection in C programs is a critical challenge in software security. Although large language models (LLMs) achieve strong detection performance, their multi-billion-…

cs.CV2025

FusionEnsemble-Net: An Attention-Based Ensemble of Spatiotemporal Networks for Multimodal Sign Language Recognition

Md. Milon Islam, Md Rezwanul Haque, S M Taslim Uddin Raju +1

Accurate recognition of sign language in healthcare communication poses a significant challenge, requiring frameworks that can accurately interpret complex multimodal gestures. To…

cs.CV2025

MDD-Net: Multimodal Depression Detection through Mutual Transformer

Md Rezwanul Haque, Md. Milon Islam, S M Taslim Uddin Raju +3

Depression is a major mental health condition that severely impacts the emotional and physical well-being of individuals. The simple nature of data collection from social media pla…

cs.LG2020

Theoretical Insights into the Use of Structural Similarity Index In Generative Models and Inferential Autoencoders

Benyamin Ghojogh, Fakhri Karray, Mark Crowley

Generative models and inferential autoencoders mostly make use of norm in their optimization objectives. In order to generate perceptually better images, this short paper…

cs.IR2025

Cold-Start Recommendation towards the Era of Large Language Models (LLMs): A Comprehensive Survey and Roadmap

Weizhi Zhang, Yuanchen Bei, Liangwei Yang +15

Cold-start problem is one of the long-standing challenges in recommender systems, focusing on accurately modeling new or interaction-limited users or items to provide better recomm…

cs.LG2020

Backprojection for Training Feedforward Neural Networks in the Input and Feature Spaces

Benyamin Ghojogh, Fakhri Karray, Mark Crowley

After the tremendous development of neural networks trained by backpropagation, it is a good time to develop other algorithms for training neural networks to gain more insights int…

stat.ML2019

Quantized Fisher Discriminant Analysis

Benyamin Ghojogh, Ali Saheb Pasand, Fakhri Karray +1

This paper proposes a new subspace learning method, named Quantized Fisher Discriminant Analysis (QFDA), which makes use of both machine learning and information theory. There is a…

stat.ML2021

Reproducing Kernel Hilbert Space, Mercer's Theorem, Eigenfunctions, Nyström Method, and Use of Kernels in Machine Learning: Tutorial and Survey

Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray +1

This is a tutorial and survey paper on kernels, kernel methods, and related fields. We start with reviewing the history of kernels in functional analysis and machine learning. Then…

cs.HC2022

Integrating Digital Twin and Advanced Intelligent Technologies to Realize the Metaverse

Moayad Aloqaily, Ouns Bouachir, Fakhri Karray +2

The advances in Artificial Intelligence (AI) have led to technological advancements in a plethora of domains. Healthcare, education, and smart city services are now enriched with A…

eess.SP2022

Human Activity Recognition Using Tools of Convolutional Neural Networks: A State of the Art Review, Data Sets, Challenges and Future Prospects

Md. Milon Islam, Sheikh Nooruddin, Fakhri Karray +1

Human Activity Recognition (HAR) plays a significant role in the everyday life of people because of its ability to learn extensive high-level information about human activity from…

stat.ME2020

Sampling Algorithms, from Survey Sampling to Monte Carlo Methods: Tutorial and Literature Review

Benyamin Ghojogh, Hadi Nekoei, Aydin Ghojogh +2

This paper is a tutorial and literature review on sampling algorithms. We have two main types of sampling in statistics. The first type is survey sampling which draws samples from…

stat.ML2022

Fisher and Kernel Fisher Discriminant Analysis: Tutorial

Benyamin Ghojogh, Fakhri Karray, Mark Crowley

This is a detailed tutorial paper which explains the Fisher discriminant Analysis (FDA) and kernel FDA. We start with projection and reconstruction. Then, one- and multi-dimensiona…

cs.IR2025

VSCBench: Bridging the Gap in Vision-Language Model Safety Calibration

Jiahui Geng, Qing Li, Zongxiong Chen +7

The rapid advancement of vision-language models (VLMs) has brought a lot of attention to their safety alignment. However, existing methods have primarily focused on model undersafe…

cs.LG2019

Feature Selection and Feature Extraction in Pattern Analysis: A Literature Review

