arXiv subjects

Muhammad Ali

Publications and source records attributed to Muhammad Ali.

At least 19 recordsLinked to original sources

arXiv2026

Faithfulness Is Not Free: Auditing Offline KV-Cache Quantization in Retrieval-Augmented Generation

Retrieval-augmented generation systems can precompute and store key-value caches of retrieved documents to avoid re-encoding context at every query. Quantizing these caches further reduces storage, but no prior work asks whether compression damages faithfulness, whether responses remain grounded in the retrieved evidence. Faithfulness and accuracy are not equivalent: a model can produce a correct answer that is no longer supported by the context it was given. We evaluate Qwen2.5-7B-Instruct under INT8 and INT4 quantization on RGB and HotpotQA, measuring both accuracy and faithfulness with a hallucination detector, NLI entailment, and an LLM judge. INT8 is near-lossless across both metrics. INT4 reduces accuracy and, more critically, even among answers that remain factually correct, over 90% of faithfulness changes are negative, i.e., accuracy metrics are blind to this regression. The harm grows under noisy retrieval and with more retrieved chunks. Faithfulness must be audited before compressed caches are deployed.

cs.CL↗

arXiv2026

Refining Over Resampling: Test-Time Self-Correction for LLM Reasoning

Test-time scaling improves LLM reasoning by using additional inference compute, but wider sampling alone can suffer from diminishing returns: new rollouts often repeat existing answer patterns instead of adding useful reasoning diversity. Verifier-based selection offers an alternative, but its performance depends on the calibration of an external reward model. We propose a verifier-free breadth--depth refinement framework that uses test-time compute to both explore and improve candidate solutions. The method samples multiple independent reasoning rollouts, refines each rollout through iterative self-critique and self-correction, and aggregates the refined answers by majority voting. Breadth preserves diverse initial attempts, while depth repairs local reasoning errors before aggregation. Across AIME24, AIME25, AMC, OlympiadBench, and MATH500, our method consistently improves over greedy decoding, majority voting, verifier-based best-of-$N$, beam search, and lookahead decoding across multiple open-weight models. For instance, with Qwen2.5-1.5B, accuracy increases from the strongest verifier-based baseline to $58.0\%$ on MATH500, and from $25.0\%$ to $32.5\%$ on AMC. These results show that test-time compute can be more effective when used to refine sampled trajectories rather than only to sample more candidates or rely on verifier-guided selection.

cs.AI↗

arXiv2026

FlexPooling with Simple Auxiliary Classifiers in Deep Networks

In computer vision, the basic pipeline of most convolutional neural networks consists of multiple feature extraction layers, where the input signal is downsampled to a lower resolution in each subsequent layer. This downsampling process is commonly referred to as pooling, which is an essential operation in CNNs. Pooling improves robustness against transformations, reduces the number of trainable parameters, increases the receptive field, and lowers computation time. Since pooling is a lossy process but remains important for extracting high-level information from low-level representations, it is important to preserve the most prominent information from previous activations to improve network discriminability. Standard pooling is usually performed using dense pooling methods, such as max pooling or average pooling, or through strided convolutional kernels. In this paper, we propose a simple yet effective adaptive pooling method, called FlexPooling, which generalizes average pooling by learning a weighted average over activations jointly with the rest of the network. We further show that attaching Simple Auxiliary Classifiers (SAC) to the CNN improves performance and demonstrates the effectiveness of the proposed method compared with standard pooling methods. Experiments on multiple popular image classification datasets show that FlexPooling consistently outperforms baseline networks, achieving approximately 1 to 3 percent improvement in accuracy.

