MetaAID 2.0: An Extensible Framework for Developing Metaverse Applications via Human-controllable Pre-trained Models
It addresses the need for more ethical and controllable AI-generated content in metaverse applications, though it appears incremental as an extension of existing frameworks.
The paper tackles the problem of uncontrollable and potentially unethical content generation by pre-trained models, presenting the MetaAID 2.0 framework that enables human-controllable information flow and responsibility management, with experiments showing good performance.
Pre-trained models (PM) have achieved promising results in content generation. However, the space for human creativity and imagination is endless, and it is still unclear whether the existing models can meet the needs. Model-generated content faces uncontrollable responsibility and potential unethical problems. This paper presents the MetaAID 2.0 framework, dedicated to human-controllable PM information flow. Through the PM information flow, humans can autonomously control their creativity. Through the Universal Resource Identifier extension (URI-extension), the responsibility of the model outputs can be controlled. Our framework includes modules for handling multimodal data and supporting transformation and generation. The URI-extension consists of URI, detailed description, and URI embeddings, and supports fuzzy retrieval of model outputs. Based on this framework, we conduct experiments on PM information flow and URI embeddings, and the results demonstrate the good performance of our system.