# Low Computational Cost

LSNet is a family of lightweight vision models inspired by the dynamic multi-scale capabilities of the human visual system, achieving a balance between performance and efficiency across various vision tasks.

Hierarchical Distillation (SwD) is a novel framework that accelerates diffusion models (DMs) by progressively increasing spatial resolution during the generation process.

A fast race classification model based on YOLOv8/YOLO11 architecture, trained on the FairFace dataset for facial race classification tasks.

A BERT-LoRA fine-tuned model for efficient detection of malicious URLs, including phishing, malware, and tampering threats.

CED is a simple audio tagging model based on ViT-Transformer, achieving state-of-the-art performance on Audioset.

LeViT-192 is a vision model that combines convolutional neural networks and Transformer architecture, focusing on image classification tasks.

IndicBART-XLSum is a sequence-to-sequence pre-trained model based on the multilingual independent script IndicBART, focusing on Indian languages.

ELECTRA is a self-supervised language representation learning method through discriminative pre-training, achieving efficient training with lower computational costs.

AraELECTRA is an Arabic pre-trained language model based on the ELECTRA architecture, achieving efficient language understanding through discriminative pre-training methods.

An efficient Arabic language model based on Funnel Transformer and ELECTRA objective, with low computational cost and superior performance