arXiv subjects

Muhammad Usman

Publications and source records attributed to Muhammad Usman.

At least 55 records · Page 3Linked to original sources

arXiv2026

Quantum Error Correction and Detection for Quantum Machine Learning

At the intersection of quantum computing and machine learning, quantum machine learning (QML) is poised to revolutionize artificial intelligence. However, the vulnerability of the current generation of quantum computers to noise and computational error poses a significant barrier to this vision. Whilst quantum error correction (QEC) offers a promising solution for almost any type of hardware noise, its application requires millions of qubits to encode even a simple logical algorithm, rendering it impractical in the near term. In this chapter, we examine strategies for integrating QEC and quantum error detection (QED) into QML under realistic resource constraints. We first quantify the resource demands of fully error-corrected QML and propose a partial QEC approach that reduces overhead while enabling error correction. We then demonstrate the application of a simple QED method, evaluating its impact on QML performance and highlighting challenges we have yet to overcome before we achieve fully fault-tolerant QML.

quant-ph↗

arXiv2025

Dual-Encoder Transformer-Based Multimodal Learning for Ischemic Stroke Lesion Segmentation Using Diffusion MRI

Accurate segmentation of ischemic stroke lesions from diffusion magnetic resonance imaging (MRI) is essential for clinical decision-making and outcome assessment. Diffusion-Weighted Imaging (DWI) and Apparent Diffusion Coefficient (ADC) scans provide complementary information on acute and sub-acute ischemic changes; however, automated lesion delineation remains challenging due to variability in lesion appearance. In this work, we study ischemic stroke lesion segmentation using multimodal diffusion MRI from the ISLES 2022 dataset. Several state-of-the-art convolutional and transformer-based architectures, including U-Net variants, Swin-UNet, and TransUNet, are benchmarked. Based on performance, a dual-encoder TransUNet architecture is proposed to learn modality-specific representations from DWI and ADC inputs. To incorporate spatial context, adjacent slice information is integrated using a three-slice input configuration. All models are trained under a unified framework and evaluated using the Dice Similarity Coefficient (DSC). Results show that transformer-based models outperform convolutional baselines, and the proposed dual-encoder TransUNet achieves the best performance, reaching a Dice score of 85.4% on the test set. The proposed framework offers a robust solution for automated ischemic stroke lesion segmentation from diffusion MRI.

eess.IV↗

arXiv2025

PENDULUM: A Benchmark for Assessing Sycophancy in Multimodal Large Language Models

Sycophancy, an excessive tendency of AI models to agree with user input at the expense of factual accuracy or in contradiction of visual evidence, poses a critical and underexplored challenge for multimodal large language models (MLLMs). While prior studies have examined this behavior in text-only settings of large language models, existing research on visual or multimodal counterparts remains limited in scope and depth of analysis. To address this gap, we introduce a comprehensive evaluation benchmark, \textit{PENDULUM}, comprising approximately 2,000 human-curated Visual Question Answering pairs specifically designed to elicit sycophantic responses. The benchmark spans six distinct image domains of varying complexity, enabling a systematic investigation of how image type and inherent challenges influence sycophantic tendencies. Through extensive evaluation of state-of-the-art MLLMs. we observe substantial variability in model robustness and a pronounced susceptibility to sycophantic and hallucinatory behavior. Furthermore, we propose novel metrics to quantify sycophancy in visual reasoning, offering deeper insights into its manifestations across different multimodal contexts. Our findings highlight the urgent need for developing sycophancy-resilient architectures and training strategies to enhance factual consistency and reliability in future MLLMs. Our proposed dataset with MLLMs response are available at https://github.com/ashikiut/pendulum/.

cs.AI↗

arXiv2025

Complex Swin Transformer for Accelerating Enhanced SMWI Reconstruction

Susceptibility Map Weighted Imaging (SMWI) is an advanced magnetic resonance imaging technique used to detect nigral hyperintensity in Parkinsons disease. However, full resolution SMWI acquisition is limited by long scan times. Efficient reconstruction methods are therefore required to generate high quality SMWI from reduced k space data while preserving diagnostic relevance. In this work, we propose a complex valued Swin Transformer based network for super resolution reconstruction of multi echo MRI data. The proposed method reconstructs high quality SMWI images from low resolution k space inputs. Experimental results demonstrate that the method achieves a structural similarity index of 0.9116 and a mean squared error of 0.076 when reconstructing SMWI from 256 by 256 k space data, while maintaining critical diagnostic features. This approach enables high quality SMWI reconstruction from reduced k space sampling, leading to shorter scan times without compromising diagnostic detail. The proposed method has the potential to improve the clinical applicability of SMWI for Parkinsons disease and support faster and more efficient neuroimaging workflows.

