LLMER: Crafting Interactive Extended Reality Worlds with JSON Data Generated by Large Language Models
This addresses the challenge of building immersive XR environments with reduced errors and costs for developers and users, though it appears incremental as it builds on existing LLM and XR integration.
The paper tackles the problem of generating interactive Extended Reality (XR) worlds from natural language inputs by introducing LLMER, a framework that uses JSON data from Large Language Models to reduce errors and costs, resulting in over 80% reduction in tokens and around 60% faster task completion compared to state-of-the-art methods.
The integration of Large Language Models (LLMs) like GPT-4 with Extended Reality (XR) technologies offers the potential to build truly immersive XR environments that interact with human users through natural language, e.g., generating and animating 3D scenes from audio inputs. However, the complexity of XR environments makes it difficult to accurately extract relevant contextual data and scene/object parameters from an overwhelming volume of XR artifacts. It leads to not only increased costs with pay-per-use models, but also elevated levels of generation errors. Moreover, existing approaches focusing on coding script generation are often prone to generation errors, resulting in flawed or invalid scripts, application crashes, and ultimately a degraded user experience. To overcome these challenges, we introduce LLMER, a novel framework that creates interactive XR worlds using JSON data generated by LLMs. Unlike prior approaches focusing on coding script generation, LLMER translates natural language inputs into JSON data, significantly reducing the likelihood of application crashes and processing latency. It employs a multi-stage strategy to supply only the essential contextual information adapted to the user's request and features multiple modules designed for various XR tasks. Our preliminary user study reveals the effectiveness of the proposed system, with over 80% reduction in consumed tokens and around 60% reduction in task completion time compared to state-of-the-art approaches. The analysis of users' feedback also illuminates a series of directions for further optimization.