About
Research & Development
AI Adapts to the Unexpected: Exploring Novelty in Board Games with GNOME
TLDR: GNOME (Generating Novelty in Open-world Multi-agent Environments) is a simulation platform designed to test how multi-agent AI systems adapt to unexpected changes, or...
Research & Development
AI-Powered Framework for Extracting Relationships from Data
TLDR: RELRaE is a novel framework that leverages Large Language Models (LLMs) to automate and enhance the process of converting semi-structured XML data into...
Research & Development
Guiding Digital Life: A New Era of Human-AI Collaboration Through Language
TLDR: A novel semantic feedback framework enables natural language to guide the evolution of artificial life systems. By integrating a prompt-to-parameter encoder, a CMA-ES...
Research & Development
Enhancing Database Query Performance with AI-Powered Hint Recommendations
TLDR: LLM4Hint is a new framework that uses Large Language Models (LLMs) combined with a lightweight model to recommend optimal hints for database query...
Research & Development
Reverger: An AI Tool for Iterative Story Development
TLDR: Reverger is a new AI-powered tool designed to enhance creative story ideation by supporting flexible, recursive iteration between divergent thinking (exploring diverse ideas)...
Research & Development
Advancing AI Adaptation Without Source Data: A New Approach with Multi-view Contrastive Learning
TLDR: This paper introduces a novel Source-Free Unsupervised Domain Adaptation (SFUDA) method that addresses challenges of low-quality prototype samples and incorrect pseudo-labels. It proposes...