正在加载视频...

视频加载失败

🔥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 次观看 • 1 个月前 •via X (Twitter)

57 条评论

Xueyan Zou 的头像
Xueyan Zou1 个月前

Code:

AI Mastery Guide 的头像
AI Mastery Guide1 个月前

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

Xueyan Zou 的头像
Xueyan Zou1 个月前

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

AI Mastery Guide 的头像
AI Mastery Guide1 个月前

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

Numan 的头像
Numan1 个月前

Thanks for sharing !!!

AdventureNLearn 的头像
AdventureNLearn1 个月前

This is WONDERFUL!!!

Xueyan Zou 的头像
Xueyan Zou1 个月前

Thanks!

Arrow 的头像
Arrow1 个月前

Interesting! Following along 🔖

Xueyan Zou 的头像
Xueyan Zou1 个月前

Thanks!

Dylan Oh 的头像
Dylan Oh1 个月前

Exactly what I need at the moment. Starred

Xueyan Zou 的头像
Xueyan Zou1 个月前

Thanks!

Vinod Thale 乐辉 的头像
Vinod Thale 乐辉1 个月前

thank you how its different from @

Xueyan Zou 的头像
Xueyan Zou1 个月前

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.

Vinod Thale 乐辉 的头像
Vinod Thale 乐辉1 个月前

好的 谢谢

skhlgnev 的头像
skhlgnev1 个月前

nice job!

Cagatay Cali 的头像
Cagatay Cali1 个月前

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

bdca 的头像
bdca1 个月前

Thank you!

Paul 的头像
Paul1 个月前

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

Xueyan Zou 的头像
Xueyan Zou1 个月前

Thanks!

Praveen Kumar Verma 的头像
Praveen Kumar Verma1 个月前

Awesome to see. Can this be integrated with kicad?

Xueyan Zou 的头像
Xueyan Zou1 个月前

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

Praveen Kumar Verma 的头像
Praveen Kumar Verma1 个月前

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

Jenny Zheng 的头像
Jenny Zheng1 个月前

@J0hn_bee check this out!

Xueyan Zou 的头像
Xueyan Zou1 个月前

@J0hn_bee Thanks!

Matthew Thomas 的头像
Matthew Thomas1 个月前

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

Xueyan Zou 的头像
Xueyan Zou1 个月前

Thanks!

Shadow Defense 的头像
Shadow Defense1 个月前

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.

Xueyan Zou 的头像
Xueyan Zou1 个月前

Thanks!

Everett Hope - DadCanMakeIT3D 的头像
Everett Hope - DadCanMakeIT3D1 个月前

This is beyond cool.

Xueyan Zou 的头像
Xueyan Zou1 个月前

Thanks!

Markus J. Buehler 的头像
Markus J. Buehler1 个月前

👀

Xueyan Zou 的头像
Xueyan Zou1 个月前

👀

Jonathan Korstad 的头像
Jonathan Korstad1 个月前

Nice!!

Hubert Thieblot 的头像
Hubert Thieblot1 个月前

@Do_owne

Rizwan Syed 的头像
Rizwan Syed1 个月前

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

Xueyan Zou 的头像
Xueyan Zou1 个月前

Thanks!

Knowix 的头像
Knowix1 个月前

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

Xueyan Zou 的头像
Xueyan Zou1 个月前

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

alber 🌊 的头像
alber 🌊1 个月前

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

Xueyan Zou 的头像
Xueyan Zou1 个月前

Thanks!

HumanoidRobots.com Tom 的头像
HumanoidRobots.com Tom1 个月前

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

Xueyan Zou 的头像
Xueyan Zou1 个月前

hhahah!

MP 的头像
MP1 个月前

Awesome stuff

BadGuyTy 🅁🅅🄽 (Tyler Hess) 的头像
BadGuyTy 🅁🅅🄽 (Tyler Hess)1 个月前

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

Xueyan Zou 的头像
Xueyan Zou1 个月前

Thanks!

Gregor 的头像
Gregor1 个月前

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.

Keifer Lee 的头像
Keifer Lee1 个月前

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!

Xueyan Zou 的头像
Xueyan Zou1 个月前

Thanks a lot!

Timothy Siopan 的头像
Timothy Siopan1 个月前

So cool, look forward to testing it!

Xueyan Zou 的头像
Xueyan Zou1 个月前

Thanks! Give us a feedback!

clankr 的头像
clankr1 个月前

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

Xueyan Zou 的头像
Xueyan Zou1 个月前

Yes, we are extending on that direction.

Moez Zhioua 的头像
Moez Zhioua1 个月前

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

Bilal Khan 的头像
Bilal Khan1 个月前

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

Sebastian Buzdugan 的头像
Sebastian Buzdugan1 个月前

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

Aiden 的头像
Aiden1 个月前

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.

Pewpy 的头像
Pewpy1 个月前

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

相关视频

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 次观看 • 8 个月前

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 次观看 • 8 个月前