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 ...

Abstract: Imitation learning is a promising approach for enabling generalist capabilities in humanoid robots, but its scaling is fundamentally constrained by the scarcity of highquality expert ...

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 ...

Semantic SEO helps search engines understand context. Learn how to use entities, topics, and intent to build richer content that ranks higher. Semantic SEO aims to describe the relationships between ...

While methods exist for aligning flow matching models — a popular and effective class of generative models — with human preferences, existing approaches fail to achieve both adaptation efficiency and ...

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 ...

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 ...

Multimodal modeling focuses on building systems to understand and generate content across visual and textual formats. These models are designed to interpret visual scenes and produce new images using ...