Benyamin Ghojogh, Maria N. Samad, Sayema Asif Mashhadi +4

Pattern analysis often requires a pre-processing stage for extracting or selecting features in order to help the classification, prediction, or clustering stage discriminate or rep…

cs.CV2026

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks

Aljalila Aladawi, Mohammed Talha Alam, Fakhri Karray

Machine unlearning for text-to-image diffusion models aims to selectively remove undesirable concepts from pre-trained models without costly retraining. Current unlearning methods…

stat.ML2019

Roweis Discriminant Analysis: A Generalized Subspace Learning Method

Benyamin Ghojogh, Fakhri Karray, Mark Crowley

We present a new method which generalizes subspace learning based on eigenvalue and generalized eigenvalue problems. This method, Roweis Discriminant Analysis (RDA), is named after…

cs.LG2018

SAFE: Spectral Evolution Analysis Feature Extraction for Non-Stationary Time Series Prediction

Arief Koesdwiady, Fakhri Karray

This paper presents a practical approach for detecting non-stationarity in time series prediction. This method is called SAFE and works by monitoring the evolution of the spectral…

cs.CV2024

AstroSpy: On detecting Fake Images in Astronomy via Joint Image-Spectral Representations

Mohammed Talha Alam, Raza Imam, Mohsen Guizani +1

The prevalence of AI-generated imagery has raised concerns about the authenticity of astronomical images, especially with advanced text-to-image models like Stable Diffusion produc…

stat.ML2022

Spectral, Probabilistic, and Deep Metric Learning: Tutorial and Survey

Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray +1

This is a tutorial and survey paper on metric learning. Algorithms are divided into spectral, probabilistic, and deep metric learning. We first start with the definition of distanc…

cs.CV2025

AdaptPrompt: Parameter-Efficient Adaptation of VLMs for Generalizable Deepfake Detection

Yichen Jiang, Mohammed Talha Alam, Sohail Ahmed Khan +2

Recent advances in image generation have led to the widespread availability of highly realistic synthetic media, increasing the difficulty of reliable deepfake detection. A key cha…

cs.LG2025

Expert or not? assessing data quality in offline reinforcement learning

Arip Asadulaev, Fakhri Karray, Martin Takac

Offline reinforcement learning (RL) learns exclusively from static datasets, without further interaction with the environment. In practice, such datasets vary widely in quality, of…

cs.LG2026

In-Context Learning Operates as Concept Subspace Learning

Wei Tang, Xinyan Jiang, Fakhri Karray +1

Regression and Bayesian accounts of in-context learning (ICL) explain how demonstrations can induce predictors, while mechanistic analyses often identify compact activation directi…

cs.LG2026

Convex Compositional Reasoning Models

Meir Roketlishvili, Semyon Semenov, Maksim Bobrin +7

Compositional energy-based models can generalize to larger combinatorial reasoning problems by reusing a learned factor energy across many local constraints. In our paper, we show…

cs.CL2025

REMONI: An Autonomous System Integrating Wearables and Multimodal Large Language Models for Enhanced Remote Health Monitoring

Thanh Cong Ho, Farah Kharrat, Abderrazek Abid +1

With the widespread adoption of wearable devices in our daily lives, the demand and appeal for remote patient monitoring have significantly increased. Most research in this field h…

stat.ML2022

Factor Analysis, Probabilistic Principal Component Analysis, Variational Inference, and Variational Autoencoder: Tutorial and Survey

Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray +1

This is a tutorial and survey paper on factor analysis, probabilistic Principal Component Analysis (PCA), variational inference, and Variational Autoencoder (VAE). These methods, w…

stat.ML2022

Theoretical Connection between Locally Linear Embedding, Factor Analysis, and Probabilistic PCA

Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray +1

Locally Linear Embedding (LLE) is a nonlinear spectral dimensionality reduction and manifold learning method. It has two main steps which are linear reconstruction and linear embed…

stat.ML2020

Weighted Fisher Discriminant Analysis in the Input and Feature Spaces

Benyamin Ghojogh, Milad Sikaroudi, H. R. Tizhoosh +2

Fisher Discriminant Analysis (FDA) is a subspace learning method which minimizes and maximizes the intra- and inter-class scatters of data, respectively. Although, in FDA, all the…

cs.LG2020

Anomaly Detection and Prototype Selection Using Polyhedron Curvature

Benyamin Ghojogh, Fakhri Karray, Mark Crowley

We propose a novel approach to anomaly detection called Curvature Anomaly Detection (CAD) and Kernel CAD based on the idea of polyhedron curvature. Using the nearest neighbors for…

cs.CL2025

HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMs

Qing Li, Jiahui Geng, Zongxiong Chen +5

In recent years, large language models (LLMs) have made remarkable advancements, yet hallucination, where models produce inaccurate or non-factual statements, remains a significant…

cs.CL2024

Reference-free Hallucination Detection for Large Vision-Language Models

Qing Li, Jiahui Geng, Chenyang Lyu +3

Large vision-language models (LVLMs) have made significant progress in recent years. While LVLMs exhibit excellent ability in language understanding, question answering, and conver…

cs.LG2026

Zero-Shot Off-Policy Learning

Arip Asadulaev, Maksim Bobrin, Salem Lahlou +3

Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents significant challenges, primarily due to t…

cs.LG2021

Generative Adversarial Networks and Adversarial Autoencoders: Tutorial and Survey

Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray +1

This is a tutorial and survey paper on Generative Adversarial Network (GAN), adversarial autoencoders, and their variants. We start with explaining adversarial learning and the van…

stat.AP2019

Addressing the Mystery of Population Decline of the Rose-Crested Blue Pipit in a Nature Preserve using Data Visualization

Benyamin Ghojogh, Mark Crowley, Fakhri Karray

Two main methods for exploring patterns in data are data visualization and machine learning. The former relies on humans for investigating the patterns while the latter relies on m…

cs.CV2015

Driver distraction detection and recognition using RGB-D sensor

Céline Craye, Fakhri Karray

Driver inattention assessment has become a very active field in intelligent transportation systems. Based on active sensor Kinect and computer vision tools, we have built an effici…

cs.LG2025

Bridging Brain with Foundation Models through Self-Supervised Learning

Hamdi Altaheri, Fakhri Karray, Md. Milon Islam +2

Foundation models (FMs), powered by self-supervised learning (SSL), have redefined the capabilities of artificial intelligence, demonstrating exceptional performance in domains lik…

cs.DC2022

Internet of Behavior (IoB) and Explainable AI Systems for Influencing IoT Behavior

Haya Elayan, Moayad Aloqaily, Fakhri Karray +1

Pandemics and natural disasters over the years have changed the behavior of people, which has had a tremendous impact on all life aspects. With the technologies available in each e…

cs.CV2023

GenLayNeRF: Generalizable Layered Representations with 3D Model Alignment for Multi-Human View Synthesis

Youssef Abdelkareem, Shady Shehata, Fakhri Karray

Novel view synthesis (NVS) of multi-human scenes imposes challenges due to the complex inter-human occlusions. Layered representations handle the complexities by dividing the scene…

eess.IV2026

NL-MambaXCT: Self-Supervised Nested-Learning Mamba for Nomex Honeycomb X-ray CT Defect Classification

Ghaleb Aldoboni, Lobna Nassar, Fakhri Karray +1

X-ray computed tomography (XCT) is widely used for non-destructive testing of Nomex honeycomb structures in aerospace manufacturing, but industrial inspection still relies heavily…

stat.ML2019

Locally Linear Image Structural Embedding for Image Structure Manifold Learning

Benyamin Ghojogh, Fakhri Karray, Mark Crowley

Most of existing manifold learning methods rely on Mean Squared Error (MSE) or norm. However, for the problem of image quality assessment, these are not promising measure.…

cs.AI2024

Advances in Preference-based Reinforcement Learning: A Review

Youssef Abdelkareem, Shady Shehata, Fakhri Karray

Reinforcement Learning (RL) algorithms suffer from the dependency on accurately engineered reward functions to properly guide the learning agents to do the required tasks. Preferen…

cs.CV2024

FLARE up your data: Diffusion-based Augmentation Method in Astronomical Imaging

Mohammed Talha Alam, Raza Imam, Mohsen Guizani +1

The intersection of Astronomy and AI encounters significant challenges related to issues such as noisy backgrounds, lower resolution (LR), and the intricate process of filtering an…

cs.CV2022

Offline versus Online Triplet Mining based on Extreme Distances of Histopathology Patches