cs.CV↗

arXiv2026

BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language

We present BaltiVoice, a 16.8-hour read-speech corpus for Balti (ISO 639-3: bft), a Tibetic language spoken in Gilgit-Baltistan, Pakistan, with no prior publicly available ASR resources. The corpus contains 10,060 validated utterances in native Nastaliq script, derived from Mozilla Common Voice recordings. Fine-tuning OpenAI Whisper-small yields a Word Error Rate (WER) of 24.78% and a Character Error Rate (CER) of 8.30% after training for 5 epochs (3,000 steps) on the 538-utterance speaker-disjoint validation set, down from a zero-shot baseline of 159.19% WER and 152.52% CER. A Whisper-base fine-tuned on the same data achieves 44.54% WER and 15.61% CER, confirming that model capacity matters for this low-resource setting. The dataset, fine-tuned model, and a live transcription demo are publicly available on HuggingFace.

cs.CL↗

arXiv2026

A Promising Ohmic Contacts Approach for High-Al AlxGa1-xN (x>0.6) Channel HEMTs with AlN/GaN Digital Alloy Channel

In this paper we report a novel ohmic contact formation scheme for Extreme Bandgap (EBG) AlxGa1-xN (x>0.6) channel HEMTs with undoped barrier layers. Our approach consists of using a new low temperature (LT) pulsed metal-organic chemical vapor deposition (PMOCVD) doping scheme for the n++-GaN regrown contacts and an AlxGa1-xN digital alloy (DA) channel layer comprising short period super lattices (SPSL) of AlN and GaN. Pulsed growth and doping yield a sheet resistivity which is a factor of 3-5 lower than that of conventional doped n++-GaN layers grown under identical conditions. Moreover, the regrown n++-GaN layer has no hetero-barrier with the GaN layers of the AlxGa1-xN DA channel. These innovations led to MOCVD regrown linear ohmic contacts and a record-low contact resistance Rc ~6.5 {\Omega}-mm to the Al0.62Ga0.38N DA channel layer of a HEMT with AlN barrier layer.

physics.app-ph↗

arXiv2026

The Surprising Effectiveness of Canonical Knowledge Distillation for Semantic Segmentation

Recent knowledge distillation (KD) methods for semantic segmentation introduce increasingly complex hand-crafted objectives, yet are typically evaluated under fixed iteration schedules. These objectives substantially increase per-iteration cost, meaning equal iteration counts do not correspond to equal training budgets. It is therefore unclear whether reported gains reflect stronger distillation signals or simply greater compute. We show that iteration-based comparisons are misleading: when wall-clock compute is matched, canonical logit- and feature-based KD outperform recent segmentation-specific methods. Under extended training, feature-based distillation achieves state-of-the-art ResNet-18 performance on Cityscapes and ADE20K. A PSPNet ResNet-18 student closely approaches its ResNet-101 teacher despite using only one quarter of the parameters, reaching 99% of the teacher's mIoU on Cityscapes (79.0 vs 79.8) and 92% on ADE20K. Our results challenge the prevailing assumption that KD for segmentation requires task-specific mechanisms and suggest that scaling, rather than complex hand-crafted objectives, should guide future method design.

cs.CV↗

arXiv2026

Network-based drug repurposing for MYH9-related nephritis

Using tools from network theory, we analyze the organization of a MYH9-oriented drug-like library in chemical space using a multi-descriptor framework. The dataset is drawn from ZINC, a publicly available database of commercially accessible compounds curated for virtual screening and drug discovery. Starting from 6004 molecules, preprocessing yields 5000 structurally valid and descriptor-complete compounds. Similarity is defined via Tanimoto distance on Morgan fingerprints and single-descriptor distances for xLogP, HBD, HBA, molecular weight, and rotatable bonds. For each representation, we construct k-nearest-neighbor networks and identify communities using the Louvain-Leiden algorithm. All networks exhibit highly significant modularity (Q=0.91-0.99) relative to degree-preserving null models, demonstrating pronounced nonrandom chemical organization across descriptors. Cross-descriptor robustness is quantified through a co-clustering matrix over 1.25 X 10^7 molecular pairs, measuring how consistently compound pairs co-occur within the same community across descriptor-specific networks. Although most pairs show limited agreement, a sparse high-consensus core emerges, highlighting the complementarity of the descriptors. Minimum spanning trees derived from structural and consensus similarities reveal distinct backbone topologies: a scaffold-driven, sparse structure versus a compact, hub-rich consensus network. Betweenness centrality on these backbones identifies compounds that are both structurally central and descriptor-balanced. These results provide a statistically validated network representation of chemical space and a principled strategy to extract consensus-stable compounds for downstream screening.

