arXiv subjects

Abdur Rehman

Publications and source records attributed to Abdur Rehman.

At least 19 recordsLinked to original sources

arXiv2026

Low Light Image Enhancement Challenge at NTIRE 2026

This paper presents a comprehensive review of the NTIRE 2026 Low Light Image Enhancement Challenge, highlighting the proposed solutions and final results. The objective of this challenge is to identify effective networks capable of producing clearer and visually compelling images in diverse and challenging conditions by learning representative visual cues with the purpose of restoring information loss due to low-contrast and noisy images. A total of 195 participants registered for the first track and 153 for the second track of the competition, and 22 teams ultimately submitted valid entries. This paper thoroughly evaluates the state-of-the-art advances in (joint denoising and) low-light image enhancement, showcasing the significant progress in the field, while leveraging samples of our novel dataset.

cs.CV↗

arXiv2026

Decoder-Free Distillation for Quantized Image Restoration

Quantization-Aware Training (QAT), combined with Knowledge Distillation (KD), holds immense promise for compressing models for edge deployment. However, joint optimization for precision-sensitive image restoration (IR) to recover visual quality from degraded images remains largely underexplored. Directly adapting QAT-KD to low-level vision reveals three critical bottlenecks: teacher-student capacity mismatch, spatial error amplification during decoder distillation, and an optimization "tug-of-war" between reconstruction and distillation losses caused by quantization noise. To tackle these, we introduce Quantization-aware Distilled Restoration (QDR), a framework for edge-deployed IR. QDR eliminates capacity mismatch via FP32 self-distillation and prevents error amplification through Decoder-Free Distillation (DFD), which corrects quantization errors strictly at the network bottleneck. To stabilize the optimization tug-of-war, we propose a Learnable Magnitude Reweighting (LMR) that dynamically balances competing gradients. Finally, we design an Edge-Friendly Model (EFM) featuring a lightweight Learnable Degradation Gating (LDG) to dynamically modulate spatial degradation localization. Extensive experiments across four IR tasks demonstrate that our Int8 model recovers 96.5% of FP32 performance, achieves 442 frames per second (FPS) on an NVIDIA Jetson Orin, and boosts downstream object detection by 16.3 mAP

cs.CV↗

arXiv2025

Illuminating Darkness: Learning to Enhance Low-light Images In-the-Wild

Single-shot low-light image enhancement (SLLIE) remains challenging due to the limited availability of diverse, real-world paired datasets. To bridge this gap, we introduce the Low-Light Smartphone Dataset (LSD), a large-scale, high-resolution (4K+) dataset collected in the wild across a wide range of challenging lighting conditions (0.1 to 200 lux). LSD contains 6,425 precisely aligned low and normal-light image pairs, selected from over 8,000 dynamic indoor and outdoor scenes through multi-frame acquisition and expert evaluation. To evaluate generalization and aesthetic quality, we collect 2,117 unpaired low-light images from previously unseen devices. To fully exploit LSD, we propose TFFormer, a hybrid model that encodes luminance and chrominance (LC) separately to reduce color-structure entanglement. We further propose a cross-attention-driven joint decoder for context-aware fusion of LC representations, along with LC refinement and LC-guided supervision to significantly enhance perceptual fidelity and structural consistency. TFFormer achieves state-of-the-art results on LSD (+2.45 dB PSNR) and substantially improves downstream vision tasks, such as low-light object detection (+6.80 mAP on ExDark).

cs.CV↗

arXiv2025

Degradation-Aware All-in-One Image Restoration via Latent Prior Encoding

Real-world images often suffer from spatially diverse degradations such as haze, rain, snow, and low-light, significantly impacting visual quality and downstream vision tasks. Existing all-in-one restoration (AIR) approaches either depend on external text prompts or embed hand-crafted architectural priors (e.g., frequency heuristics); both impose discrete, brittle assumptions that weaken generalization to unseen or mixed degradations. To address this limitation, we propose to reframe AIR as learned latent prior inference, where degradation-aware representations are automatically inferred from the input without explicit task cues. Based on latent priors, we formulate AIR as a structured reasoning paradigm: (1) which features to route (adaptive feature selection), (2) where to restore (spatial localization), and (3) what to restore (degradation semantics). We design a lightweight decoding module that efficiently leverages these latent encoded cues for spatially-adaptive restoration. Extensive experiments across six common degradation tasks, five compound settings, and previously unseen degradations demonstrate that our method outperforms state-of-the-art (SOTA) approaches, achieving an average PSNR improvement of 1.68 dB while being three times more efficient.

