Summary of Unbounded: a Generative Infinite Game Of Character Life Simulation, by Jialu Li et al.
Unbounded: A Generative Infinite Game of Character Life Simulation
by Jialu Li, Yuanzhen Li, Neal Wadhwa, Yael Pritch, David E. Jacobs, Michael Rubinstein, Mohit Bansal, Nataniel Ruiz
First submitted to arxiv on: 24 Oct 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Graphics (cs.GR); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper introduces Unbounded, a video game that transcends traditional finite systems by using generative models. Inspired by James P. Carse’s distinction between finite and infinite games, the authors leverage recent advances in generative AI to create a game of character life simulation fully encapsulated in generative models. The game draws inspiration from sandbox life simulations and allows users to interact with their autonomous virtual character in a virtual world through open-ended mechanics generated by a large language model (LLM). To develop Unbounded, the authors propose technical innovations in both LLM and visual generation domains. Specifically, they present a specialized, distilled LLM that dynamically generates game mechanics, narratives, and character interactions in real-time, as well as a dynamic regional image prompt Adapter (IP-Adapter) for vision models ensuring consistent yet flexible visual generation of characters across multiple environments. The system is evaluated through both qualitative and quantitative analysis, showing significant improvements in character life simulation, user instruction following, narrative coherence, and visual consistency compared to traditional approaches. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a new kind of video game called Unbounded that uses artificial intelligence (AI) to generate gameplay. Instead of being limited by rules or code, the game lets players interact with their own virtual characters in a simulated world. The authors used special AI models to make this happen and tested it against other approaches. |
Keywords
» Artificial intelligence » Large language model » Prompt