Milad Sikaroudi, Benyamin Ghojogh, Amir Safarpoor +3

We analyze the effect of offline and online triplet mining for colorectal cancer (CRC) histopathology dataset containing 100,000 patches. We consider the extreme, i.e., farthest an…

cs.CV2025

UrbanGS: Semantic-Guided Gaussian Splatting for Urban Scene Reconstruction

Ziwen Li, Jiaxin Huang, Runnan Chen +5

Reconstructing urban scenes is challenging due to their complex geometries and the presence of potentially dynamic objects. 3D Gaussian Splatting (3DGS)-based methods have shown st…

stat.ML2023

Eigenvalue and Generalized Eigenvalue Problems: Tutorial

Benyamin Ghojogh, Fakhri Karray, Mark Crowley

This paper is a tutorial for eigenvalue and generalized eigenvalue problems. We first introduce eigenvalue problem, eigen-decomposition (spectral decomposition), and generalized ei…

eess.IV2020

A Review on Deep Learning Techniques for the Diagnosis of Novel Coronavirus (COVID-19)

Md. Milon Islam, Fakhri Karray, Reda Alhajj +1

Novel coronavirus (COVID-19) outbreak, has raised a calamitous situation all over the world and has become one of the most acute and severe ailments in the past hundred years. The…

cs.AI2021

On the Philosophical, Cognitive and Mathematical Foundations of Symbiotic Autonomous Systems (SAS)

Yingxu Wang, Fakhri Karray, Sam Kwong +12

Symbiotic Autonomous Systems (SAS) are advanced intelligent and cognitive systems exhibiting autonomous collective intelligence enabled by coherent symbiosis of human-machine inter…

stat.ML2021

Quantile-Quantile Embedding for Distribution Transformation and Manifold Embedding with Ability to Choose the Embedding Distribution

Benyamin Ghojogh, Fakhri Karray, Mark Crowley

We propose a new embedding method, named Quantile-Quantile Embedding (QQE), for distribution transformation and manifold embedding with the ability to choose the embedding distribu…

math.OC2021

KKT Conditions, First-Order and Second-Order Optimization, and Distributed Optimization: Tutorial and Survey

Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray +1

This is a tutorial and survey paper on Karush-Kuhn-Tucker (KKT) conditions, first-order and second-order numerical optimization, and distributed optimization. After a brief review…

cs.CV2016

Semi-supervised Dictionary Learning Based on Hilbert-Schmidt Independence Criterion

Mehrdad J. Gangeh, Safaa M. A. Bedawi, Ali Ghodsi +1

In this paper, a novel semi-supervised dictionary learning and sparse representation (SS-DLSR) is proposed. The proposed method benefits from the supervisory information by learnin…

cs.SD2023

Arabic Dysarthric Speech Recognition Using Adversarial and Signal-Based Augmentation

Massa Baali, Ibrahim Almakky, Shady Shehata +1

Despite major advancements in Automatic Speech Recognition (ASR), the state-of-the-art ASR systems struggle to deal with impaired speech even with high-resource languages. In Arabi…

cs.SE2026

CodeMMR: Bridging Natural Language, Code, and Image for Unified Retrieval

Jiahui Geng, Qing Li, Fengyu Cai +1

Code search, framed as information retrieval (IR), underpins modern software engineering and increasingly powers retrieval-augmented generation (RAG), improving code discovery, reu…

cs.LG2020

Fisher Discriminant Triplet and Contrastive Losses for Training Siamese Networks

Benyamin Ghojogh, Milad Sikaroudi, Sobhan Shafiei +3

Siamese neural network is a very powerful architecture for both feature extraction and metric learning. It usually consists of several networks that share weights. The Siamese conc…

cs.CV2025

PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention

Ziwen Li, Xin Wang, Hanlue Zhang +8

The Vision-Language-Action (VLA) models have demonstrated remarkable performance on embodied tasks and shown promising potential for real-world applications. However, current VLAs…

cs.LG2025

Internal Activation Revision: Safeguarding Vision Language Models Without Parameter Update