cs.CV↗

arXiv2025

Propulsion of a flexible foil in a wavy flow: resonance, antiresonance, and destructive self-interference

Swimming and flying animals demonstrate remarkable adaptations to diverse flow conditions in their environments. In this study, we aim to advance the fundamental understanding of the interaction between flexible bodies and heterogeneous flow conditions. We develop a linear inviscid model of an elastically mounted foil that passively pitches in response to a prescribed heaving motion and an incoming flow that consists of a traveling wave disturbance superposed on a uniform flow. In addition to the well-known resonant response, the wavy flow induces an antiresonant response for non-dimensional phase velocities near unity due to the emergence of non-circulatory forces that oppose circulatory forces. We also find that the wavy flow destructively interferes with itself, effectively rendering the foil a low-pass filter. The net result is that the waviness of the flow always improves thrust and efficiency when the wavy flow is of a different frequency than the prescribed heaving motion. Such a simple statement cannot be made when the wavy flow and heaving motion have the same frequency. Depending on the wavenumber and relative phase, the two may work in concert or in opposition, but they do open the possibility of simultaneous propulsion and net energy extraction from the flow, which, according to our model, is impossible in a uniform flow.

physics.flu-dyn↗

arXiv2025

Punching Above Precision: Small Quantized Model Distillation with Learnable Regularizer

Quantization-aware training (QAT) combined with knowledge distillation (KD) is a promising strategy for compressing Artificial Intelligence (AI) models for deployment on resource-constrained hardware. However, existing QAT-KD methods often struggle to balance task-specific (TS) and distillation losses due to heterogeneous gradient magnitudes, especially under low-bit quantization. We propose Game of Regularizer (GoR), a novel learnable regularization method that adaptively balances TS and KD objectives using only two trainable parameters for dynamic loss weighting. GoR reduces conflict between supervision signals, improves convergence, and boosts the performance of small quantized models (SQMs). Experiments on image classification, object detection (OD), and large language model (LLM) compression show that GoR consistently outperforms state-of-the-art QAT-KD methods. On low-power edge devices, it delivers faster inference while maintaining full-precision accuracy. We also introduce QAT-EKD-GoR, an ensemble distillation framework that uses multiple heterogeneous teacher models. Under optimal conditions, the proposed EKD-GoR can outperform full-precision models, providing a robust solution for real-world deployment.

cs.CV↗

arXiv2025

Enhanced Urdu Intent Detection with Large Language Models and Prototype-Informed Predictive Pipelines

Multifarious intent detection predictors are developed for different languages, including English, Chinese and French, however, the field remains underdeveloped for Urdu, the 10th most spoken language. In the realm of well-known languages, intent detection predictors utilize the strategy of few-shot learning and prediction of unseen classes based on the model training on seen classes. However, Urdu language lacks few-shot strategy based intent detection predictors and traditional predictors are focused on prediction of the same classes which models have seen in the train set. To empower Urdu language specific intent detection, this introduces a unique contrastive learning approach that leverages unlabeled Urdu data to re-train pre-trained language models. This re-training empowers LLMs representation learning for the downstream intent detection task. Finally, it reaps the combined potential of pre-trained LLMs and the prototype-informed attention mechanism to create a comprehensive end-to-end LLMPIA intent detection pipeline. Under the paradigm of proposed predictive pipeline, it explores the potential of 6 distinct language models and 13 distinct similarity computation methods. The proposed framework is evaluated on 2 public benchmark datasets, namely ATIS encompassing 5836 samples and Web Queries having 8519 samples. Across ATIS dataset under 4-way 1 shot and 4-way 5 shot experimental settings LLMPIA achieved 83.28% and 98.25% F1-Score and on Web Queries dataset produced 76.23% and 84.42% F1-Score, respectively. In an additional case study on the Web Queries dataset under same classes train and test set settings, LLMPIA outperformed state-of-the-art predictor by 53.55% F1-Score.

cs.CL↗

arXiv2025

The Tenth NTIRE 2025 Image Denoising Challenge Report

This paper presents an overview of the NTIRE 2025 Image Denoising Challenge (σ = 50), highlighting the proposed methodologies and corresponding results. The primary objective is to develop a network architecture capable of achieving high-quality denoising performance, quantitatively evaluated using PSNR, without constraints on computational complexity or model size. The task assumes independent additive white Gaussian noise (AWGN) with a fixed noise level of 50. A total of 290 participants registered for the challenge, with 20 teams successfully submitting valid results, providing insights into the current state-of-the-art in image denoising.

