Mohammed Elbtity

University of South Carolina

Papers

1

Total Citations

12

H-Index

1

About

Mohammed Elbtity is a rising researcher at the forefront of efficient deep learning, with a primary focus on deploying Transformer models on resource-constrained edge AI accelerators. His work addresses a critical bottleneck in modern AI: bridging the gap between the computational demands of state-of-the-art architectures and the limited power of mobile and embedded devices. His most-cited paper, "Work in Progress: Real-time Transformer Inference on Edge AI Accelerators" (2023, 12 citations), explores novel optimization strategies for achieving real-time performance, a key step toward enabling advanced NLP and computer vision applications on smartphones and IoT devices. This contribution is particularly timely as Transformers continue to dominate machine learning benchmarks. Elbtity’s research is characterized by its practical orientation, aiming to make high-performance AI accessible beyond cloud infrastructure. As a young investigator, his work signals a promising trajectory in the critical area of model compression and hardware-aware deployment, with potential implications for autonomous systems, healthcare wearables, and smart sensors.

Research Focus

Key Achievements

1
H-Index
1
Papers
12
Total Citations
12
Avg Citations/Paper
🏆 Most Cited Paper
Work in Progress: Real-time Transformer Inference on Edge AI Accelerators
12 citations · 2023
📈 Most Prolific Year: 2023 (1 Papers)
🤝 Key Collaborators: 4
🏛 Institutions: University of South Carolina

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 15 days ago