Loading Now

Summary of 3d Building Generation in Minecraft Via Large Language Models, by Shiying Hu et al.


3D Building Generation in Minecraft via Large Language Models

by Shiying Hu, Zengrong Huang, Chengpeng Hu, Jialin Liu

First submitted to arxiv on: 13 Jun 2024

Categories

  • Main: Artificial Intelligence (cs.AI)
  • Secondary: None

     Abstract of paper      PDF of paper


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
A recently proposed procedural content generation method using large language models (LLMs) has demonstrated promising results in generating 2D game levels. This paper investigates whether LLMs can also be applied to generate 3D buildings in Minecraft, a sandbox game. To achieve this, the authors propose a Text-to-Building in Minecraft (T2BM) model that refines prompts, decodes interlayer representations, and repairs buildings. The generated structures include facades, indoor scenes, and functional blocks like doors. Experiments show that LLMs have significant potential for 3D building generation, successfully producing complete and correct structures with specific elements such as windows and beds, meeting user requirements.
Low GrooveSquid.com (original content) Low Difficulty Summary
Recently, a new way to create game levels using computers has been developed. This method uses large language models (LLMs) to make decisions about what the level should look like. In this paper, scientists try out this idea on a different kind of game: Minecraft. They want to see if LLMs can help build 3D structures in the game. To do this, they created a special program called Text-to-Building in Minecraft (T2BM). This program helps the computer decide what to build and how to fix any mistakes. The scientists tested their idea and found that it worked really well! They were able to create buildings with different parts like facades, windows, and doors. This is important because it shows that computers can be used to make games more fun and interesting.

Keywords

» Artificial intelligence