CoDi-2: In-Context Interleaved and Interactive Any-to-Any Generation

[PDF] arxiv.org

The Evolution of Multimodal Model Architectures

SN Wadekar, A Chaurasia, A Chadha… - arXiv preprint arXiv …, 2024 - arxiv.org
This work uniquely identifies and characterizes four prevalent multimodal model
architectural patterns in the contemporary multimodal landscape. Systematically …
相关文章 所有 4 个版本
[PDF] arxiv.org

Visual Echoes: A Simple Unified Transformer for Audio-Visual Generation

S Yang, Z Zhong, M Zhao, S Takahashi, M Ishii… - arXiv preprint arXiv …, 2024 - arxiv.org
In recent years, with the realistic generation results and a wide range of personalized
applications, diffusion-based generative models gain huge attention in both visual and …
被引用次数：1 相关文章 所有 2 个版本