Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

🔥We’re open-sourcing Multi-Agent CAD, a text-to-CAD pipeline that generates 3D assets for about $0.15 each—at roughly 1/13 the cost of CAD Skills, with faster inference and higher accuracy 🚀 This project began when our lab recruited Guanxing for his CAD expertise 🛠️ to build connected parts for robot learning...

150,324 Aufrufe • vor 1 Monat •via X (Twitter)

57 Kommentare

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

Code:

Profilbild von AI Mastery Guide
AI Mastery Guidevor 1 Monat

15 cents per 3D asset is a massive drop in cost.

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

Yeap : ) Feel free to try it out and raise any issue!

Profilbild von AI Mastery Guide
AI Mastery Guidevor 1 Monat

Definitely will, open sourcing this could push the whole space forward.

Profilbild von Numan
Numanvor 1 Monat

Thanks for sharing !!!

Profilbild von AdventureNLearn
AdventureNLearnvor 1 Monat

This is WONDERFUL!!!

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

Thanks!

Profilbild von Arrow
Arrowvor 1 Monat

Interesting! Following along 🔖

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

Thanks!

Profilbild von Dylan Oh
Dylan Ohvor 1 Monat

Exactly what I need at the moment. Starred

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

Thanks!

Profilbild von Vinod Thale 乐辉
Vinod Thale 乐辉vor 1 Monat

thank you how its different from @

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

We are using multi-agent, it is cheaper with better success rate. The code is very different if you do a comparison. We also politely cite and compare with them at the very beginning of the github paper. If you see my twitter, I just share their code base yesterday.

Profilbild von Vinod Thale 乐辉
Vinod Thale 乐辉vor 1 Monat

好的 谢谢

Profilbild von skhlgnev
skhlgnevvor 1 Monat

nice job!

Profilbild von Cagatay Cali
Cagatay Calivor 1 Monat

I am curious to compare the notes on this for text to print directly…

Profilbild von bdca
bdcavor 1 Monat

Thank you!

Profilbild von Paul
Paulvor 1 Monat

Wow! Will try it out! gave you a follow as well✅

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

Thanks!

Profilbild von Praveen Kumar Verma
Praveen Kumar Vermavor 1 Monat

Awesome to see. Can this be integrated with kicad?

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

Sorry, not so familiar with kicad, the output is stl file, raise an issue in the github to ask my student 🥲

Profilbild von Praveen Kumar Verma
Praveen Kumar Vermavor 1 Monat

Got it. It is amazing though. Thanks for the work.

Profilbild von Jenny Zheng
Jenny Zhengvor 1 Monat

@J0hn_bee check this out!

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

@J0hn_bee Thanks!

Profilbild von Matthew Thomas
Matthew Thomasvor 1 Monat

Incredible, that's a beautiful piece of art. Added to my bucket list. So peaceful.

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

Thanks!

Profilbild von Shadow Defense
Shadow Defensevor 1 Monat

add actuator planetary and cycloidal parts along with the exact motors that can be used to create actuators with pancake drone motors and nema, etc. then please give me 5% of sales for the idea.

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

Thanks!

Profilbild von Everett Hope - DadCanMakeIT3D
Everett Hope - DadCanMakeIT3Dvor 1 Monat

This is beyond cool.

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

Thanks!

Profilbild von Markus J. Buehler
Markus J. Buehlervor 1 Monat

👀

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

👀

Profilbild von Jonathan Korstad
Jonathan Korstadvor 1 Monat

Nice!!

Profilbild von Hubert Thieblot
Hubert Thieblotvor 1 Monat

@Do_owne

Profilbild von Rizwan Syed
Rizwan Syedvor 1 Monat

This looks very cool, Professor. Would love to try it.

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

Thanks!

Profilbild von Knowix
Knowixvor 1 Monat

good to see guys,I’ll test it out and give feedback

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

Give me a feedback if you happens to play with it.

Profilbild von alber 🌊
alber 🌊vor 1 Monat

Nice! These are the kind of projects that will lead to computers building useful things 🚀

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

Thanks!

Profilbild von HumanoidRobots.com Tom
HumanoidRobots.com Tomvor 1 Monat

the $0.15 ball-in-cage is going to ruin a lot of afternoons.

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

hhahah!

Profilbild von MP
MPvor 1 Monat

Awesome stuff

Profilbild von BadGuyTy 🅁🅅🄽 (Tyler Hess)
BadGuyTy 🅁🅅🄽 (Tyler Hess)vor 1 Monat

THANK YOU! been looking for a good text to cad repo

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

Thanks!

Profilbild von Gregor
Gregorvor 1 Monat

The $0.15 figure makes sense if the output is clean geometry, but genuinely asking, how are you measuring 'higher accuracy' here? Prompt adherence and structural validity feel like very different bars.

Profilbild von Keifer Lee
Keifer Leevor 1 Monat

Awesome work, congratulations on the release! That aside, I personally know of a few founders in the text -> CAD space and they'd be stoke to see releases like this. Perhaps a super impactful continuation would be to create a set of useful "harness" on top of this. Cheers!

