Data-driven methods such as reinforcement and imitation learning have achieved
remarkable success in robot autonomy. However, their data-centric nature still hinders them …

With the growth of the industrial internet of things, the poor performance of conventional
deep learning models hinders the application of intelligent diagnosis methods in industrial …

Meta-learning has emerged as a powerful approach for leveraging knowledge from previous
tasks to solve new tasks. The mainstream methods focus on training a well-generalized …

Large language models (LLMs) are trained on a vast amount of human-written data, but data
providers often remain uncredited. In response to this issue, data valuation (or data …

Resolution Enhancement Techniques (RETs) are critical to meet the demands of advanced
technology nodes. Among RETs, Source Mask Optimization (SMO) is pivotal, concurrently …

Gradient-based hyperparameter optimization methods update hyperparameters using
hypergradients, gradients of a meta criterion with respect to hyperparameters. Previous …

In the evolving landscape of federated learning (FL), the integration of multimodal data
presents both unprecedented opportunities and significant challenges. Existing works fall …

Demand prediction is a crucial task for e-commerce and physical retail businesses,
especially during high-stake sales events. However, the limited availability of historical data …

Bi-level optimization (BO) has become a fundamental mathematical framework for
addressing hierarchical machine learning problems. As deep learning models continue to …

Masked Autoencoder (MAE) is a notable method for self-supervised pretraining in visual
representation learning. It operates by randomly masking image patches and reconstructing …