AI"s inability to continually learn remains one of the biggest problems standing in the way to truly general purpose models.

Abstract: Parallel computing is a fundamental technique in modern software development, enabling the efficient execution of large-scale computations by distributing workloads across multiple ...

We propose FreeDave (Free Draft-and-Verification), a fast sampling algorithm for diffusion language models, which achieves lossless parallel decoding via a pipeline of parallel-decoded candidate ...

Abstract: In recent years, visual-based sign language recognition (SLR) has become an active research area with the advancement of deep learning. However, it is difficult to collect sign language data ...