Octopus v3: Technical Report for On-device Sub-billion Multimodal AI Agent

arXiv:2404.11459v1 Announce Type: cross
Abstract: A multimodal AI agent is characterized by its ability to process and learn from various types of data, including natural language, visual, and audio inputs, to inform its actions. Despite advancements in large language models that incorporate visual data, such as GPT-4V, effectively translating image-based data into actionable outcomes for AI agents continues to be challenging. In this paper, we introduce a multimodal model that incorporates the concept of functional token specifically designed for AI …

abstract agent arxiv audio billion cs.cl cs.cv data gpt gpt-4v image inputs language language models large language large language models learn multimodal multimodal ai natural natural language process report technical type types visual visual data