physics.bio-ph↗

arXiv2025

MuCol Milestone Report No. 7: Consolidated Parameters

This document is comprised of a collection of consolidated parameters for the key parts of the muon collider. These consolidated parameters follow on from the October 2024 Preliminary Parameters Report. Attention has been given to a high-level consistent set of baseline parameters throughout all systems of the complex, following a 10 TeV center-of-mass design. Additional details of the designs contributing to this baseline design are featured in the appendix. Likewise, explorative variations from this baseline set can be found in the appendix. The data is collected from a collaborative spreadsheet and transferred to overleaf.

physics.acc-ph↗

arXiv2025

Waste-Bench: A Comprehensive Benchmark for Evaluating VLLMs in Cluttered Environments

Recent advancements in Large Language Models (LLMs) have paved the way for Vision Large Language Models (VLLMs) capable of performing a wide range of visual understanding tasks. While LLMs have demonstrated impressive performance on standard natural images, their capabilities have not been thoroughly explored in cluttered datasets where there is complex environment having deformed shaped objects. In this work, we introduce a novel dataset specifically designed for waste classification in real-world scenarios, characterized by complex environments and deformed shaped objects. Along with this dataset, we present an in-depth evaluation approach to rigorously assess the robustness and accuracy of VLLMs. The introduced dataset and comprehensive analysis provide valuable insights into the performance of VLLMs under challenging conditions. Our findings highlight the critical need for further advancements in VLLM's robustness to perform better in complex environments. The dataset and code for our experiments will be made publicly available.

cs.CV↗

arXiv2025

FusionSort: Enhanced Cluttered Waste Segmentation with Advanced Decoding and Comprehensive Modality Optimization

In the realm of waste management, automating the sorting process for non-biodegradable materials presents considerable challenges due to the complexity and variability of waste streams. To address these challenges, we introduce an enhanced neural architecture that builds upon an existing Encoder-Decoder structure to improve the accuracy and efficiency of waste sorting systems. Our model integrates several key innovations: a Comprehensive Attention Block within the decoder, which refines feature representations by combining convolutional and upsampling operations. In parallel, we utilize attention through the Mamba architecture, providing an additional performance boost. We also introduce a Data Fusion Block that fuses images with more than three channels. To achieve this, we apply PCA transformation to reduce the dimensionality while retaining the maximum variance and essential information across three dimensions, which are then used for further processing. We evaluated the model on RGB, hyperspectral, multispectral, and a combination of RGB and hyperspectral data. The results demonstrate that our approach outperforms existing methods by a significant margin.

cs.CV↗

arXiv2025

Real-TabPFN: Improving Tabular Foundation Models via Continued Pre-training With Real-World Data

Foundation models for tabular data, like TabPFN, achieve strong performance on small datasets when pre-trained solely on synthetic data. We show that this performance can be significantly boosted by a targeted continued pre-training phase. Specifically, we demonstrate that leveraging a small, curated collection of large, real-world datasets for continued pre-training yields superior downstream predictive accuracy compared to using broader, potentially noisier corpora like CommonCrawl or GitTables. Our resulting model, Real-TabPFN, achieves substantial performance gains on 29 datasets from the OpenML AutoML Benchmark.

cs.LG↗

arXiv2025

Automated MRI Tumor Segmentation using hybrid U-Net with Transformer and Efficient Attention

