arXiv subjects

Mohammed E. Fouda

Publications and source records attributed to Mohammed E. Fouda.

At least 19 recordsLinked to original sources

arXiv2026

SalamahBench: Dialect and Category Level Safety Evaluation of Arabic Language Models

While different stakeholders are trying to leverage Arabic Language Models (ALMs), safety alignment in ALMs remains largely underexplored, hindering their mainstream adoption. Existing safety benchmarks are predominantly English-centric and evaluate Arabic only in its standardized form, obscuring fine-grained safety vulnerabilities in Arabic NLP systems. This paper introduces SalamahBench, a unified benchmark of 8{,}270 human-verified harmful prompts across ML Commons hazard categories, each rendered in Modern Standard Arabic (MSA) and five regional Arabic varieties, namely Egyptian, Syrian, Saudi, Lebanese, and Moroccan, for a total of 49{,}620 paired instances. To analyze the resulting data, we introduce two complementary metrics, namely Dialect Shift, which measures a model's aggregate change in safety under dialectal reformulation, and Category-Specific Dialect Deviation, which isolates harm categories whose change departs from that aggregate trend. Evaluating models such as Fanar 2, ALLaM 2, and Karnak 1 under multiple safeguard configurations, we find that cross-variety robustness is strongly model dependent, and that aggregate scores can conceal category-level divergence. Our findings highlight the necessity of evaluating Arabic model safety jointly across linguistic varieties and harm domains rather than relying on aggregate scores or MSA alone.

cs.CL↗

arXiv2026

EdgeCIM: A Hardware-Software Co-Design for CIM-Based Acceleration of Small Language Models

The growing demand for deploying Small Language Models (SLMs) on edge devices, including laptops, smartphones, and embedded platforms, has exposed fundamental inefficiencies in existing accelerators. While GPUs handle prefill workloads efficiently, the autoregressive decoding phase is dominated by GEMV operations that are inherently memory-bound, resulting in poor utilization and prohibitive energy costs at the edge. In this work, we present EdgeCIM, a hardware-software co-design framework that rethinks accelerator design for end-to-end decoder-only inference. At its core is a CIM macro, implemented in 65nm, coupled with a tile-based mapping strategy that balances pipeline stages, maximizing parallelism while alleviating DRAM bandwidth bottlenecks. Our simulator enables design space exploration of SLMs up to 4B parameters, identifying Pareto-optimal configurations in terms of latency and energy. Compared to an NVIDIA Orin Nano, EdgeCIM achieves up to 7.3x higher throughput and 49.59x better energy efficiency on LLaMA3.2-1B, and delivers 9.95x higher throughput than Qualcomm SA8255P on LLaMA3.2-3B. Extensive benchmarks on TinyLLaMA-1.1B, LLaMA3.2 (1B, 3B), Phi-3.5-mini-3.8B, Qwen2.5 (0.5B, 1.5B, 3B), SmolLM2-1.7B, SmolLM3-3B, and Qwen3 (0.6B, 1.7B, 4B) reveal that our accelerator, under INT4 precision, achieves on average 336.42 tokens/s and 173.02 tokens/J. These results establish EdgeCIM as a compelling solution towards real-time, energy-efficient edge-scale SLM inference.

cs.AR↗

arXiv2026

Joint Hardware-Workload Co-Optimization for In-Memory Computing Accelerators

Software-hardware co-design is essential for optimizing in-memory computing (IMC) hardware accelerators for neural networks. However, most existing optimization frameworks target a single workload, leading to highly specialized hardware designs that do not generalize well across models and applications. In contrast, practical deployment scenarios require a single IMC platform that can efficiently support multiple neural network workloads. This work presents a joint hardware-workload co-optimization framework based on an optimized evolutionary algorithm for designing generalized IMC accelerator architectures. By explicitly capturing cross-workload trade-offs rather than optimizing for a single model, the proposed approach significantly reduces the performance gap between workload-specific and generalized IMC designs. The framework is evaluated on both RRAM- and SRAM-based IMC architectures, demonstrating strong robustness and adaptability across diverse design scenarios. Compared to baseline methods, the optimized designs achieve energy-delay-area product (EDAP) reductions of up to 76.2% and 95.5% when optimizing across a small set (4 workloads) and a large set (9 workloads), respectively. The source code of the framework is available at https://github.com/OlgaKrestinskaya/JointHardwareWorkloadOptimizationIMC.

