Learning with few labeled data has been a longstanding problem in the computer vision and
machine learning research community. In this paper, we introduced a new semi-supervised …

Recently neural architecture (NAS) search has attracted great interest in academia and
industry. It remains a challenging problem due to the huge search space and computational …

We investigate the potential of GPT-4~\cite {gpt4} to perform Neural Architecture Search
(NAS)--the task of designing effective neural architectures. Our proposed approach,\textbf …

Abstract Human-Object Interaction (HOI) detection is a challenging computer vision task that
requires visual models to address the complex interactive relationship between humans and …

This paper studies using foundational large language models (LLMs) to make decisions
during hyperparameter optimization (HPO). Empirical evaluations demonstrate that in …

Vision transformers (ViTs) are usually considered to be less light-weight than convolutional
neural networks (CNNs) due to the lack of inductive bias. Recent works thus resort to …

Vision transformers (ViTs) inherited the success of NLP but their structures have not been
sufficiently investigated and optimized for visual tasks. One of the simplest solutions is to …

The release of tabular benchmarks, such as NAS-Bench-101 and NAS-Bench-201, has
significantly lowered the computational overhead for conducting scientific research in neural …

Structural re-parameterization (Rep) methods achieve noticeable improvements on simple
VGG-style networks. Despite the prevalence, current Rep methods simply re-parameterize …

Neural Architecture Search (NAS), a promising and fast-moving research field, aims to
automate the architectural design of Deep Neural Networks (DNNs) to achieve better …