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.

 

Atlas Learns To Be Useful 15/06/2025 Boston Dynamics next generation electric, as opposed to hydraulic, Atlas Robot is less messy than its predecessor which left a thin film of hydraulic fluid in its wake. Thanks to AI, Atlas is qui [ ... ] + Full Story

Court Rejects Apple's Appeal - An Epic Win 06/06/2025 Apple's latest attempt to maintain full financial control over the App Store has failed, allowing Fortite to stay in the App Store and Epic to use external methods for in-app purchases. + Full Story

More News Linux Foundation Launches Agent2Agent Project ACM Grace Hopper Award Recognizes Breakthrough Techniques in Algorithm Design Student’s Robot Smashes 4x4 Rubik’s Cube World Record CouchDB Adds Support For Truly Parallel Reads Konrad Zuse Born On This Day In 1910 Stack Overflow Strives To Survive In Era Of AI Microsoft's RAG Time Three Tools To Run MCP On Your Github Repositories Closer To A Proof That P!= PSPACE SQL and Assembly Language In Decline In TIOBE Index pg_disatch - Run SQL Queries Asynchronously On PostgreSQL Swift 6.2 Adds WebAssembly Support Unemployment Rate High Among US CS Graduates

 

Comments

Make a Comment or View Existing Comments Using Disqus

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