eess.IV↗

arXiv2025

DGTEN: A Robust Deep Gaussian based Graph Neural Network for Dynamic Trust Evaluation with Uncertainty-Quantification Support

Dynamic trust evaluation in large, rapidly evolving graphs demands models that capture changing relationships, express calibrated confidence, and resist adversarial manipulation. DGTEN (Deep Gaussian-Based Trust Evaluation Network) introduces a unified graph-based framework that does all three by combining uncertainty-aware message passing, expressive temporal modeling, and built-in defenses against trust-targeted attacks. It represents nodes and edges as Gaussian distributions so that both semantic signals and epistemic uncertainty propagate through the graph neural network, enabling risk-aware trust decisions rather than overconfident guesses. To track how trust evolves, it layers hybrid absolute-Gaussian-hourglass positional encoding with Kolmogorov-Arnold network-based unbiased multi-head attention, then applies an ordinary differential equation-based residual learning module to jointly model abrupt shifts and smooth trends. Robust adaptive ensemble coefficient analysis prunes or down-weights suspicious interactions using complementary cosine and Jaccard similarity, curbing reputation laundering, sabotage, and on-off attacks. On two signed Bitcoin trust networks, DGTEN delivers standout gains where it matters most: in single-timeslot prediction on Bitcoin-OTC, it improves MCC by +12.34% over the best dynamic baseline; in the cold-start scenario on Bitcoin-Alpha, it achieves a +25.00% MCC improvement, the largest across all tasks and datasets; while under adversarial on-off attacks, it surpasses the baseline by up to +10.23% MCC. These results endorse the unified DGTEN framework.

cs.LG↗

arXiv2025

Anatomy-Guided Representation Learning Using a Transformer-Based Network for Thyroid Nodule Segmentation in Ultrasound Images

Accurate thyroid nodule segmentation in ultrasound images is critical for diagnosis and treatment planning. However, ambiguous boundaries between nodules and surrounding tissues, size variations, and the scarcity of annotated ultrasound data pose significant challenges for automated segmentation. Existing deep learning models struggle to incorporate contextual information from the thyroid gland and generalize effectively across diverse cases. To address these challenges, we propose SSMT-Net, a Semi-Supervised Multi-Task Transformer-based Network that leverages unlabeled data to enhance Transformer-centric encoder feature extraction capability in an initial unsupervised phase. In the supervised phase, the model jointly optimizes nodule segmentation, gland segmentation, and nodule size estimation, integrating both local and global contextual features. Extensive evaluations on the TN3K and DDTI datasets demonstrate that SSMT-Net outperforms state-of-the-art methods, with higher accuracy and robustness, indicating its potential for real-world clinical applications.

cs.CV↗

arXiv2025

Integrating Uncertainty Quantification into Computational Fluid Dynamics Models of Coronary Arteries Under Steady Flow

Computational models are continuously integrated in the clinical space, where they support clinicians in disease diagnosis, prognosis, and prevention strategies. While assisting in clinical space, these computational models frequently use deterministic approaches, where the inherent (aleatoric) variability of input parameters is ignored. This questions the credibility and often hinders the clinical adoption of these computational models. Therefore, in this study, we introduced uncertainty quantification in the computational fluid dynamics models of the left main coronary artery to analyze the influence of input hemodynamics parameters on wall shear stress (WSS). UncertainSCI was used, where an emulator was built using polynomial chaos expansion between the input parameters and the output quantity of interest, and the output sensitivities and statistics were directly extracted from the emulator. The uncertainty-informed framework was first applied to an analytical solution of the Navier-Stokes equation (Poiseuille flow) and then to a patient-specific model of the left main coronary artery. Different input hemodynamics parameters are considered, such as pressure, viscosity, density, velocity, and radius, whereas wall shear stress was considered as our output quantity of interest. The results suggest that velocity dominated the variability in WSS in the analytical model (~79%), whereas viscosity dominated in the patient-specific model (~59%). The results further suggest that out of all the Sobol indices interactions, unary interactions were the most dominant ones, contributing ~93.2% and ~99% for the analytical and patient-specific model, respectively. This study will enhance confidence in computational models, facilitating their adoption in the clinical space to improve decision-making for coronary artery disease diagnosis, prognosis, and therapeutic strategies.

