Lotfi Abdelkrim Mecharbat
Lotfi Abdelkrim Mecharbat has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Ibrahim Almakky
Mohamed bin Zayed University of Artificial Intelligence
2 shared publications - Martin Takáč
MBZUAI Abu Dhabi UAE
2 shared publications - Mohammad Yaqub
Mohamed bin Zayed University of Artificial Intelligence
2 shared publications - Almsouti
Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI)
1 shared publication - Elsayed Abdelrahman
Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI)
1 shared publication - Hadjer Benmeziane
IBM Research Europe, Rüschlikon, Switzerland
1 shared publication
Latest Publications
- 26 September 2026
- Published by Springer Nature
- p. 415-426
MetaVFM: Meta-Learned Efficient Adaptation of Vision Foundation Models for Medical Imaging
- 26 September 2026
- Published by Springer Nature
- p. 415-426
MetaVFM: Meta-Learned Efficient Adaptation of Vision Foundation Models for Medical Imaging
- 19 September 2025
- Published by Springer Nature
- p. 448-458
MedNNS: Supernet-Based Medical Task-Adaptive Neural Network Search
- 19 September 2025
- Published by Springer Nature
- p. 448-458
MedNNS: Supernet-Based Medical Task-Adaptive Neural Network Search
- Open Access
- 21 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 41-45
HyT-NAS: Hybrid Transformers Neural Architecture Search for Edge Devices
Vision Transformers have enabled recent attention-based Deep Learning (DL) architectures to achieve remarkable results in Computer Vision (CV) tasks. However, due to the extensive computational resources required, these architectures are rarely implemented on resource-constrained platforms. Current research investigates hybrid handcrafted convolution-based and attention-based models for CV tasks such as image classification and object detection. In this paper, we propose HyT-NAS, an efficient Hardware-aware Neural Architecture Search (HW-NAS) including hybrid architectures targeting vision tasks on tiny devices. HyT-NAS improves state-of-the-art HW-NAS by enriching the search space and enhancing the search strategy as well as the performance predictors. Our experiments show that HyT-NAS achieves a similar hypervolume with less than 5x training evaluations. Our resulting architecture outperforms MLPerf MobileNetVl by 6.3% accuracy improvement with 3.5x less number of parameters on Visual Wake Words.
- 21 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 41-45
Open AccessHyT-NAS: Hybrid Transformers Neural Architecture Search for Edge Devices
Vision Transformers have enabled recent attention-based Deep Learning (DL) architectures to achieve remarkable results in Computer Vision (CV) tasks. However, due to the extensive computational resources required, these architectures are rarely implemented on resource-constrained platforms. Current research investigates hybrid handcrafted convolution-based and attention-based models for CV tasks such as image classification and object detection. In this paper, we propose HyT-NAS, an efficient Hardware-aware Neural Architecture Search (HW-NAS) including hybrid architectures targeting vision tasks on tiny devices. HyT-NAS improves state-of-the-art HW-NAS by enriching the search space and enhancing the search strategy as well as the performance predictors. Our experiments show that HyT-NAS achieves a similar hypervolume with less than 5x training evaluations. Our resulting architecture outperforms MLPerf MobileNetVl by 6.3% accuracy improvement with 3.5x less number of parameters on Visual Wake Words.