@berryxia: Folks, 3D asset generation is truly taking off. A team led by Assistant Professor Elliott Wu (former Stanford, Oxford background) at the University of Cambridge just released Articraft — a true agentic coding system. It doesn't just generate static 3D models, it...
Summary
The team of Assistant Professor Elliott Wu from the University of Cambridge released Articraft — an agentic coding system that can automatically generate interactive 3D assets with parts, joints, and realistic motion, and open-sourced the Articraft-10K dataset, significantly lowering the asset threshold for robot training and physical AI.
View Cached Full Text
Cached at: 05/16/26, 09:17 AM
Brothers, 3D asset generation is about to take off completely.
Elliott Wu, Assistant Professor at Cambridge (formerly Stanford, Oxford), and his team just released Articraft — a truly agentic coding system.
It doesn’t just generate static 3D models. Instead, it lets an AI agent write its own code, execute it, receive physics validation feedback, iterate, and ultimately output interactive 3D assets with parts, joints, and realistic motion — ready to plug directly into robot simulations and physical AI scenarios.
Previously, creating a high-quality articulated asset took days or even weeks. Now the agent handles everything automatically, and the whole process is ridiculously efficient.
They also open-sourced the Articraft-10K dataset: over 10,000 articulated 3D objects across 250 categories, all interactive and simulation-ready. This drastically lowers the asset barrier for large-scale robot training and physical world AI.
The “data hunger” problem in physical AI and robot simulation has been largely addressed by this agentic pipeline.
Project page: https://articraft3d.github.io
Full code and dataset are open-sourced on GitHub as well.
If you work on robotics, simulation, physical AI, or 3D content generation, this open-source release is worth trying immediately.
PS: Not tested yet — review coming later!
Elliott / Shangzhe Wu (@elliottszwu): Check out Ariticraft 🦾 - a highly efficient agentic system that generates articulated 3D assets fully automatically at scale!
🚀
Similar Articles
@NFTCPS: Brothers, doing AI without large models is like doing nothing! Today I have to recommend an open-source masterpiece 'Foundations of LLMs' to you. Don't wait, just read it! This book doesn't beat around the bush—it goes deep from the start! From getting started with large language models to architectural evolution, and then it breaks down Prompt engineering, parameter-efficient fine-tuning, model editing, RAG (Retrieval-Augmented Generation) and other hardcore techniques in one go—a one-stop service.
This article promotes the open-source book 'Foundations of LLMs', which systematically explains knowledge about large language models, and introduces the multi-agent development framework Agent-Kernel.
@servasyy_ai: The physics calculations that 3D developers have practiced for years can now be done with just a single sentence. A free tool has been released that generates complex 3D particle effects from English instructions and can immediately output React or three.js code. The barriers of math and physics engines have disappeared, ushering in an era of instantly transforming ideas into reality. Experience
A free tool has been released that can generate complex 3D particle effects from English instructions and directly output React or three.js code, lowering the barrier to 3D physics calculations.
@NFTCPS: An open-source project even Musk retweeted, and you haven't tried it yet? PraisonAI: Just 5 lines of code to set up an AI agent team that can autonomously run tasks 24/7 without you watching. Key highlights: ① Supports 100+ LLMs, plug and play ② Agents automatically hand off and correct each other ③ Visual drag-and-drop workflow orchestration, no coding needed…
PraisonAI is an open-source project that only needs 5 lines of code to deploy an AI agent team. It supports over 100 large language models, visual workflow orchestration, and can integrate with platforms like Slack/Discord for 24/7 autonomous task execution. The project was retweeted by Elon Musk.
@AYi_AInotes: Fellow AI learners, stop just tuning packages. Writing a large language model from scratch is now easier than mastering PyTorch. Look at these two 19-year-old undergrads—they built a complete ML framework and a large model from scratch in four months. Two 19-year-old Waterloo undergrads, who knew nothing about ML four months ago, now…
Two 19-year-old undergraduates from the University of Waterloo built a complete machine learning framework and a 12M-parameter large language model from scratch in four months, using Rust and TypeScript, emphasizing understanding from the bottom up rather than just using packages.
@FinanceYF5: Counterattack of the AI Application Layer 1/ Large model companies are being encroached upon from the other side. Cursor, Decagon, Harvey, Notion are all doing the same thing: moving from API to self-trained models. Not to save money, but to take back the flywheel.
AI application layer companies such as Cursor, Decagon, Harvey, and Notion are shifting from using large model APIs to self-trained models. This trend aims to regain control of the data flywheel rather than merely saving costs.