physics.med-ph↗

arXiv2025

Effect of shape on void growth: A coupled Extended Finite Element Method (XFEM) and Discrete Dislocation Plasticity (DDP) study

Voids are one of the many material defects present at the microscopic length scale. They are primarily responsible for the formation of cracks and hence contribute to ductile fracture. Circular voids tend to deform into elliptical voids just before their coalescence to form cracks. The principle aim of this study is to investigate the effect of void shape on the micro-mechanism of void growth by using Discrete Dislocation Plasticity simulations. For voided crystals, conventional DDP produces a continuous slip step throughout the material even if a dislocation escapes from a non-convex domain. To overcome this issue, the Extended Finite Element Method (XFEM) is used here to incorporate the displacement discontinuity. Different aspect ratios of elliptical voids are considered under uniaxial and biaxial deformation boundary conditions. The results suggest that voids having the largest surface area tend to have maximum growth rate as compared to void with lower surface area, i.e. "larger is faster". Under biaxial loading, a higher magnitude of strain hardening, and void growth rate are observed as compared to uniaxial loading. The results also suggest that the orientation of slip planes as well as voids, affect the overall plastic behavior of the voided-ductile material. Furthermore, circular void tends to induce minimum growth rate but have the maximum strain hardening effect as compared to other void shapes under both loading conditions. The results of this study provide a deeper understanding of ductile fracture with applications in manufacturing industry, aerospace industry and in the design of nano/micro-electromechanical devices i.e. NEMS/MEMS.

physics.app-ph↗

arXiv2025

Almost fault-tolerant quantum machine learning with drastic overhead reduction

Errors in the current generation of quantum processors pose a significant challenge towards practical-scale implementations of quantum machine learning (QML) as they lead to trainability issues arising from noise-induced barren plateaus, as well as performance degradations due to the noise accumulation in deep circuits even when QML models are free from barren plateaus. Quantum error correction (QEC) protocols are being developed to overcome hardware noise, but their extremely high spacetime overheads, mainly due to magic state distillation, make them infeasible for near-term practical implementation. This work proposes the idea of partial quantum error correction (QEC) for quantum machine learning (QML) models and identifies a sweet spot where distillations are omitted to significantly reduce overhead. By assuming error-corrected two-qubit Controlled-$Z$s (Clifford operations), we demonstrate that the QML models remain trainable even when single-qubit gates are subjected to $\approx0.2\%$ depolarizing noise, corresponding to a gate error rate of $\approx0.13\%$ under randomized benchmarking. Further analysis based on various noise models, such as phase-damping and thermal-dissipation channels at low temperature, indicates that the QML models are trainable independent of the mean angle of over-rotation, or can even be improved by thermal damping that purifies a quantum state away from depolarizations. While it may take several years to build quantum processors capable of fully fault-tolerant QML, our work proposes a resource-efficient solution for trainable and high-accuracy QML implementations in noisy environments.

quant-ph↗

arXiv2025

Adversarially Robust Quantum Transfer Learning

Quantum machine learning (QML) has emerged as a promising area of research for enhancing the performance of classical machine learning systems by leveraging quantum computational principles. However, practical deployment of QML remains limited due to current hardware constraints such as limited number of qubits and quantum noise. This chapter introduces a hybrid quantum-classical architecture that combines the advantages of quantum computing with transfer learning techniques to address high-resolution image classification. Specifically, we propose a Quantum Transfer Learning (QTL) model that integrates classical convolutional feature extraction with quantum variational circuits. Through extensive simulations on diverse datasets including Ants \& Bees, CIFAR-10, and Road Sign Detection, we demonstrate that QTL achieves superior classification performance compared to both conventional and quantum models trained without transfer learning. Additionally, we also investigate the model's vulnerability to adversarial attacks and demonstrate that incorporating adversarial training significantly boosts the robustness of QTL, enhancing its potential for deployment in security sensitive applications.

