Ahmed Radwan

Contrastive Predictive Coding with Compression for Enhanced Channel State Feedback in Wireless Networks

Soon

Ahmed Y. Radwan, Hina Tabassum, Fahad Syed Muhammad, Matthew Baker

First author of a research paper enhancing CSI feedback in 3GPP’s next release using AI-driven compression. We propose two CPC-based architectures to tackle data aging and channel variations, achieving superior SGCS performance on industry datasets (Nokia, Oppo, CATT). Additionally, we explore GRU pruning for real-time deployment and discuss future directions like split learning and adaptive online strategies.

A Tutorial-cum-Survey on Self-Supervised Learning for Wi-Fi Sensing: Trends, Challenges, and Outlook

IEEE COMST

Ahmed Y. Radwan, Mustafa Yildirim, Navid Hasanzadeh, Hina Tabassum, and Shahrokh Valaee

First author of a comprehensive survey on Wi-Fi sensing, where we explore its evolution from communication routers to sensing devices. Our work delves into channel state information (CSI) extraction, dataset comparisons, and the impact of mobile objects on CSI. We discuss preprocessing techniques for feature extraction, highlight the role of machine learning (ML) and self-supervised learning (SSL) in Wi-Fi sensing, and provide a quantitative analysis of contrastive and non-contrastive learning approaches. The paper concludes with insights into emerging technologies and future research opportunities in this field

TinyML NLP Scheme for Semantic Wireless Sentiment Classification with Privacy Preservation

EuCNC & 6G Summit 2025

Ahmed Y. Radwan, Mohammad Shehab, Mohamed-Slim Alouini

First author of a study on privacy-preserving, energy-efficient NLP for edge devices. We propose semantic split learning (SL) as a TinyML framework, outperforming FL and CL in energy efficiency and privacy, with significantly higher reconstruction error and lower CO2 emissions.

SARD: A Human-AI Collaborative Story Generation

HCI International 2024

Ahmed Y. Radwan, Khaled M. Alasmari, Omar A. Abdulbagi, Emad A. Alghamdi

First author of SARD, a drag-and-drop interface for multi-chapter story generation using LLMs. Our study shows that while node-based visualization aids mental modeling, it adds cognitive load as stories grow. We also find AI-generated stories lack lexical diversity, highlighting patterns and limitations for future human-AI co-writing tools.

Addressing Bias Through Ensemble Learning and Regularized Fine-Tuning

Preprint

Ahmed Y. Radwan, Layan Zaafarani, Jetana Abudawood, Faisal AlZahrani, Fares Fourati

First author of a preprint proposing a novel approach to reduce bias in AI models with limited data. Method combines fine-tuning, ensemble learning, and knowledge distillation, demonstrating improved fairness on CIFAR-10 and HAM10000 datasets.

Humanibench: A Human-Centric Framework for Large Multimodal Models Evaluation

arXiv preprint (2025)

Shaina Raza, Aravind Narayanan, Vahid Reza Khazaie, Ashmal Vayani, Ahmed Y. Radwan, Mukund S Chettiar, Amandeep Singh, Mubarak Shah, Deval Pandya

Co-author of Humanibench, a unified evaluation framework for multimodal models grounded in human-centered principles (fairness, ethics, inclusivity, empathy, and robustness), spanning realistic visual contexts and multiple tasks (e.g., VQA, multilinguality, visual grounding, empathetic captioning).

Reducing Hallucinations in LLMs via Factuality-Aware Preference Learning

arXiv preprint (2026)

Sindhuja Chaduvula, Ahmed Y. Radwan, Azib Farooq, Yani Ioannou, Shaina Raza

Co-author of a preference-learning method (F-DPO) that targets factuality directly, improving factuality scores while reducing hallucination rates across multiple open-weight LLMs.

SONIC-O1 (Vector Institute)

A real-world benchmark + end-to-end pipeline for omnimodal video understanding (audio + video + social context), with systematic fairness analysis across demographic groups.

SARD: Images-Inspired Narratives

Developed a novel visual interface for AI-assisted story generation, leading design, implementation, and user studies.

Addressing Bias Framework in DL models

Co-authored preprint proposing a novel approach to reduce bias in AI models with limited data. Method combines fine-tuning, ensemble learning, and knowledge distillation, demonstrating improved fairness on CIFAR-10 and HAM10000 datasets.

Skin Cancer Classification

Developed a model for image classification using data loading techniques and Convolutional Neural Network using Keras.

PerfectPrayer

Developed and deployed a real-time Rak'ah tracking system for Salah on Android phones and watches. The project utilizes IMU sensors for motion recognition and features an enhanced Android app that provides real-time accuracy and error detection, ensuring reliable and user-friendly performance.

Fairness-Aware Medical Imaging

Implemented adversarial and balanced fine-tuning strategies to reduce demographic bias in chest X-ray classification. Improved fairness across gender, race, and insurance groups while maintaining diagnostic accuracy on real-world medical data.