cs.AR↗

arXiv2025

A Comprehensive Evaluation of Large Language Models on Mental Illnesses

Large Language Models (LLMs) have shown promise in various domains, including healthcare, with significant potential to transform mental health applications by enabling scalable and accessible solutions. This study aims to provide a comprehensive evaluation of 33 LLMs, ranging from 2 billion to 405+ billion parameters, in performing key mental health tasks using social media data across six datasets. To our knowledge, this represents the largest-scale systematic evaluation of modern LLMs for mental health applications. Models such as GPT-4, Llama 3, Claude, Gemma, Gemini, and Phi-3 were assessed for their zero-shot (ZS) and few-shot (FS) capabilities across three tasks: binary disorder detection, disorder severity evaluation, and psychiatric knowledge assessment. Key findings revealed that models like GPT-4 and Llama 3 exhibited superior performance in binary disorder detection, achieving accuracies up to 85% on certain datasets, while FS learning notably enhanced disorder severity evaluations, reducing the Mean Absolute Error (MAE) by 1.3 points for the Phi-3-mini model. Recent models, such as Llama 3.1 405b, demonstrated exceptional psychiatric knowledge assessment accuracy at 91.2%, while prompt engineering played a crucial role in improving performance across tasks. However, the ethical constraints imposed by many LLM providers limit their ability to respond to sensitive queries, hampering comprehensive performance evaluations. This work highlights both the capabilities and limitations of LLMs in mental health contexts, offering valuable insights for future applications in psychiatry.

cs.AI↗

arXiv2025

PsychiatryBench: A Multi-Task Benchmark for LLMs in Psychiatry

Large language models (LLMs) offer significant potential in enhancing psychiatric practice, from improving diagnostic accuracy to streamlining clinical documentation and therapeutic support. However, existing evaluation resources heavily rely on small clinical interview corpora, social media posts, or synthetic dialogues, which limits their clinical validity and fails to capture the full complexity of diagnostic reasoning. In this work, we introduce PsychiatryBench, a rigorously curated benchmark grounded exclusively in authoritative, expert-validated psychiatric textbooks and casebooks. PsychiatryBench comprises eleven distinct question-answering tasks ranging from diagnostic reasoning and treatment planning to longitudinal follow-up, management planning, clinical approach, sequential case analysis, and multiple-choice/extended matching formats totaling 5,188 expert-annotated items. {\color{red}We evaluate a diverse set of frontier LLMs (including Google Gemini, DeepSeek, Sonnet 4.5, and GPT 5) alongside leading open-source medical models such as MedGemma using both conventional metrics and an "LLM-as-judge" similarity scoring framework. Our results reveal substantial gaps in clinical consistency and safety, particularly in multi-turn follow-up and management tasks, underscoring the need for specialized model tuning and more robust evaluation paradigms. PsychiatryBench offers a modular, extensible platform for benchmarking and improving LLM performance in mental health applications.

cs.CL↗

arXiv2025

Mixed-Precision Quantization for Language Models: Techniques and Prospects

The rapid scaling of language models (LMs) has resulted in unprecedented computational, memory, and energy requirements, making their training and deployment increasingly unsustainable. Quantization has emerged as an essential compression technique to reduce model size, alleviate memory bottlenecks, and accelerate inference. However, while uniform low-bit quantization (e.g., INT8, INT4) provides significant efficiency gains, it can degrade accuracy in sensitive components of transformer-based LMs. Mixed-precision quantization offers a promising alternative by selectively allocating precision across layers or within tensors to balance efficiency and accuracy. This survey provides a comprehensive overview of Mixed-Precision quantization frameworks for LMs (MXPLMs). We first review quantization fundamentals, including uniform and non-uniform quantizers, quantization granularity, and methods widely used in post-training quantization. We then categorize and compare recent MXPLM frameworks according to their bit allocation strategies and precision configurations across weights, activations, and key-value caches. A comparative analysis highlights differences in perplexity, zero-shot task performance, and deployment trade-offs. Furthermore, we contrast MXPLMs with earlier mixed-precision quantization methods for deep neural networks, identifying strategies that transfer and those that face challenges in the LM setting. Finally, we summarize open issues and future directions, including hardware-aware design, activation quantization, and scalable optimization methods for billion-parameter models. By consolidating recent advances, this work serves as a reference for understanding the current landscape and research prospects of mixed-precision quantization for large-scale language models.