quant-ph↗

arXiv2025

Bird Eye-View to Street-View: A Survey

In recent years, street view imagery has grown to become one of the most important sources of geospatial data collection and urban analytics, which facilitates generating meaningful insights and assisting in decision-making. Synthesizing a street-view image from its corresponding satellite image is a challenging task due to the significant differences in appearance and viewpoint between the two domains. In this study, we screened 20 recent research papers to provide a thorough review of the state-of-the-art of how street-view images are synthesized from their corresponding satellite counterparts. The main findings are: (i) novel deep learning techniques are required for synthesizing more realistic and accurate street-view images; (ii) more datasets need to be collected for public usage; and (iii) more specific evaluation metrics need to be investigated for evaluating the generated images appropriately. We conclude that, due to applying outdated deep learning techniques, the recent literature failed to generate detailed and diverse street-view images.

cs.CV↗

arXiv2025

From Satellite to Street: A Hybrid Framework Integrating Stable Diffusion and PanoGAN for Consistent Cross-View Synthesis

Street view imagery has become an essential source for geospatial data collection and urban analytics, enabling the extraction of valuable insights that support informed decision-making. However, synthesizing street-view images from corresponding satellite imagery presents significant challenges due to substantial differences in appearance and viewing perspective between these two domains. This paper presents a hybrid framework that integrates diffusion-based models and conditional generative adversarial networks to generate geographically consistent street-view images from satellite imagery. Our approach uses a multi-stage training strategy that incorporates Stable Diffusion as the core component within a dual-branch architecture. To enhance the framework's capabilities, we integrate a conditional Generative Adversarial Network (GAN) that enables the generation of geographically consistent panoramic street views. Furthermore, we implement a fusion strategy that leverages the strengths of both models to create robust representations, thereby improving the geometric consistency and visual quality of the generated street-view images. The proposed framework is evaluated on the challenging Cross-View USA (CVUSA) dataset, a standard benchmark for cross-view image synthesis. Experimental results demonstrate that our hybrid approach outperforms diffusion-only methods across multiple evaluation metrics and achieves competitive performance compared to state-of-the-art GAN-based methods. The framework successfully generates realistic and geometrically consistent street-view images while preserving fine-grained local details, including street markings, secondary roads, and atmospheric elements such as clouds.

cs.CV↗

arXiv2025

Automatizing the search for mass resonances using BumpNet

Physics Beyond the Standard Model (BSM) has yet to be observed at the Large Hadron Collider (LHC), motivating the development of model-agnostic, machine learning-based strategies to probe more regions of the phase space. As many final states have not yet been examined for mass resonances, an accelerated approach to bump-hunting is desirable. BumpNet is a neural network trained to map smoothly falling invariant-mass histogram data to statistical significance values. It provides a unique, automatized approach to mass resonance searches with the capacity to scan hundreds of final states reliably and efficiently.

hep-ph↗

arXiv2025

Cardiverse: Harnessing LLMs for Novel Card Game Prototyping

The prototyping of computer games, particularly card games, requires extensive human effort in creative ideation and gameplay evaluation. Recent advances in Large Language Models (LLMs) offer opportunities to automate and streamline these processes. However, it remains challenging for LLMs to design novel game mechanics beyond existing databases, generate consistent gameplay environments, and develop scalable gameplay AI for large-scale evaluations. This paper addresses these challenges by introducing a comprehensive automated card game prototyping framework. The approach highlights a graph-based indexing method for generating novel game variations, an LLM-driven system for consistent game code generation validated by gameplay records, and a gameplay AI constructing method that uses an ensemble of LLM-generated heuristic functions optimized through self-play. These contributions aim to accelerate card game prototyping, reduce human labor, and lower barriers to entry for game developers. For code repo visit this http URL https://github.com/danruili/Cardiverse