Qing Li, Jiahui Geng, Zongxiong Chen +3

Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large l…

cs.CV2025

A Signer-Invariant Conformer and Multi-Scale Fusion Transformer for Continuous Sign Language Recognition

Md Rezwanul Haque, Md. Milon Islam, S M Taslim Uddin Raju +1

Continuous Sign Language Recognition (CSLR) faces multiple challenges, including significant inter-signer variability and poor generalization to novel sentence structures. Traditio…

cs.CV2025

MMFformer: Multimodal Fusion Transformer Network for Depression Detection

Md Rezwanul Haque, Md. Milon Islam, S M Taslim Uddin Raju +3

Depression is a serious mental health illness that significantly affects an individual's well-being and quality of life, making early detection crucial for adequate care and treatm…

eess.IV2022

UncertaintyFuseNet: Robust Uncertainty-aware Hierarchical Feature Fusion Model with Ensemble Monte Carlo Dropout for COVID-19 Detection

Moloud Abdar, Soorena Salari, Sina Qahremani +7

The COVID-19 (Coronavirus disease 2019) pandemic has become a major global threat to human health and well-being. Thus, the development of computer-aided detection (CAD) systems th…

cs.LG2021

Deep Learning Approaches for Forecasting Strawberry Yields and Prices Using Satellite Images and Station-Based Soil Parameters

Mohita Chaudhary, Mohamed Sadok Gastli, Lobna Nassar +1

Computational tools for forecasting yields and prices for fresh produce have been based on traditional machine learning approaches or time series modelling. We propose here an alte…

cs.LG2024

Enhance Hyperbolic Representation Learning via Second-order Pooling

Kun Song, Ruben Solozabal, Li hao +5

Hyperbolic representation learning is well known for its ability to capture hierarchical information. However, the distance between samples from different levels of hierarchical cl…

stat.ML2022

Stochastic Neighbor Embedding with Gaussian and Student-t Distributions: Tutorial and Survey

Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray +1

Stochastic Neighbor Embedding (SNE) is a manifold learning and dimensionality reduction method with a probabilistic approach. In SNE, every point is consider to be the neighbor of…

stat.ME2021

Sufficient Dimension Reduction for High-Dimensional Regression and Low-Dimensional Embedding: Tutorial and Survey

Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray +1

This is a tutorial and survey paper on various methods for Sufficient Dimension Reduction (SDR). We cover these methods with both statistical high-dimensional regression perspectiv…

cs.LG2026

Dual Advantage Fields

Alexey Zemtsov, Maxim Bobrin, Alexander Nikulin +5

Offline goal-conditioned reinforcement learning requires both long-horizon reachability estimates and local action comparisons. Dual goal representations provide value fields that…

cs.HC2021

Uniform Manifold Approximation and Projection (UMAP) and its Variants: Tutorial and Survey

Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray +1

Uniform Manifold Approximation and Projection (UMAP) is one of the state-of-the-art methods for dimensionality reduction and data visualization. This is a tutorial and survey paper…

cs.CL2025

Vision Language Models for Dynamic Human Activity Recognition in Healthcare Settings

Abderrazek Abid, Thanh-Cong Ho, Fakhri Karray

As generative AI continues to evolve, Vision Language Models (VLMs) have emerged as promising tools in various healthcare applications. One area that remains relatively underexplor…

stat.ML2020

Multidimensional Scaling, Sammon Mapping, and Isomap: Tutorial and Survey

Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray +1

Multidimensional Scaling (MDS) is one of the first fundamental manifold learning methods. It can be categorized into several methods, i.e., classical MDS, kernel classical MDS, met…

cs.SE2026

CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrieval

Jiahui Geng, Fengyu Cai, Shaobo Cui +8

Code retrieval is essential in modern software development, as it boosts code reuse and accelerates debugging. However, current benchmarks primarily emphasize functional relevance…

cs.CL2026

Latent Reasoning in TRMs is Secretly a Policy Improvement Operator

Arip Asadulaev, Rayan Banerjee, Fakhri Karray +1

Recently, small models with latent recursion have obtained promising results on complex reasoning tasks. These results are typically explained by the theory that such recursion inc…

cs.CY2021

Smart Healthcare in the Age of AI: Recent Advances, Challenges, and Future Prospects