cs.LG↗

arXiv2025

CIMNAS: A Joint Framework for Compute-In-Memory-Aware Neural Architecture Search

To maximize hardware efficiency and performance accuracy in Compute-In-Memory (CIM)-based neural network accelerators for Artificial Intelligence (AI) applications, co-optimizing both software and hardware design parameters is essential. Manual tuning is impractical due to the vast number of parameters and their complex interdependencies. To effectively automate the design and optimization of CIM-based neural network accelerators, hardware-aware neural architecture search (HW-NAS) techniques can be applied. This work introduces CIMNAS, a joint model-quantization-hardware optimization framework for CIM architectures. CIMNAS simultaneously searches across software parameters, quantization policies, and a broad range of hardware parameters, incorporating device-, circuit-, and architecture-level co-optimizations. CIMNAS experiments were conducted over a search space of 9.9x10^85 potential parameter combinations with the MobileNet model as a baseline and RRAM-based CIM architecture. Evaluated on the ImageNet dataset, CIMNAS achieved a reduction in energy-delay-area product (EDAP) ranging from 90.1x to 104.5x, an improvement in TOPS/W between 4.68x and 4.82x, and an enhancement in TOPS/mm^2 from 11.3x to 12.78x relative to various baselines, all while maintaining an accuracy of 73.81%. The adaptability and robustness of CIMNAS are demonstrated by extending the framework to support the SRAM-based ResNet50 architecture, achieving up to an 819.5x reduction in EDAP. Unlike other state-of-the-art methods, CIMNAS achieves EDAP-focused optimization without any accuracy loss, generating diverse software-hardware parameter combinations for high-performance CIM-based neural network designs. The source code of CIMNAS is available at https://github.com/OlgaKrestinskaya/CIMNAS.

cs.AI↗

arXiv2025

Leveraging Audio and Text Modalities in Mental Health: A Study of LLMs Performance

Mental health disorders are increasingly prevalent worldwide, creating an urgent need for innovative tools to support early diagnosis and intervention. This study explores the potential of Large Language Models (LLMs) in multimodal mental health diagnostics, specifically for detecting depression and Post Traumatic Stress Disorder through text and audio modalities. Using the E-DAIC dataset, we compare text and audio modalities to investigate whether LLMs can perform equally well or better with audio inputs. We further examine the integration of both modalities to determine if this can enhance diagnostic accuracy, which generally results in improved performance metrics. Our analysis specifically utilizes custom-formulated metrics; Modal Superiority Score and Disagreement Resolvement Score to evaluate how combined modalities influence model performance. The Gemini 1.5 Pro model achieves the highest scores in binary depression classification when using the combined modality, with an F1 score of 0.67 and a Balanced Accuracy (BA) of 77.4%, assessed across the full dataset. These results represent an increase of 3.1% over its performance with the text modality and 2.7% over the audio modality, highlighting the effectiveness of integrating modalities to enhance diagnostic accuracy. Notably, all results are obtained in zero-shot inferring, highlighting the robustness of the models without requiring task-specific fine-tuning. To explore the impact of different configurations on model performance, we conduct binary, severity, and multiclass tasks using both zero-shot and few-shot prompts, examining the effects of prompt variations on performance. The results reveal that models such as Gemini 1.5 Pro in text and audio modalities, and GPT-4o mini in the text modality, often surpass other models in balanced accuracy and F1 scores across multiple tasks.