Cancer is an abnormal growth with potential to invade locally and metastasize to distant organs. Accurate auto-segmentation of the tumor and surrounding normal tissues is required for radiotherapy treatment plan optimization. Recent AI-based segmentation models are generally trained on large public datasets, which lack the heterogeneity of local patient populations. While these studies advance AI-based medical image segmentation, research on local datasets is necessary to develop and integrate AI tumor segmentation models directly into hospital software for efficient and accurate oncology treatment planning and execution. This study enhances tumor segmentation using computationally efficient hybrid UNet-Transformer models on magnetic resonance imaging (MRI) datasets acquired from a local hospital under strict privacy protection. We developed a robust data pipeline for seamless DICOM extraction and preprocessing, followed by extensive image augmentation to ensure model generalization across diverse clinical settings, resulting in a total dataset of 6080 images for training. Our novel architecture integrates UNet-based convolutional neural networks with a transformer bottleneck and complementary attention modules, including efficient attention, Squeeze-and-Excitation (SE) blocks, Convolutional Block Attention Module (CBAM), and ResNeXt blocks. To accelerate convergence and reduce computational demands, we used a maximum batch size of 8 and initialized the encoder with pretrained ImageNet weights, training the model on dual NVIDIA T4 GPUs via checkpointing to overcome Kaggle's runtime limits. Quantitative evaluation on the local MRI dataset yielded a Dice similarity coefficient of 0.764 and an Intersection over Union (IoU) of 0.736, demonstrating competitive performance despite limited data and underscoring the importance of site-specific model development for clinical deployment.

eess.IV↗

arXiv2025

The Muon Collider

Muons offer a unique opportunity to build a compact high-energy electroweak collider at the 10 TeV scale. A Muon Collider enables direct access to the underlying simplicity of the Standard Model and unparalleled reach beyond it. It will be a paradigm-shifting tool for particle physics representing the first collider to combine the high-energy reach of a proton collider and the high precision of an electron-positron collider, yielding a physics potential significantly greater than the sum of its individual parts. A high-energy muon collider is the natural next step in the exploration of fundamental physics after the HL-LHC and a natural complement to a future low-energy Higgs factory. Such a facility would significantly broaden the scope of particle colliders, engaging the many frontiers of the high energy community. The last European Strategy for Particle Physics Update and later the Particle Physics Project Prioritisation Panel in the US requested a study of the muon collider, which is being carried on by the International Muon Collider Collaboration. In this comprehensive document we present the physics case, the state of the work on accelerator design and technology, and propose an R\&D project that can make the muon collider a reality.

physics.acc-ph↗

arXiv2025

Intelligent Task Offloading in VANETs: A Hybrid AI-Driven Approach for Low-Latency and Energy Efficiency

Vehicular Ad-hoc Networks (VANETs) are integral to intelligent transportation systems, enabling vehicles to offload computational tasks to nearby roadside units (RSUs) and mobile edge computing (MEC) servers for real-time processing. However, the highly dynamic nature of VANETs introduces challenges, such as unpredictable network conditions, high latency, energy inefficiency, and task failure. This research addresses these issues by proposing a hybrid AI framework that integrates supervised learning, reinforcement learning, and Particle Swarm Optimization (PSO) for intelligent task offloading and resource allocation. The framework leverages supervised models for predicting optimal offloading strategies, reinforcement learning for adaptive decision-making, and PSO for optimizing latency and energy consumption. Extensive simulations demonstrate that the proposed framework achieves significant reductions in latency and energy usage while improving task success rates and network throughput. By offering an efficient, and scalable solution, this framework sets the foundation for enhancing real-time applications in dynamic vehicular environments.

cs.LG↗

arXiv2025

Enhanced Permeability Estimation in Microporous Rocks Using a Hybrid Macropore-Darcy Approach