Mahmoud Nasr, MD. Milon Islam, Shady Shehata +2

The significant increase in the number of individuals with chronic ailments (including the elderly and disabled) has dictated an urgent need for an innovative model for healthcare…

cs.AI2026

Towards Robust Reinforcement Learning for Small-Scale Language Model Agents

Md Rezwanul Haque, Md. Milon Islam, Fakhri Karray

The alignment of Small Language Models (SLMs) in the 70--500M parameter range using reinforcement learning is often considered unstable, though the underlying failure mechanisms ha…

stat.ML2021

Johnson-Lindenstrauss Lemma, Linear and Nonlinear Random Projections, Random Fourier Features, and Random Kitchen Sinks: Tutorial and Survey

Benyamin Ghojogh, Ali Ghodsi, Fakhri Karray +1

This is a tutorial and survey paper on the Johnson-Lindenstrauss (JL) lemma and linear and nonlinear random projections. We start with linear random projection and then justify its…

eess.IV2021

Magnification Generalization for Histopathology Image Embedding

Milad Sikaroudi, Benyamin Ghojogh, Fakhri Karray +2

Histopathology image embedding is an active research area in computer vision. Most of the embedding models exclusively concentrate on a specific magnification level. However, a use…

cs.IR2024

Large Language Model Simulator for Cold-Start Recommendation

Feiran Huang, Yuanchen Bei, Zhenghang Yang +6

Recommending cold items remains a significant challenge in billion-scale online recommendation systems. While warm items benefit from historical user behaviors, cold items rely sol…

cs.CV2023

Multi-Plane Neural Radiance Fields for Novel View Synthesis

Youssef Abdelkareem, Shady Shehata, Fakhri Karray

Novel view synthesis is a long-standing problem that revolves around rendering frames of scenes from novel camera viewpoints. Volumetric approaches provide a solution for modeling…

cs.CL2026

PAST-TIDE: Prototype-Anchored Statement Tuning with Topic-Invariant Normalization for Stance Detection

Md. Shakhoyat Rahman Shujon, MD Jahid Hasan Jim, Md. Milon Islam +2

We introduce PAST-TIDE, our stance detection system addressing both subtasks of the StanceNakba Shared Task at NakbaNLP@LREC-COLING 2026. The main idea is statement tuning. We rede…

math.OC2021

Vector Transport Free Riemannian LBFGS for Optimization on Symmetric Positive Definite Matrix Manifolds

Reza Godaz, Benyamin Ghojogh, Reshad Hosseini +3

This work concentrates on optimization on Riemannian manifolds. The Limited-memory Broyden-Fletcher-Goldfarb-Shanno (LBFGS) algorithm is a commonly used quasi-Newton method for num…

cs.LG2023

Harris Hawks Feature Selection in Distributed Machine Learning for Secure IoT Environments

Neveen Hijazi, Moayad Aloqaily, Bassem Ouni +2

The development of the Internet of Things (IoT) has dramatically expanded our daily lives, playing a pivotal role in the enablement of smart cities, healthcare, and buildings. Emer…

stat.ML2020

Batch-Incremental Triplet Sampling for Training Triplet Networks Using Bayesian Updating Theorem

Milad Sikaroudi, Benyamin Ghojogh, Fakhri Karray +2

Variants of Triplet networks are robust entities for learning a discriminative embedding subspace. There exist different triplet mining approaches for selecting the most suitable t…

cs.CV2025

GNN-ViTCap: GNN-Enhanced Multiple Instance Learning with Vision Transformers for Whole Slide Image Classification and Captioning

S M Taslim Uddin Raju, Md. Milon Islam, Md Rezwanul Haque +2

Microscopic assessment of histopathology images is vital for accurate cancer diagnosis and treatment. Whole Slide Image (WSI) classification and captioning have become crucial task…

cs.CV2025

FaceAnonyMixer: Cancelable Faces via Identity Consistent Latent Space Mixing

Mohammed Talha Alam, Fahad Shamshad, Fakhri Karray +1

Advancements in face recognition (FR) technologies have amplified privacy concerns, necessitating methods that protect identity while maintaining recognition utility. Existing face…