cs.CL↗

arXiv2025

On Jailbreaking Quantized Language Models Through Fault Injection Attacks

The safety alignment of Language Models (LMs) is a critical concern, yet their integrity can be challenged by direct parameter manipulation attacks, such as those potentially induced by fault injection. As LMs are increasingly deployed using low-precision quantization for efficiency, this paper investigates the efficacy of such attacks for jailbreaking aligned LMs across different quantization schemes. We propose gradient-guided attacks, including a tailored progressive bit-level search algorithm introduced herein and a comparative word-level (single weight update) attack. Our evaluation on Llama-3.2-3B, Phi-4-mini, and Llama-3-8B across FP16 (baseline), and weight-only quantization (FP8, INT8, INT4) reveals that quantization significantly influences attack success. While attacks readily achieve high success (>80% Attack Success Rate, ASR) on FP16 models, within an attack budget of 25 perturbations, FP8 and INT8 models exhibit ASRs below 20% and 50%, respectively. Increasing the perturbation budget up to 150 bit-flips, FP8 models maintained ASR below 65%, demonstrating some resilience compared to INT8 and INT4 models that have high ASR. In addition, analysis of perturbation locations revealed differing architectural targets across quantization schemes, with (FP16, INT4) and (INT8, FP8) showing similar characteristics. Besides, jailbreaks induced in FP16 models were highly transferable to subsequent FP8/INT8 quantization (<5% ASR difference), though INT4 significantly reduced transferred ASR (avg. 35% drop). These findings highlight that while common quantization schemes, particularly FP8, increase the difficulty of direct parameter manipulation jailbreaks, vulnerabilities can still persist, especially through post-attack quantization.

cs.CR↗

arXiv2025

Leveraging Embedding Techniques in Multimodal Machine Learning for Mental Illness Assessment

The increasing global prevalence of mental disorders, such as depression and PTSD, requires objective and scalable diagnostic tools. Traditional clinical assessments often face limitations in accessibility, objectivity, and consistency. This paper investigates the potential of multimodal machine learning to address these challenges, leveraging the complementary information available in text, audio, and video data. Our approach involves a comprehensive analysis of various data preprocessing techniques, including novel chunking and utterance-based formatting strategies. We systematically evaluate a range of state-of-the-art embedding models for each modality and employ Convolutional Neural Networks (CNNs) and Bidirectional LSTM Networks (BiLSTMs) for feature extraction. We explore data-level, feature-level, and decision-level fusion techniques, including a novel integration of Large Language Model (LLM) predictions. We also investigate the impact of replacing Multilayer Perceptron classifiers with Support Vector Machines. We extend our analysis to severity prediction using PHQ-8 and PCL-C scores and multi-class classification (considering co-occurring conditions). Our results demonstrate that utterance-based chunking significantly improves performance, particularly for text and audio modalities. Decision-level fusion, incorporating LLM predictions, achieves the highest accuracy, with a balanced accuracy of 94.8% for depression and 96.2% for PTSD detection. The combination of CNN-BiLSTM architectures with utterance-level chunking, coupled with the integration of external LLM, provides a powerful and nuanced approach to the detection and assessment of mental health conditions. Our findings highlight the potential of MMML for developing more accurate, accessible, and personalized mental healthcare tools.

eess.AS↗

arXiv2025

Towards Efficient IMC Accelerator Design Through Joint Hardware-Workload Co-optimization

Designing generalized in-memory computing (IMC) hardware that efficiently supports a variety of workloads requires extensive design space exploration, which is infeasible to perform manually. Optimizing hardware individually for each workload or solely for the largest workload often fails to yield the most efficient generalized solutions. To address this, we propose a joint hardware-workload optimization framework that identifies optimised IMC chip architecture parameters, enabling more efficient, workload-flexible hardware. We show that joint optimization achieves 36%, 36%, 20%, and 69% better energy-latency-area scores for VGG16, ResNet18, AlexNet, and MobileNetV3, respectively, compared to the separate architecture parameters search optimizing for a single largest workload. Additionally, we quantify the performance trade-offs and losses of the resulting generalized IMC hardware compared to workload-specific IMC designs.

cs.AR↗

arXiv2025

A Comprehensive Evaluation of Large Language Models on Mental Illnesses in Arabic Context

