LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents
This addresses the need for more capable multimodal AI agents for real-world applications, though it appears incremental by building on existing models.
The paper tackles the problem of enhancing large multimodal models by developing LLaVA-Plus, a general-purpose multimodal assistant that uses a skill repository of pre-trained models to activate tools for tasks like visual understanding and generation, resulting in improved performance over LLaVA and enabling new capabilities.
LLaVA-Plus is a general-purpose multimodal assistant that expands the capabilities of large multimodal models. It maintains a skill repository of pre-trained vision and vision-language models and can activate relevant tools based on users' inputs to fulfill real-world tasks. LLaVA-Plus is trained on multimodal instruction-following data to acquire the ability to use tools, covering visual understanding, generation, external knowledge retrieval, and compositions. Empirical results show that LLaVA-Plus outperforms LLaVA in existing capabilities and exhibits new ones. It is distinct in that the image query is directly grounded and actively engaged throughout the entire human-AI interaction sessions, significantly improving tool use performance and enabling new scenarios.