This study presents a novel workflow for constructing hybrid macropore-Darcy models from micro-CT images of microporous rocks. In our approach, macropore networks are extracted using established methods, while the microporosity is characterised through segmented phase classification and incorporated into the model as Darcy cells. Effectively, Darcy cells capture the micro scale connectivity variations that are missing in the macroscopic networks. This dual entity model thus incorporates both the conventional macroscopic pore structure and the critical flow pathways present in the under-resolved microporous regions. The proposed workflow is rigorously validated by comparing the permeability estimates with direct numerical simulation (DNS) results and experimental measurements. Our findings demonstrate that this hybrid approach reliably reproduces fluid flow behaviour in complex porous media while significantly reducing computational demands, offering a promising tool for advanced groundwater modelling and water resource management.

physics.flu-dyn↗

arXiv2025

Unequal Opportunities: Examining the Bias in Geographical Recommendations by Large Language Models

Recent advancements in Large Language Models (LLMs) have made them a popular information-seeking tool among end users. However, the statistical training methods for LLMs have raised concerns about their representation of under-represented topics, potentially leading to biases that could influence real-world decisions and opportunities. These biases could have significant economic, social, and cultural impacts as LLMs become more prevalent, whether through direct interactions--such as when users engage with chatbots or automated assistants--or through their integration into third-party applications (as agents), where the models influence decision-making processes and functionalities behind the scenes. Our study examines the biases present in LLMs recommendations of U.S. cities and towns across three domains: relocation, tourism, and starting a business. We explore two key research questions: (i) How similar LLMs responses are, and (ii) How this similarity might favor areas with certain characteristics over others, introducing biases. We focus on the consistency of LLMs responses and their tendency to over-represent or under-represent specific locations. Our findings point to consistent demographic biases in these recommendations, which could perpetuate a ``rich-get-richer'' effect that widens existing economic disparities.

cs.CL↗

arXiv2025

A Chaotic Image Encryption Scheme Using Novel Geometric Block Permutation and Dynamic Substitution

In this digital era, ensuring the security of digital data during transmission and storage is crucial. Digital data, particularly image data, needs to be protected against unauthorized access. To address this, this paper presents a novel image encryption scheme based on a confusion diffusion architecture. The diffusion module introduces a novel geometric block permutation technique, which effectively scrambles the pixels based on geometric shape extraction of pixels. The image is converted into four blocks, and pixels are extracted from these blocks using L-shape, U-shape, square-shape, and inverted U-shape patterns for each block, respectively. This robust extraction and permutation effectively disrupts the correlation within the image. Furthermore, the confusion module utilises bit-XOR and dynamic substitution techniques. For the bit-XOR operation, 2D Henon map has been utilised to generate a chaotic seed matrix, which is bit-XORed with the scrambled image. The resultant image then undergoes the dynamic substitution process to complete confusion phase. A statistical security analysis demonstrates the superior security of the proposed scheme, with being high uncertainty and unpredictability, achieving an entropy of 7.9974 and a correlation coefficient of 0.0014. These results validate the proposed scheme's effectiveness in securing digital images.

cs.CR↗

arXiv2025

X-Cross: Image Encryption Featuring Novel Dual-Layer Block Permutation and Dynamic Substitution Techniques

In this digital age, ensuring the security of digital data, especially the image data is critically important. Image encryption plays an important role in securing the online transmission/storage of images from unauthorized access. In this regard, this paper presents a novel diffusion-confusion-based image encryption algorithm named as X-CROSS. The diffusion phase involves a dual-layer block permutation. It involves a bit-level permutation termed Inter-Bit Transference (IBT) using a Bit-Extraction key, and pixel permutation with a unique X-crosspermutation algorithm to effectively scramble the pixels within an image. The proposed algorithm utilizes a resilient 2D chaotic map with non-linear dynamical behavior, assisting in generating complex Extraction Keys. After the permutation phase, the confusion phase proceeds with a dynamic substitution technique on the permuted images, establishing the final encryption layer. This combination of novel permutation and confusion results in the removal of the image's inherent patterns and increases its resistance to cyber-attacks. The close to ideal statistical security results for information entropy, correlation, homogeneity, contrast, and energy validate the proposed scheme's effectiveness in hiding the information within the image.

cs.CR↗