Mental health disorders pose a growing public health concern in the Arab world, emphasizing the need for accessible diagnostic and intervention tools. Large language models (LLMs) offer a promising approach, but their application in Arabic contexts faces challenges including limited labeled datasets, linguistic complexity, and translation biases. This study comprehensively evaluates 8 LLMs, including general multi-lingual models, as well as bi-lingual ones, on diverse mental health datasets (such as AraDepSu, Dreaddit, MedMCQA), investigating the impact of prompt design, language configuration (native Arabic vs. translated English, and vice versa), and few-shot prompting on diagnostic performance. We find that prompt engineering significantly influences LLM scores mainly due to reduced instruction following, with our structured prompt outperforming a less structured variant on multi-class datasets, with an average difference of 14.5\%. While language influence on performance was modest, model selection proved crucial: Phi-3.5 MoE excelled in balanced accuracy, particularly for binary classification, while Mistral NeMo showed superior performance in mean absolute error for severity prediction tasks. Few-shot prompting consistently improved performance, with particularly substantial gains observed for GPT-4o Mini on multi-class classification, boosting accuracy by an average factor of 1.58. These findings underscore the importance of prompt optimization, multilingual analysis, and few-shot learning for developing culturally sensitive and effective LLM-based mental health tools for Arabic-speaking populations.

cs.CL↗

arXiv2024

Chimera: A Block-Based Neural Architecture Search Framework for Event-Based Object Detection

Event-based cameras are sensors that simulate the human eye, offering advantages such as high-speed robustness and low power consumption. Established Deep Learning techniques have shown effectiveness in processing event data. Chimera is a Block-Based Neural Architecture Search (NAS) framework specifically designed for Event-Based Object Detection, aiming to create a systematic approach for adapting RGB-domain processing methods to the event domain. The Chimera design space is constructed from various macroblocks, including Attention blocks, Convolutions, State Space Models, and MLP-mixer-based architectures, which provide a valuable trade-off between local and global processing capabilities, as well as varying levels of complexity. The results on the PErson Detection in Robotics (PEDRo) dataset demonstrated performance levels comparable to leading state-of-the-art models, alongside an average parameter reduction of 1.6 times.

cs.CV↗

arXiv2024

Automated Multi-Label Annotation for Mental Health Illnesses Using Large Language Models

The growing prevalence and complexity of mental health disorders present significant challenges for accurate diagnosis and treatment, particularly in understanding the interplay between co-occurring conditions. Mental health disorders, such as depression and Anxiety, often co-occur, yet current datasets derived from social media posts typically focus on single-disorder labels, limiting their utility in comprehensive diagnostic analyses. This paper addresses this critical gap by proposing a novel methodology for cleaning, sampling, labeling, and combining data to create versatile multi-label datasets. Our approach introduces a synthetic labeling technique to transform single-label datasets into multi-label annotations, capturing the complexity of overlapping mental health conditions. To achieve this, two single-label datasets are first merged into a foundational multi-label dataset, enabling realistic analyses of co-occurring diagnoses. We then design and evaluate various prompting strategies for large language models (LLMs), ranging from single-label predictions to unrestricted prompts capable of detecting any present disorders. After rigorously assessing multiple LLMs and prompt configurations, the optimal combinations are identified and applied to label six additional single-disorder datasets from RMHD. The result is SPAADE-DR, a robust, multi-label dataset encompassing diverse mental health conditions. This research demonstrates the transformative potential of LLM-driven synthetic labeling in advancing mental health diagnostics from social media data, paving the way for more nuanced, data-driven insights into mental health care.

cs.AI↗

arXiv2024

SoftmAP: Software-Hardware Co-design for Integer-Only Softmax on Associative Processors

Recent research efforts focus on reducing the computational and memory overheads of Large Language Models (LLMs) to make them feasible on resource-constrained devices. Despite advancements in compression techniques, non-linear operators like Softmax and Layernorm remain bottlenecks due to their sensitivity to quantization. We propose SoftmAP, a software-hardware co-design methodology that implements an integer-only low-precision Softmax using In-Memory Compute (IMC) hardware. Our method achieves up to three orders of magnitude improvement in the energy-delay product compared to A100 and RTX3090 GPUs, making LLMs more deployable without compromising performance.

cs.AR↗

arXiv2024

BF-IMNA: A Bit Fluid In-Memory Neural Architecture for Neural Network Acceleration

