Hazem Hesham Yousef Shalby

Hazem Hesham Yousef Shalby

Auto-generated profile, based on publicly available information

Hazem Hesham Yousef Shalby

Politecnico di Milano, Milan, Italy

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 March 2026 in Neural Networks
Verified
Journal Article
Open access
RBRiccardo Bravin
Riccardo Bravin
MPMassimo Pavan
Massimo Pavan
HSHazem Hesham Yousef Shalby
Hazem Hesham Yousef Shalby
FPFabrizio Pittorino
Fabrizio Pittorino
Manuel RoveriManuel Roveri
Manuel Roveri
Transformer architectures based on the attention mechanism have revolutionized natural language processing (NLP), driving major breakthroughs across virtually every NLP task. However, their substantial memory and computational requirements still hinder deployment on ultra-constrained devices such as wearables and Internet-of-Things (IoT) units, where available memory is limited to just a few megabytes. To address this challenge, we introduce EmbBERT, a tiny language model (TLM) architecturally designed for extreme efficiency. The model integrates a compact embedding layer, streamlined feed-forward blocks, and an efficient attention mechanism that together enable optimal performance under strict memory budgets. Through this redesign for the extreme edge, we demonstrate that highly simplified transformer architectures remain remarkably effective under tight resource constraints. EmbBERT requires only 2 MB of total memory, and achieves accuracy performance comparable to the ones of state-of-the-art (SotA) models that require a 10 × memory budget. Extensive experiments on the curated TinyNLP benchmark and the GLUE suite confirm that EmbBERT achieves competitive accuracy, comparable to that of larger SotA models, and consistently outperforms downsized versions of BERT and MAMBA of similar size. Furthermore, we demonstrate the model's resilience to 8-bit quantization, which further reduces memory usage to just 781 kB, and the scalability of the EmbBERT architecture across the sub-megabyte to tens-of-megabytes range. Finally, we perform an ablation study demonstrating the positive contributions of all components and the pre-training procedure. All code, scripts, and checkpoints are publicly released to ensure reproducibility: https://github.com/RiccardoBravin/tiny-LLM.

21 April 2026 in IEEE Sensors Journal
Verified
Journal Article
Closed access
HSHazem Hesham Yousef Shalby
Hazem Hesham Yousef Shalby
JMJulian Moosmann
Julian Moosmann
DTDiana Trojaniello
Diana Trojaniello
Michele MagnoMichele Magno
Michele Magno
Manuel RoveriManuel Roveri
Manuel Roveri
Recent advances have enabled deep object detection on low-power edge devices, such as smart glasses, yet these systems remain static after deployment, unable to learn new objects in the field. We present Cerberus, an on-device continuous learning architecture tailored for resource-constrained processors, enabling efficient model updates without full model retraining. Cerberus employs a lightweight multi-head structure, where each head specializes in a single object class, mitigating catastrophic forgetting while maintaining minimal computational and memory overhead. Evaluated on the PAS-CAL Visual Object Classes (VOC) benchmark, our method demonstrates superior performance in data-scarce scenarios, matching or exceeding unconstrained off-device baselines even when trained with only 1% of available labeled data. For example, when learning 5 new classes incrementally after initial training on 15 classes, Cerberus achieves 48.6 mAP@0.5 compared to 29.2 for a replay-based baseline and 34.8 for a fine-tuning baseline, while reducing sample storage requirements by over 20×. We demonstrate end-to-end deployment on a novel low-power multi-core RISC-V processor, achieving an inference latency of only 66.14ms with an energy cost of 5.49mJ. Notably, learning a new class requires only 9 KB of additional memory, and just 29.65mJ per training update, showcasing the feasibility of sustained on-device adaptive perception in battery-powered edge systems, including wearable applications, with an estimated battery life of approximately 22 hours.