A fundamental question in theoretical machine learning is generalization. Over the past
decades, the PAC-Bayesian approach has been established as a flexible framework to …

Abstract Physics-Informed Neural Networks (PINNs) have proven effective in solving partial
differential equations (PDEs), especially when some data are available by seamlessly …

Diffusion-based generative methods have proven effective in modeling trajectories with
offline datasets. However, they often face computational challenges and can falter in …

Variance-Invariance-Covariance Regularization (VICReg) is a self-supervised learning
(SSL) method that has shown promising results on a variety of tasks. However, the …

As machine learning has been deployed ubiquitously across applications in modern data
science, algorithmic fairness has become a great concern. Among them, imposing fairness …

Deep neural networks are susceptible to catastrophic forgetting when trained on sequential
tasks. Various continual learning (CL) methods often rely on exemplar buffers or/and …

The booming use of text-to-image generative models has raised concerns about their high
risk of producing copyright-infringing content. While probabilistic copyright protection …

While physics-informed neural networks (PINNs) have been proven effective for low-
dimensional partial differential equations (PDEs), the computational cost remains a hurdle in …

Conscious states—state that there is something it is like to be in—seem both rich or full of
detail and ineffable or hard to fully describe or recall. The problem of ineffability, in particular …

Creativity serves as a cornerstone for societal progress and innovation. With the rise of
advanced generative AI models capable of tasks once reserved for human creativity, the …