This paper presents FLOAT, an audio-driven talking portrait video generation method based on flow matching generative model. We shift the generative modeling from the pixel-based latent space to a ...

Generative models have shown robust performance on speech enhancement and restoration tasks, but most prior approaches operate offline with high latency, making them unsuitable for streaming ...

Abstract: We propose a novel generative speech enhancement (SE) framework that integrates a language model (LM) and a flow-matching model. To utilize an LM with discrete tokens, we introduce dMel, ...

Modeling interactive driving behaviors in complex scenarios remains a fundamental challenge for autonomous driving planning. Learning-based approaches attempt to address this challenge with advanced ...

OSWEGO — Kevin Waters wasn’t satisfied with his tournament golf performances for much of the past year. That changed emphatically this week as the recent Oswego High School graduate advanced to the ...

Deep generative models, including diffusion and flow matching, have shown outstanding performance in synthesizing realistic multi-modal content across images, audio, video, and text. However, the ...