Jordi Cabot

☄️First full draft of my new #book 📖 : "How to survive (and thrive) in research". With 150 #advices for #PhD and #junior #researchers

Now I'm going to go over all your comments and suggestions 🔎🕵️ and share the draft with early readers

Learn more ➡️➡️ jordicabot.com/book-advice-...

🕸️Visit our new brand website🕸️

🔗 besser-pearl.org

Many things to improve, but it's a start!

#lowcode #opensource #modeling

Convincing 😅

🥰 Always happy to get this feedback 🥰:

"We are adopting BESSER. We had the 1stclass, and it was easy for students to start modeling (much more than with EMF"

Already 20 univ. using BESSER to teach #mde #uml #modeling

Do you want to be next? ➡️ lowcode-book.com/book-users/

YouTube video by BESSER Multilingual Agent Generation in BESSER

Model an #agent once, generate multiple versions automatically, one for every language of your choice.

#Video: youtube.com/watch?v=MnFxZYaFAJA&feature=youtu.be

#Details: www.linkedin.com/feed/update/...

#internationalization #i18n #agentic #lowcode #oss

Forget #vibecoding , embrace #vibemodeling.

And soon this will be possible in BESSER. See the #teaser below.

For more on vibe modeling --> modeling-languages.com/vibe-modeling/

Creating Smart Data Models with BESSER Smart data models described visually in UML can be directly turned into NGSI-LD compliant data models, drastically reducing the time between design and deployment in real-world systems.

Creating Smart Data Models with BESSER modeling-languages.com/smart-data-m...

#smartdatamodel #fiware #jsonschema #jsonld #ngsi

This is what we tested in a recent work where we show that current LLMs beat fine tuned versions of older ones in the education domain, in particular in question generation tasks.

And we've seen this also in other domains where top finetuned models on a task get obsolete by newer general #LLMs.

Should you #finetune or should you wait?

Finetuning is still an option to improve the quality of the results, but a costly one (in terms of data, time and expertise).

So if you can #wait, do it. It is likely the next generation of #LLMs will be good enough for you.

A 2024 paper with already 10 citations 🥳🎉

Glad that you do find the topic of #LLMs for #modeling interesting!

Haven't read it yet? See how we use a #ToT strategy for #domain modeling scholar.google.es/citations?vi...

#uml #llm

From Image to UML: First Results of Image Based Class Diagram Generation Using LLMs Can we use LLM to quickly generate proper UML models from hand drawn model sketches? We set out to answer this question by comparing four different LLMs with vision capabilities

Read the science behind it: modeling-languages.com/image-to-uml...

Try it yourself editor.besser-pearl.org (note that you will need an OpenAI key)

See a demo in 30 seconds www.youtube.com/watch?v=-5N-...

#uml #lowcode #oss

🚀 Exciting new feature in release 4.2.0!

We just integrated the #IMG2UML feature into the graphical editor of BESSER 🎉

This allows users to upload an image of a class diagram and automatically convert it into an interactive model.

#tech #books #anecdotal #data #datapoint #uml #softwaredevelopment #programminglanguages #top | Jordi Cabot 😔People don't buy #tech #books 😔 I think I read this sentence from a Greg Wilson text somewhere (I couldn't find it back, so, Greg, if it wasn't you my apologies) as one of the reasons he would not b...

😔People don't buy #tech #books 😔 www.linkedin.com/feed/update/...

What a time to be alive: The first conference for AI-authored and AI-peer reviewed papers.

agents4science.stanford.edu/index.html

So I had to manually enter my #lowcode book into #GoogleScholar as it seems Google doesn't like self-published books and does not automatically index them... scholar.google.com/citations?vi...

GitHub - markrussinovich/refchecker: A tool that validates academic paper references A tool that validates academic paper references. Contribute to markrussinovich/refchecker development by creating an account on GitHub.

Academic Paper Reference Checker github.com/markrussinov...

ModelFed: a Federated Protocol for Collaborative Cross-Platform Modeling modeling-languages.com/modelfed-fed...

inspired by the #fediverse and #actvitiypub

Modeling the obsolescence of models Models get old and need to be revised and updated to make sure they still reflect the reality of the domain. We provide a DSL to define the elements to be reviewed and an engine to automatically ident...

1st citation for the paper: "Modeling the obsolescence of models".

Because models, like people, get old.

Read it here ➡️ modeling-languages.com/model-obsole...

We'll be presenting at the #Models25 conference as part of the @sosym_journal first track

#modeling #obsolescence #dsl

📢 NEW #BOOK PROJECT📢

Read about my new book project aimed at giving #junior #researchers the advice they need to #accelerate their #research #career 🏎️

🔎 jordicabot.com/book-advice-...

Answer the short survey📋in the post to make sure the book is useful to you.

Pls RT

#phdchat #phdlife #postdoc

Glad to see that @OutSystems and I agree on the importance of vibe modeling modeling-languages.com?s=vibe+model... (vs #vibecoding).

See this interview to their new CEO diginomica.com/outsystems-n...

Why Universities Struggle to Teach Low-Code (Survey Results) A few months ago, we started a survey trying to understand why no more universities were offering low-code courses, or at the very least integrating low-code

Our paper on "Teaching Low-Code Development with BESSER" (related to modeling-languages.com/teaching-low..., full preprint coming soon), has been accepted to the Educators Symposium at #MODELS'25 conference. 🥳🥳

Absolutely. We are losing our minds. And conferences (not only workshops) with more and more pages to fill also generates additional stress and work as people feel bad when not filling the space (and reviewers use it to say "you could have done more eval, you have space")

The low-code handbook: Learn how to unlock faster and better software development with low-code solutions Amazon.com: The low-code handbook: Learn how to unlock faster and better software development with low-code solutions eBook : Cabot, Jordi: Kindle Store

📢🔔 ONLY THIS WEEK - The #lowcode #book is 60% off (#kindle version) www.amazon.com/low-code-han...

Now it turns out that even workshop papers need to come with empirical validation. Next time an idea tries to pop up in my brain I'll stop it and tell her you need to come up validated or stay out of my head 😫😩

The low-code handbook: Learn how to unlock faster and better software development with low-code solutions Amazon.com: The low-code handbook: Learn how to unlock faster and better software development with low-code solutions eBook : Cabot, Jordi: Kindle Store

📢🔔 ONLY THIS WEEK - The #lowcode #book is 60% off (#kindle version) www.amazon.com/low-code-han...

2️⃣ Papers accepted at the #ER conference 🥳🍾

Wanna know what they are about? ⬇️🔽

✅ ModelFed: a #Federated #Protocol for #Collaborative #CrossPlatform Modeling

✅ Towards #Human-in-the-Loop #LLM-Enabled #Domain Modeling

We will soon publish the preprint versions !

Towards Sustainability Model Cards: A DSL for specifying AI's Environmental Impact We propose a new Domain-Specific Language to precisely define the sustainability aspects of an ML model (including the energy costs for its different tasks) that can be exported as an extended Model C...

Towards Sustainability Model Cards: A DSL for specifying AI’s Environmental Impact modeling-languages.com/sustainabili...

#greenAI #energy #sustainability #AI #DSL #ModelCards

📢 New paper introducing the concept of #Vibe #Modeling 📢

where I discuss a novel approach to integrate the best of both #AI and of #ModelDriven engineering to speed up the development of #reliable #complex systems.

📜https://arxiv.org/pdf/2507.23120