cs.CL↗

arXiv2025

Crosstalk Attacks and Defence in a Shared Quantum Computing Environment

Quantum computing has the potential to provide solutions to problems that are intractable on classical computers, but the accuracy of the current generation of quantum computers suffer from the impact of noise or errors such as leakage, crosstalk, dephasing, and amplitude damping among others. As the access to quantum computers is almost exclusively in a shared environment through cloud-based services, it is possible that an adversary can exploit crosstalk noise to disrupt quantum computations on nearby qubits, even carefully designing quantum circuits to purposely lead to wrong answers. In this paper, we analyze the extent and characteristics of crosstalk noise through tomography conducted on IBM Quantum computers, leading to an enhanced crosstalk simulation model. Our results indicate that crosstalk noise is a significant source of errors on IBM quantum hardware, making crosstalk based attack a viable threat to quantum computing in a shared environment. Based on our crosstalk simulator benchmarked against IBM hardware, we assess the impact of crosstalk attacks and develop strategies for mitigating crosstalk effects. Through a systematic set of simulations, we assess the effectiveness of three crosstalk attack mitigation strategies, namely circuit separation, qubit allocation optimization via reinforcement learning, and the use of spectator qubits, and show that they all overcome crosstalk attacks with varying degrees of success and help to secure quantum computing in a shared platform.

quant-ph↗

arXiv2025

A graph-theoretic approach to chaos and complexity in quantum systems

There has recently been considerable interest in studying quantum systems via dynamical Lie algebras (DLAs) -- Lie algebras generated by the terms which appear in the Hamiltonian of the system. However, there are some important properties that are revealed only at a finer level of granularity than the DLA. In this work we explore, via the commutator graph, average notions of scrambling, chaos and complexity over ensembles of systems with DLAs that possess a basis consisting of Pauli strings. Unlike DLAs, commutator graphs are sensitive to short-time dynamics, and therefore constitute a finer probe to various characteristics of the corresponding ensemble. We link graph-theoretic properties of the commutator graph to the out-of-time-order correlator (OTOC), the frame potential, the frustration graph of the Hamiltonian of the system, and the Krylov complexity of operators evolving under the dynamics. For example, we reduce the calculation of average OTOCs to a counting problem on the graph; separately, we connect the Krylov complexity of an operator to the module structure of the adjoint action of the DLA on the space of operators in which it resides, and prove that its average over the ensemble is lower bounded by the average shortest path length between the initial operator and the other operators in the commutator graph.

quant-ph↗

arXiv2025

Time-adaptive single-shot crosstalk detector on superconducting quantum computer

Quantum crosstalk which stems from unwanted interference of quantum operations with nearby qubits is a major source of noise or errors in a quantum processor. In the context of shared quantum computing, it is challenging to mitigate the crosstalk effect between quantum computations being simultaneously run by multiple users since the exact spatio-temporal gate distributions are not apparent due to privacy concerns. It is therefore important to develop techniques for accurate detection and mitigation of crosstalk to enable high-fidelity quantum computing. Assuming prior knowledge of crosstalk parameters, we propose a time-adaptive detection method leveraging spectator qubits and multiple quantum coherence to amplify crosstalk-induced perturbations. We demonstrate its utility in detecting random sparsely distributed crosstalk within a time window. Our work evaluates its performance in two scenarios: simulation using an artificial noise model with gate-induced crosstalk and always-on idlings channels; and the simulation using noise sampled from an IBM quantum computer parametrised by the reduced HSA error model. The presented results show our method's efficacy hinges on the dominance of single-qubit coherent noise across channels, and the impact of angle mismatching is suppressed as spectator qubits increase. From simulation using real-device noise parameters, our strategy outperforms the previous constant-frequency detection method of Harper et. al. [arXiv: 2402.02753 (2024)] in the detection success rate, achieving an average detection success probability of $0.852\pm 0.022$ (equally scaled noise channels) and $0.933\pm0.024$ (asymmetrically scaled noise channels) from 1 to 7 crosstalk counts.

quant-ph↗

arXiv2025

RBF-FD Method for Some Dispersive Wave Equations and Their Eventual Periodicity

In this paper, we approximate the solution and also discuss the periodic behavior termed as eventual periodicity of solutions of (IBVPs) for some dispersive wave equations on a bounded domain corresponding to periodic forcing. The constructed numerical scheme is based on radial kernels and local in nature like finite difference method. The temporal variable is executed through RK4 scheme. Due to the local nature and sparse differentiation matrices our numerical scheme efficiently recovers the solution. The results achieved are validated and examined with other methods accessible in the literature.

math.NA↗