Selected work

Representative Papers

smartcor: Intelligent Correlation Method Selection for Mixed Variable Types

Jul 24, 2026

This study addresses the common misuse of Pearson correlation for mixed variable types—such as binary, ordinal, and nominal—which often introduces bias in traditional correlation analyses. To resolve this, the authors introduce smartcor (for R) and pysmartcor (for Python), the first toolkits to systematically support all ten possible combinations of variable types. These packages employ automatic variable-type detection and a rule-based engine to intelligently select the optimal correlation or association method from a repertoire of fourteen, while also providing interpretable justifications for each choice. Monte Carlo simulations demonstrate substantially improved selection accuracy, and real-world case studies reveal meaningful discrepancies between type-aware analyses and naive Pearson correlations, thereby enhancing the reliability of statistical inference.

0 citationsRead paper

QPredSGG: Hybrid Quantum Predicate Learning for Long-Tailed Scene Graph Generation

Jun 03, 2026

This work addresses the bias in relationship prediction caused by the long-tailed predicate distribution in scene graph generation by proposing a hybrid quantum-classical architecture. Specifically, the conventional predicate classification head of a causal feature enhancement network is replaced with a quantum predicate head trained via weighted cross-entropy. The approach demonstrates, for the first time on Visual Genome 150, the effectiveness of quantum circuits for modeling scene graph relationships: amplitude embedding combined with strongly entangling layers constructs 4- or 8-qubit circuits that compress 4096-dimensional features into 16 dimensions using only 96–384 trainable parameters. Experimental results show that the 4-qubit model achieves an mR@100 of 57.25%, substantially outperforming the classical CFEN (41.1%), while the 8-qubit variant maintains strong long-tail performance (55.38%) with a 256-fold improvement in parameter efficiency.

0 citationsRead paper

Different Strokes for Different Folks: Writer Identification for Historical Arabic Manuscripts

Apr 24, 2026

This study addresses authorship identification in historical Arabic manuscripts by proposing a convolutional neural network integrated with an attention mechanism. The model performs closed-set author classification under two evaluation protocols: line-level and page-independent settings. Notably, it innovatively treats rare manuscript lines containing contributions from two authors as composite categories. Leveraging a substantially expanded and manually verified version of the Muharaf dataset, this work establishes the first baseline results for both protocols. Extensive experiments employing backbone architectures such as DenseNet201 and diverse training strategies—validated through fourteen ablation configurations—achieve a Top-1 accuracy of 99.05% (F1: 97.44%) under the line-level protocol and 78.61% (F1: 66.55%) under the page-independent protocol, demonstrating significant performance gains in manuscript authorship identification.

0 citationsRead paper

Noise Steering for Controlled Text Generation: Improving Diversity and Reading-Level Fidelity in Arabic Educational Story Generation

Apr 03, 2026

This work proposes a training-free, noise-guided approach to enhance narrative diversity in Arabic early-grade reading assessment stories while preserving strict educational constraints—such as vocabulary control, readability level, and narrative structure. The method injects calibrated Gaussian perturbations into internal representations of Transformer models, specifically targeting the residual stream and attention entropy. Evaluation across five Arabic-specific models (7–9B parameters) demonstrates that residual stream noise significantly boosts narrative diversity with minimal impact on text quality or constraint adherence, while attention entropy noise injection (AENI) effectively stabilizes logical coherence and recovers textual fluency. Unlike conventional high-temperature sampling, which often induces readability drift and quality degradation, the proposed technique successfully balances diversity with pedagogical fidelity.

0 citationsRead paper

LRConv-NeRV: Low Rank Convolution for Efficient Neural Video Compression

Mar 18, 2026

This work addresses the high computational and memory overhead of NeRV’s convolutional decoder, which hinders deployment on resource-constrained devices. The authors propose replacing selected dense 3×3 convolutions in the NeRV decoder with structured low-rank separable convolutions (LRConv) and introduce a progressive low-rank decomposition strategy that incrementally integrates LRConv from the decoder’s backend toward its frontend, enabling a controllable trade-off between efficiency and reconstruction quality. Applying LRConv only in the final decoding stage reduces decoding complexity by 68% (from 201.9 to 64.9 GFLOPs), shrinks model size by 9.3%, and lowers bitrate by approximately 9.2%, while achieving superior performance over existing methods in terms of PSNR, MS-SSIM, and temporal stability as measured by LPIPS.

