Abstract Optimizing Deep Neural Networks (DNNs) to obtain high-quality models for efficient
real-world deployment has posed multi-faceted challenges to machine learning engineers …

Abstract Vision Transformer (ViT) has prevailed among computer vision tasks for its powerful
capability of image representation recently. Frustratingly, the manual design of efficient …

Recent advancements in Zero-shot Neural Architecture Search (NAS) highlight the efficacy
of zero-cost proxies in various NAS benchmarks. Several studies propose the automated …

Abstract Neural Architecture Search is a costly practice. The fact that a search space can
span a vast number of design choices with each architecture evaluation taking nontrivial …

Neural predictors (NPs) aim to swiftly evaluate architectures during the neural architecture
search (NAS) process. Precise evaluations with NPs heavily depend on the representation …

The rise of neural architecture search (NAS) demonstrates the deep exploration between the
neural network architecture and its performance (eg, accuracy). Many NAS methods are …

An efficient hardware-aware neural architecture search is crucial for automating the creation
of network architectures that are optimized for resource-limited platforms. However …

Training-free metrics (aka zero-cost proxies) are widely used to avoid resource-intensive
neural network training, especially in Neural Architecture Search (NAS). Recent studies …

With the blossom of deep learning models and services, it has become an imperative
concern to safeguard the valuable model parameters from being stolen. Watermarking is …

Revolutionizing the field of deep learning Transformer-based models have achieved
remarkable performance in many tasks. Recent research has recognized these models are …