cs.CV↗

arXiv2024

Complete $\mathcal{O}(α_s^2)$ Corrections to the Leptonic Invariant Mass Spectrum in $b\to X_c l\barν_l$ Decay

In the determination of the Cabibbo-Kobayashi-Maskawa matrix element $|V_{cb}|$ from inclusive semileptonic $B$-meson decays, moments of the leptonic invariant mass spectrum constitute valuable observables. To evaluate them with sufficient precision, perturbative $\mathcal{O}(α_s^2)$ corrections to the analogous spectrum in the partonic $b\to X_c l\barν_l$ decay are necessary. In the present paper, we compute such perturbative corrections in a complete manner, including contributions from the triple-charm channel, namely from the $cc\bar{c}l\barν_l$ final states. We present our results in terms of numerical fits in both the single- and triple-charm cases. We confirm the recently found results for the single-charm correction, and analyze the triple-charm channel impact on centralized moments of the spectrum.

hep-ph↗

arXiv2024

Angular observables of the four-fold $B \to K_{1}(1270,1400)(\to V P) \ell^{+}\ell^{-}$ decays in and beyond the Standard Model

Recent measurements of the lepton flavor universality ratios $R^{μe}_{K}$ and $R^{μe}_{K^*}$ in $B\to \left(K, K^*\right)μ^{+}μ^{-}\left(e^+e^-\right)$ at LHCb align with the Standard Model predictions, necessitating search for the complementary decay modes. In this context, we derive the angular decay distributions of the four-fold $B \to K_{1}(1270,1400)(\to V P) μ^{+}μ^{-}$ decays, where $K_1 $ is an axial-vector meson, $V=ρ, K^{\ast}$, and $P=K, π$. Considering the weak effective Hamiltonian with vector and axial-vector new physics operators, and employing the helicity formalism, we obtain the four-dimensional differential decay distributions and extract various physical observables. These include differential branching ratios, lepton forward-backward asymmetry, forward-backward asymmetry for transversely polarized $K_1$ meson, longitudinal and transverse polarization fractions of the $K_1$ meson, and the normalized angular coefficients with longitudinally and transversely polarized final state vector meson $V$, in the cascade decay $K_1\to VP$. Based on the latest global fit analysis data for all $b\to s$ transitions, we predict the results of these observables in various bins of the square of the momentum transfer, $q^2$. Our findings indicate that these physical observables are not only sensitive to new physics but can also differentiate between various new physics scenarios in certain kinematical regions. The precise measurements of these observables in $B \to K_{1}(1270,1400)(\to V P) μ^{+}μ^{-}$ decays at current and future experiments will provide opportunities for the complementary searches for physics beyond the Standard Model in $b\to s\ell^+\ell^-$ decays.

hep-ph↗

arXiv2024

Semileptonic $W$ Decay to the $B$ Meson with Lepton Pairs in Heavy Quark Effective Theory Factorization upto $\mathcal{O}$$(α_s)$

Motivated by the study of heavy-light meson production within the framework of heavy quark effective theory (HQET) factorization, we extend the factorization formalism for a rather complicated process $W^+\to B^+\ell^+\ell^-$ in the limit of a non-zero invariant squared-mass of dilepton, $q^2$, at the lowest order in $1/m_b$ up to $\mathcal{O}(α_s)$. The purpose of the current study is to extend the HQET factorization formula for the $W^+\to B^+\ell^+\ell^-$ process and subsequently compute the form factors for this channel up to next-to-leading-order corrections in $α_s$. We explicitly show the amplitude of the $W^+\to B^+\ell^+\ell^-$ process can also be factorized into a convolution between the perturbatively calculable hard-scattering kernel and the non-perturbative yet universal light-cone distribution amplitude (LCDA) defined in HQET. The validity of HQET factorization depends on the assumed scale hierarchy $m_W \sim m_b \gg Λ_{\mathrm{QCD}}$. Within the HQET framework, we evaluate the form factors associated with the $W^+ \rightarrow B^+\ell^+\ell^-$ process, providing insights into its phenomenology. In addition, we also perform an exploratory phenomenological study on $W^+ \rightarrow B^+\ell^+\ell^-$ by employing an exponential model for the LCDAs for $B^+$ meson. Our findings reveal that the branching ratio for $W^+ \rightarrow B^+\ell^+\ell^-$ is below $10^{-10}$. Although the branching ratios are small, this channel in high luminosity LHC experiments may serve to further constraints the value of $λ_B$.