Mixed-precision quantization works Neural Networks (NNs) are gaining traction for their efficient realization on the hardware leading to higher throughput and lower energy. In-Memory Computing (IMC) accelerator architectures are offered as alternatives to traditional architectures relying on a data-centric computational paradigm, diminishing the memory wall problem, and scoring high throughput and energy efficiency. These accelerators can support static fixed-precision but are not flexible to support mixed-precision NNs. In this paper, we present BF-IMNA, a bit fluid IMC accelerator for end-to-end Convolutional NN (CNN) inference that is capable of static and dynamic mixed-precision without any hardware reconfiguration overhead at run-time. At the heart of BF-IMNA are Associative Processors (APs), which are bit-serial word-parallel Single Instruction, Multiple Data (SIMD)-like engines. We report the performance of end-to-end inference of ImageNet on AlexNet, VGG16, and ResNet50 on BF-IMNA for different technologies (eNVM and NVM), mixed-precision configurations, and supply voltages. To demonstrate bit fluidity, we implement HAWQ-V3's per-layer mixed-precision configurations for ResNet18 on BF-IMNA using different latency budgets, and results reveal a trade-off between accuracy and Energy-Delay Product (EDP): On one hand, mixed-precision with a high latency constraint achieves the closest accuracy to fixed-precision INT8 and reports a high (worse) EDP compared to fixed-precision INT4. On the other hand, with a low latency constraint, BF-IMNA reports the closest EDP to fixed-precision INT4, with a higher degradation in accuracy compared to fixed-precision INT8. We also show that BF-IMNA with fixed-precision configuration still delivers performance that is comparable to current state-of-the-art accelerators: BF-IMNA achieves $20\%$ higher energy efficiency and $2\%$ higher throughput.

cs.AR↗

arXiv2024

A Recurrent YOLOv8-based framework for Event-Based Object Detection

Object detection is crucial in various cutting-edge applications, such as autonomous vehicles and advanced robotics systems, primarily relying on data from conventional frame-based RGB sensors. However, these sensors often struggle with issues like motion blur and poor performance in challenging lighting conditions. In response to these challenges, event-based cameras have emerged as an innovative paradigm. These cameras, mimicking the human eye, demonstrate superior performance in environments with fast motion and extreme lighting conditions while consuming less power. This study introduces ReYOLOv8, an advanced object detection framework that enhances a leading frame-based detection system with spatiotemporal modeling capabilities. We implemented a low-latency, memory-efficient method for encoding event data to boost the system's performance. We also developed a novel data augmentation technique tailored to leverage the unique attributes of event data, thus improving detection accuracy. Our models outperformed all comparable approaches in the GEN1 dataset, focusing on automotive applications, achieving mean Average Precision (mAP) improvements of 5%, 2.8%, and 2.5% across nano, small, and medium scales, respectively.These enhancements were achieved while reducing the number of trainable parameters by an average of 4.43% and maintaining real-time processing speeds between 9.2ms and 15.5ms. On the PEDRo dataset, which targets robotics applications, our models showed mAP improvements ranging from 9% to 18%, with 14.5x and 3.8x smaller models and an average speed enhancement of 1.67x.

cs.CV↗

arXiv2024

Network architecture search of X-ray based scientific applications

X-ray and electron diffraction-based microscopy use bragg peak detection and ptychography to perform 3-D imaging at an atomic resolution. Typically, these techniques are implemented using computationally complex tasks such as a Psuedo-Voigt function or solving a complex inverse problem. Recently, the use of deep neural networks has improved the existing state-of-the-art approaches. However, the design and development of the neural network models depends on time and labor intensive tuning of the model by application experts. To that end, we propose a hyperparameter (HPS) and neural architecture search (NAS) approach to automate the design and optimization of the neural network models for model size, energy consumption and throughput. We demonstrate the improved performance of the auto-tuned models when compared to the manually tuned BraggNN and PtychoNN benchmark. We study and demonstrate the importance of the exploring the search space of tunable hyperparameters in enhancing the performance of bragg peak detection and ptychographic reconstruction. Our NAS and HPS of (1) BraggNN achieves a 31.03\% improvement in bragg peak detection accuracy with a 87.57\% reduction in model size, and (2) PtychoNN achieves a 16.77\% improvement in model accuracy and a 12.82\% reduction in model size when compared to the baseline PtychoNN model. When inferred on the Orin-AGX platform, the optimized Braggnn and Ptychonn models demonstrate a 10.51\% and 9.47\% reduction in inference latency and a 44.18\% and 15.34\% reduction in energy consumption when compared to their respective baselines, when inferred in the Orin-AGX edge platform.

cs.LG↗