SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation

arXiv:2404.14396v1 Announce Type: new
Abstract: The rapid evolution of multimodal foundation model has demonstrated significant progresses in vision-language understanding and generation, e.g., our previous work SEED-LLaMA. However, there remains a gap between its capability and the real-world applicability, primarily due to the model's limited capacity to effectively respond to various user instructions and interact with diverse visual data. In this work, we focus on bridging this gap through integrating two enhanced features: (1) comprehending images of arbitrary sizes and ratios, …

arxiv cs.cv multimodal multimodal models seed type