Загрузка видео...

Не удалось загрузить видео

На главную

🔥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 просмотров • 1 месяц назад •via X (Twitter)

Комментарии: 57

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

Code:

Фото профиля AI Mastery Guide
AI Mastery Guide1 месяц назад

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

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

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

Фото профиля AI Mastery Guide
AI Mastery Guide1 месяц назад

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

Фото профиля Numan
Numan1 месяц назад

Thanks for sharing !!!

Фото профиля AdventureNLearn
AdventureNLearn1 месяц назад

This is WONDERFUL!!!

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

Thanks!

Фото профиля Arrow
Arrow1 месяц назад

Interesting! Following along 🔖

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

Thanks!

Фото профиля Dylan Oh
Dylan Oh1 месяц назад

Exactly what I need at the moment. Starred

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

Thanks!

Фото профиля Vinod Thale 乐辉
Vinod Thale 乐辉1 месяц назад

thank you how its different from @

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

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.

Фото профиля Vinod Thale 乐辉
Vinod Thale 乐辉1 месяц назад

好的 谢谢

Фото профиля skhlgnev
skhlgnev1 месяц назад

nice job!

Фото профиля Cagatay Cali
Cagatay Cali1 месяц назад

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

Фото профиля bdca
bdca1 месяц назад

Thank you!

Фото профиля Paul
Paul1 месяц назад

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

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

Thanks!

Фото профиля Praveen Kumar Verma
Praveen Kumar Verma1 месяц назад

Awesome to see. Can this be integrated with kicad?

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

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

Фото профиля Praveen Kumar Verma
Praveen Kumar Verma1 месяц назад

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

Фото профиля Jenny Zheng
Jenny Zheng1 месяц назад

@J0hn_bee check this out!

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

@J0hn_bee Thanks!

Фото профиля Matthew Thomas
Matthew Thomas1 месяц назад

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

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

Thanks!

Фото профиля Shadow Defense
Shadow Defense1 месяц назад

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.

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

Thanks!

Фото профиля Everett Hope - DadCanMakeIT3D
Everett Hope - DadCanMakeIT3D1 месяц назад

This is beyond cool.

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

Thanks!

Фото профиля Markus J. Buehler
Markus J. Buehler1 месяц назад

👀

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

👀

Фото профиля Jonathan Korstad
Jonathan Korstad1 месяц назад

Nice!!

Фото профиля Hubert Thieblot
Hubert Thieblot1 месяц назад

@Do_owne

Фото профиля Rizwan Syed
Rizwan Syed1 месяц назад

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

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

Thanks!

Фото профиля Knowix
Knowix1 месяц назад

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

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

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

Фото профиля alber 🌊
alber 🌊1 месяц назад

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

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

Thanks!

Фото профиля HumanoidRobots.com Tom
HumanoidRobots.com Tom1 месяц назад

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

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

hhahah!

Фото профиля MP
MP1 месяц назад

Awesome stuff

Фото профиля BadGuyTy 🅁🅅🄽 (Tyler Hess)
BadGuyTy 🅁🅅🄽 (Tyler Hess)1 месяц назад

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

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

Thanks!

Фото профиля Gregor
Gregor1 месяц назад

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.

Фото профиля Keifer Lee
Keifer Lee1 месяц назад

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!

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

Thanks a lot!

Фото профиля Timothy Siopan
Timothy Siopan1 месяц назад

So cool, look forward to testing it!

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

Thanks! Give us a feedback!

Фото профиля clankr
clankr1 месяц назад

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

Фото профиля Xueyan Zou
Xueyan Zou1 месяц назад

Yes, we are extending on that direction.

Фото профиля Moez Zhioua
Moez Zhioua1 месяц назад

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

Фото профиля Bilal Khan
Bilal Khan1 месяц назад

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

Фото профиля Sebastian Buzdugan
Sebastian Buzdugan1 месяц назад

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

Фото профиля Aiden
Aiden1 месяц назад

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.

Фото профиля Pewpy
Pewpy1 месяц назад

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

Похожие видео

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 просмотров • 8 месяцев назад

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 просмотров • 8 месяцев назад