hep-ph↗

arXiv2024

Light quark mediated Higgs boson production in association with a jet at the next-to-next-leading order and beyond

We study the light quark effect on the Higgs boson production in association with a jet at the LHC in the intermediate transverse momentum region between the quark and the Higgs boson mass scales. Though the effect is suppressed by the small Yukawa coupling, it is enhanced by large logarithms of the quark mass ratio to the Higgs boson mass or transverse momentum. Following a remarkable success of the logarithmic expansion [39] for the prediction of the next-to-next-to-leading bottom quark contribution to the total cross section of the Higgs boson production we extend the analysis to its kinematical distributions. A new factorization formula is derived for the light quark mediated $gg\to Hg$ amplitudes and the differential cross section of the process is computed in the logarithmic approximation, which is used for an estimate of the bottom quark effect at the next-to-next-to-leading order.

hep-ph↗

arXiv2022

A Secure Healthcare 5.0 System Based on Blockchain Technology Entangled with Federated Learning Technique

In recent years, the global Internet of Medical Things (IoMT) industry has evolved at a tremendous speed. Security and privacy are key concerns on the IoMT, owing to the huge scale and deployment of IoMT networks. Machine learning (ML) and blockchain (BC) technologies have significantly enhanced the capabilities and facilities of healthcare 5.0, spawning a new area known as "Smart Healthcare." By identifying concerns early, a smart healthcare system can help avoid long-term damage. This will enhance the quality of life for patients while reducing their stress and healthcare costs. The IoMT enables a range of functionalities in the field of information technology, one of which is smart and interactive health care. However, combining medical data into a single storage location to train a powerful machine learning model raises concerns about privacy, ownership, and compliance with greater concentration. Federated learning (FL) overcomes the preceding difficulties by utilizing a centralized aggregate server to disseminate a global learning model. Simultaneously, the local participant keeps control of patient information, assuring data confidentiality and security. This article conducts a comprehensive analysis of the findings on blockchain technology entangled with federated learning in healthcare. 5.0. The purpose of this study is to construct a secure health monitoring system in healthcare 5.0 by utilizing a blockchain technology and Intrusion Detection System (IDS) to detect any malicious activity in a healthcare network and enables physicians to monitor patients through medical sensors and take necessary measures periodically by predicting diseases.

cs.LG↗

arXiv2020

Interpretation of LHCb Hidden-Charm Pentaquarks within the Compact Diquark Model

The LHCb collaboration have recently updated their analysis of the resonant $J/ψ\, p$ mass spectrum in the decay $Λ_b^0 \to J/ψ\, p\, K^-$, making use of their combined Run~1 and Run~2 data. In the updated analysis, three narrow states, $P_c (4312)^+$, $P_c (4440)^+$, and $P_c (4457)^+$, are observed. The spin-parity assignments of these states are not yet known. We interpret these narrow resonances as compact hidden-charm diquark-diquark-antiquark pentaquarks. Using an effective Hamiltonian, based on constituent quarks and diquarks, we calculate the pentaquark mass spectrum for the complete $SU (3)_F$ lowest $S$- and $P$-wave multiplets, taking into account dominant spin-spin, spin-orbit, orbital and tensor interactions. The resulting spectrum is very rich and we work out the quark flavor compositions, masses, and $J^P$ quantum numbers of the pentaquarks. However, heavy quark symmetry restricts the observable states in $Λ_b$-baryon, as well as in the decays of the other weakly-decaying $b$-baryons, $Ξ_b$ and $Ω_b$. In addition, some of the pentaquark states are estimated to lie below the $J/ψ\, p$ threshold in $Λ_b$-decays (and corresponding thresholds in $Ξ_b$- and $Ω_b$-decays). They decay via $c \bar c$ annihilation into light hadrons or a dilepton pair, and are expected to be narrower than the $P_c$-states observed. We anticipate their discovery, as well as of the other pentaquark states present in the spectrum at the LHC, and in the long-term future at a Tera-$Z$ factory.

