LegoGPT is an AI model that creates physically stable Lego structures from text prompts. Not only does it design Lego models that match text-supplied descriptions, it also ensures they can be built brick by brick in the real world, either by hand or with robotic assistance.

LegoGPT, which comes from Carnegie Mellon University, is outlined in a paper titled "Generating Physically Stable and Buildable Lego Designs from Text". In it the authors, led by Ava Pun explain that while many existing 3D generation models focus on making diverse objects with detailed geometry, such designs often can't be physically made commenting:

"Without proper support, parts of the design can collapse, float, or remain disconnected" 

By contrast their AI-generated LEGO structures are physically stable and are buildable.

To build LegoGPT, the Carnegie Mellon team repurposed the technology behind large language models (LLMs), similar to the kind that run ChatGPT, for "next-brick prediction" instead of next-word prediction. To do so, the team fine-tuned LLaMA-3.2-1B-Instruct, an instruction-following language model from Meta.

The team then augmented the brick-predicting model with a separate software tool that can verify physical stability using mathematical models that simulate gravity and structural forces.

To train the model, the team assembled a new dataset,  "StableText2Lego," containing over 47,000 stable Lego structures paired with descriptive captions generated by a separate AI model, OpenAI's GPT-4o. Each structure underwent physics analysis to ensure it could be built in the real world. 

The paper reports that LegoGPT produces stable, diverse, and aesthetically pleasing LEGO designs that align closely with the input text prompts and that our designs can be assembled manually by humans and automatically by robotic arms:

The project is open source on GitHub and there's a Demo on Hugging Face if you want to try it out.

More Information 

Generating Physically Stable and Buildable LEGO Designs from Text by Ava Pun, Kangle Deng, Ruixuan Liu, Deva Ramanan, Changliu Liu, Jun-Yan Zhu

LegoGPT on GitHub

Related Articles

AI Builds Lego From The Manual

DIY AI To Sort 2 Metric Tons Of Lego

A Worm's Mind In A Lego Body

A Turing Machine In LEGO

Lego Difference Engine

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.

 

Java Agent Development Kit Goes GA 19/08/2025 This is the general availability of the Java's interface to Google's Agent Development Kit, the toolkit for building smart AI agents. + Full Story

Copilot Diagnostics Toolset for .NET In Visual Studio 02/09/2025 Microsoft has added a new diagnostics toolset for .NET development in Visual Studio. The Copilot Diagnostics for .NET is integrated with GitHub Copilot and aims to cut out the repetitive, tedious [ ... ] + Full Story

More News One Thousand Wooden Block Display With MCP Docs Servers You'll Never Run Out Of Fresh Documentation Google Gets To Keep Chrome Record Level Of Interest In Google Summer of Code 2025 jQuery 4.0.0 Close To Release Robot Mall, A Bejing 4S Store Rubrik Introduces Agent Rewind To Undo AI Mistakes AI Finds Vulnerabilities - Not Everyone Is Happy Python - The Documentary Hour Of AI With Funding From Microsoft Elevate Go 1.35 Adds Experimental Garbage Collector DocumentDB Joins Linux Foundation Apache Netbeans 27 Adds Gradle Fixes

 

Comments

Make a Comment or View Existing Comments Using Disqus

or email your comment to: comments@i-programmer.info