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

Thanks a lot!

Profilbild von Timothy Siopan
Timothy Siopanvor 1 Monat

So cool, look forward to testing it!

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

Thanks! Give us a feedback!

Profilbild von clankr
clankrvor 1 Monat

Amazing work. The results in the video look great, but could this be used to manufacture mechanical parts for something like a robotic arm?

Profilbild von Xueyan Zou
Xueyan Zouvor 1 Monat

Yes, we are extending on that direction.

Profilbild von Moez Zhioua
Moez Zhiouavor 1 Monat

Cutting CAD generation to $0.15 shows the power of tightly coupled agents. The Qwen backbone explains the speed boost you demoed. Keep the budget tight, let the agents handle error correction

Profilbild von Bilal Khan
Bilal Khanvor 1 Monat

$0.15 per 3D asset is impressive. The real breakthrough is making CAD generation faster, cheaper, and accessible through multi-agent workflows.

Profilbild von Sebastian Buzdugan
Sebastian Buzduganvor 1 Monat

does the $0.15 include geometry validation retries, where these pipelines usually lose margin

Profilbild von Aiden
Aidenvor 1 Monat

Text-to-CAD agents are finally moving past demos. The real test isn't the pipeline, it's whether a designer can iterate on the output without fighting the harness.

Profilbild von Pewpy
Pewpyvor 1 Monat

these are such basic shapes, a novice CAD user could do these in a short amount of time

Ähnliche Videos

so I started with FreeCAD, since i am a linux guy, haven't touched windows since the past 8 years. Also I did this online course from Uni of California Irvine on "building your hardware for your embedded and IoT projects" which had FreeCAD as the main CAD software. FreeCAD was free, and fun, yeah a bit buggy sometimes but gets the job done, since initially all the CAD work i had was just builidng cases, or mounts, or some light hobby stuff. So FreeCAD did just fine. Then I joined a company as a product engineer where I worked with LiFePo4 home energy storage battery packs and was responsible for all the modules of the pack (Cells, BMS, MCUs, Touch Display ) mainly the embedded system. Since I was the product engineer, I'd have back and forth convos with the CAD designers off the battery pack box/casing. I didn't really do any CAD work on that project, tho it seemed really interesting to me. They used Solidworks, and I installed windows for it(swallowing that was difficult); to do Solidworks in my free time which I hardly got. I tried Solidworks and I kinda liked it. But then I quit the job and started working on my SAAS products. A few months into it, it's not fun anymore, slowly getting started with CAD and eventually to electronics to hardware products. Now, I want to go about CAD. I'll be doing a 30 days CAD challenge increasing in complexity and will be sharing daily progress here! It was day 2; I designer a bolt and a nut. I'm going with Fusion 360 for now, coz i like the UI/UX and the hobbyist version is free. So yeah. This is so much fun, i completely lost track of time while doing it. Gemini on the side is alot helpful.

Mustafa

20,127 Aufrufe • vor 8 Monaten

Introducing LobeHub: Agent teammates that grow with you. LobeHub is the ultimate space for work and life: to find, build, and collaborate with agent teammates that grow with you. We’re building the world’s first and largest human–agent co-evolving network. Two years ago, we built LobeChat, an open-source interface for using different AI models. Today, LobeChat has 70k+ GitHub stars and serves 6M+ users worldwide. How to fully unlock the power of models has always been a shared mission between us and the community. We started with interaction — a fundamentally new, agent-first experience. Agents are no longer passive tools invoked in a single conversation. They should be proactive, always-on units of work. Treating agents as the minimal atomic unit is also the core of our agent harness infra. Today’s agents are mostly one-off executors. Even with memory, it’s often global — and hallucinates. We build long-term agent teammates that evolve with users. Each agent has its own dedicated memory space, editable by users, allowing humans and agents to co-evolve over time. This, in turn, allows us to design clearer rewards for reinforcement learning and create cleaner environments for continual learning. Agent teammates can work in groups. Through a multi-agent system, agent groups operate faster, more cost-effective, and go beyond what single-agent systems can achieve. For example, a single agent often requires heavy user involvement to proceed step by step, whereas LobeHub can execute the same work from a single instruction, with a supervisor orchestrating agents that run in parallel or debate to produce better results. We are building the collaboration network among agent teammates — and between humans and agent teammates as well. Ease of use matters. AI intelligence and shared human intelligence are equally important. With simple instructions and tool selection, you can effortlessly build and team up with agent coworkers to deliver complex, systematic work — even assembling a quant team to execute trades. Through the LobeHub community, anyone can discover, reuse, and remix agents and agent groups, customizing them to fit their own workflows, preferences, and needs. Last but not least, our vision started with LobeChat: multi-model support is the most efficient approach for users. We believe different models excel in different scenarios. By routing across multiple models, LobeHub improves cost efficiency and unlocks capabilities that a single-model setup cannot easily support.

LobeHub

185,401 Aufrufe • vor 8 Monaten