0 citationsRead paper

Recent publications

Latest Papers

smartcor: Intelligent Correlation Method Selection for Mixed Variable Types

Jul 24, 2026

This study addresses the common misuse of Pearson correlation for mixed variable types—such as binary, ordinal, and nominal—which often introduces bias in traditional correlation analyses. To resolve this, the authors introduce smartcor (for R) and pysmartcor (for Python), the first toolkits to systematically support all ten possible combinations of variable types. These packages employ automatic variable-type detection and a rule-based engine to intelligently select the optimal correlation or association method from a repertoire of fourteen, while also providing interpretable justifications for each choice. Monte Carlo simulations demonstrate substantially improved selection accuracy, and real-world case studies reveal meaningful discrepancies between type-aware analyses and naive Pearson correlations, thereby enhancing the reliability of statistical inference.

0 citationsRead paper

QPredSGG: Hybrid Quantum Predicate Learning for Long-Tailed Scene Graph Generation

Jun 03, 2026

This work addresses the bias in relationship prediction caused by the long-tailed predicate distribution in scene graph generation by proposing a hybrid quantum-classical architecture. Specifically, the conventional predicate classification head of a causal feature enhancement network is replaced with a quantum predicate head trained via weighted cross-entropy. The approach demonstrates, for the first time on Visual Genome 150, the effectiveness of quantum circuits for modeling scene graph relationships: amplitude embedding combined with strongly entangling layers constructs 4- or 8-qubit circuits that compress 4096-dimensional features into 16 dimensions using only 96–384 trainable parameters. Experimental results show that the 4-qubit model achieves an mR@100 of 57.25%, substantially outperforming the classical CFEN (41.1%), while the 8-qubit variant maintains strong long-tail performance (55.38%) with a 256-fold improvement in parameter efficiency.

0 citationsRead paper

Different Strokes for Different Folks: Writer Identification for Historical Arabic Manuscripts

Apr 24, 2026

This study addresses authorship identification in historical Arabic manuscripts by proposing a convolutional neural network integrated with an attention mechanism. The model performs closed-set author classification under two evaluation protocols: line-level and page-independent settings. Notably, it innovatively treats rare manuscript lines containing contributions from two authors as composite categories. Leveraging a substantially expanded and manually verified version of the Muharaf dataset, this work establishes the first baseline results for both protocols. Extensive experiments employing backbone architectures such as DenseNet201 and diverse training strategies—validated through fourteen ablation configurations—achieve a Top-1 accuracy of 99.05% (F1: 97.44%) under the line-level protocol and 78.61% (F1: 66.55%) under the page-independent protocol, demonstrating significant performance gains in manuscript authorship identification.

0 citationsRead paper

Noise Steering for Controlled Text Generation: Improving Diversity and Reading-Level Fidelity in Arabic Educational Story Generation

Apr 03, 2026

This work proposes a training-free, noise-guided approach to enhance narrative diversity in Arabic early-grade reading assessment stories while preserving strict educational constraints—such as vocabulary control, readability level, and narrative structure. The method injects calibrated Gaussian perturbations into internal representations of Transformer models, specifically targeting the residual stream and attention entropy. Evaluation across five Arabic-specific models (7–9B parameters) demonstrates that residual stream noise significantly boosts narrative diversity with minimal impact on text quality or constraint adherence, while attention entropy noise injection (AENI) effectively stabilizes logical coherence and recovers textual fluency. Unlike conventional high-temperature sampling, which often induces readability drift and quality degradation, the proposed technique successfully balances diversity with pedagogical fidelity.

0 citationsRead paper

LRConv-NeRV: Low Rank Convolution for Efficient Neural Video Compression

Mar 18, 2026

This work addresses the high computational and memory overhead of NeRV’s convolutional decoder, which hinders deployment on resource-constrained devices. The authors propose replacing selected dense 3×3 convolutions in the NeRV decoder with structured low-rank separable convolutions (LRConv) and introduce a progressive low-rank decomposition strategy that incrementally integrates LRConv from the decoder’s backend toward its frontend, enabling a controllable trade-off between efficiency and reconstruction quality. Applying LRConv only in the final decoding stage reduces decoding complexity by 68% (from 201.9 to 64.9 GFLOPs), shrinks model size by 9.3%, and lowers bitrate by approximately 9.2%, while achieving superior performance over existing methods in terms of PSNR, MS-SSIM, and temporal stability as measured by LPIPS.

0 citationsRead paper