hep-ph↗

arXiv2019

Mass spectrum of the hidden-charm pentaquarks in the compact diquark model

The LHCb collaboration have recently updated their analysis of the resonant $J/ψp$ mass spectrum in the decay $Λ_b^0 \to J/ψp K^-$, making use of their combined Run 1 and Run 2 data. In the updated analysis, three narrow states, $P_c (4312)^+$, $P_c (4440)^+$,and $P_c (4457)^+$, are observed. The spin-parity assignments of these states are not yet known. We interpret these narrow resonances as compact hidden-charm diquark-diquark-antiquark pentaquarks. Using an effective Hamiltonian, based on constituent quarks and diquarks, we calculate the pentaquark mass spectrum for the complete $SU (3)_F$ lowest $S$- and $P$-wave multiplets, taking into account dominant spin-spin, spin-orbit, orbital and tensor interactions. The resulting spectrum is very rich and we work out the quark flavor compositions, masses, and $J^P$ quantum numbers of the pentaquarks. However, heavy quark symmetry restricts the observable states in $Λ_b$-baryon, as well as in the decays of the other weakly-decaying $b$-baryons, $Ξ_b$ and $Ω_b$. In addition, some of the pentaquark states are estimated to lie below the $J/ψp$ threshold in $Λ_b$-decays (and corresponding thresholds in $Ξ_b$- and $Ω_b$-decays). They decay via $c \bar c$ annihilation into light hadrons or a dilepton pair, and are expected to be narrower than the $P_c$-states observed. We anticipate their discovery, as well as of the other pentaquark states present in the spectrum at the LHC, and in the long-term future at a Tera-$Z$ factory.

hep-ph↗

arXiv2018

LHCb anomaly in $\boldsymbol{B\to K^*μ^+ μ^-}$ optimised observables and potential of $\boldsymbol{Z^\prime}$ Model

Over the last few years LHCb with present energies found some discrepancies in $b\to s\ell^+\ell^-$ FCNC transitions including anomalies in the angular observables of $B\to K^*μ^+μ^-$, particularly in $P_5^\prime$, in low dimuon mass region. Recently, these anomalies are confirmed by Belle, CMS and ATLAS. As the direct evidence of physics beyond-the-SM is absent so far, therefore, these anomalies are being interpreted as indirect hint of new physics. In this context, we study the implication of non universal family of $Z^\prime$ model to the angular observables $P_{1,2,3}$, $P^{\prime}_{4,5,6}$ and newly proposed lepton flavor universality violation observables, $Q_{4,5}$, in $B\to K^*(\to Kπ)μ^+ μ^-$ decay channel in the low dimuon mass region. To see variation in the values of these observables from their standard model values, we have chosen the different scenarios of the $Z^\prime$ model. It is found that these angular observables are sensitive to the values of the parameters of $Z^\prime$ model. We have also found that with the present parametric space of $Z^\prime$ model, the $P_5^\prime$-anomaly could be accommodated. However, more statistics on the anomalies in the angular observables are helpful to reveal the status of the considered model and, in general, the nature of new physics.

hep-ph↗

arXiv2017

A New Look at the $Y$ Tetraquarks and $Ω_c$ Baryons in the Diquark Model

We analyze the hidden charm $P$-wave tetraquarks in the diquark model, using an effective Hamiltonian incorporating the dominant spin-spin, spin-orbit and tensor interactions. We compare with other $P$-wave system such as $P$-wave charmonia and the newly discovered $Ω_c$ baryons, analysed recently in this framework. Given the uncertain experimental situation on the $Y$ states, we allow for different spectra and discuss the related parameters in the diquark model. In addition to the presently observed ones, we expect many more states in the supermultiplet of $L=1$ diquarkonia, whose $J^{PC}$ quantum numbers and masses are worked out, using the parameters from the currently preferred $Y$-states pattern. The existence of these new resonances would be a decisive footprint of the underlying diquark dynamics.

hep-ph↗

arXiv2017

NNLO QCD counterterm contributions to $B$ \to $X_s γ$ for the physical value of $m_c$

One of the most important O($α_s^2$) corrections to the $B \to X_s γ$ branching ratio originates from interference of contributions from the current-current and photonic dipole operators. Its value has been estimated using an interpolation in the charm quark mass between the known results at $m_c=0$ and for $m_c \ll m_b/2$. An explicit calculation for the physical value of $m_c$ is necessary to remove the associated uncertainty. In the present work, we evaluate all the ultraviolet counterterm contributions that are relevant for this purpose.

hep-ph↗