Lorenzo Bertolini
@lorenzoscottb.bsky.social
3.1K followers 650 following 55 posts
Researcher at the European Commission Joint Research Centre (JRC). Multimodality & interpretability in AI for health. Occasionally, AI for dream research. Developer of DReAMy. All views are my own https://lorenzoscottb.github.io
Posts Media Videos Starter Packs
Pinned
lorenzoscottb.bsky.social
I’ll be at #ACL2025NLP next week, with a paper for the #GeBNLP workshop!

In this work, we tested the ability of a task-level explainability method to trace biological-sex biases in medical image classification, using general and biomedical VLMs.

@aclmeeting.bsky.social @genderbiasnlp.bsky.social
lorenzoscottb.bsky.social
Unserious post:

Now that (some) #AI researchers and engineers have rockstars-level salaries and notoriety, will they also have stage (or, better, paper) names?
lorenzoscottb.bsky.social
Made it alive and well to the last day of #ACL2025NLP? Hats off you to you (well…us…)!!!

Time to collect the last energy and pass by our poster this afternoon 😀
lorenzoscottb.bsky.social
I’ll be at #ACL2025NLP next week, with a paper for the #GeBNLP workshop!

In this work, we tested the ability of a task-level explainability method to trace biological-sex biases in medical image classification, using general and biomedical VLMs.

@aclmeeting.bsky.social @genderbiasnlp.bsky.social
lorenzoscottb.bsky.social
Not pressing _this_ work at #ACL2025NLP, but always happy to chat NLP/AI for dream analysis 😴🤖
lorenzoscottb.bsky.social
👋 #sleeppeeps In this new work, we show how multiple LLMs appear to easily process #dreams, and reflect previously observed differences in reports (e.g., male-female, blind-sighted).

We also argue for caution linking dreams and bizarreness when using #LLMs

www.frontiersin.org/journals/sle...
Frontiers | Dreams are more “predictable” than you think
IntroductionA growing body of work has used machine learning and AI tools to analyse dream reports, and compare them to other textual content. Since these to...
www.frontiersin.org
lorenzoscottb.bsky.social
I’ll be at #ACL2025NLP next week, with a paper for the #GeBNLP workshop!

In this work, we tested the ability of a task-level explainability method to trace biological-sex biases in medical image classification, using general and biomedical VLMs.

@aclmeeting.bsky.social @genderbiasnlp.bsky.social
lorenzoscottb.bsky.social
👋 #sleeppeeps In this new work, we show how multiple LLMs appear to easily process #dreams, and reflect previously observed differences in reports (e.g., male-female, blind-sighted).

We also argue for caution linking dreams and bizarreness when using #LLMs

www.frontiersin.org/journals/sle...
Frontiers | Dreams are more “predictable” than you think
IntroductionA growing body of work has used machine learning and AI tools to analyse dream reports, and compare them to other textual content. Since these to...
www.frontiersin.org
lorenzoscottb.bsky.social
Happy to share that our work on #conformalprediction for pulmonary nodule detection has been accepted for presentation at COPA 25 conference!
arxiv-cs-cv.bsky.social
Roel Hulsman, Valentin Comte, Lorenzo Bertolini, Tobias Wiesenthal, Antonio Puertas Gallardo, Mario Ceresa
Conformal Risk Control for Pulmonary Nodule Detection
https://arxiv.org/abs/2412.20167
lorenzoscottb.bsky.social
Introducing PreDA (prefix-based dream annotation), a set of generative LLMs tuned to annotate dream reports for 6 Hall & Van De Castle features! The paper will be presented at LOD 25 conference later this year as a long contribution. Models available here huggingface.co/jrc-ai
#sleeppeeps #dream
Reposted by Lorenzo Bertolini
arxiv-cs-cv.bsky.social
Roel Hulsman, Valentin Comte, Lorenzo Bertolini, Tobias Wiesenthal, Antonio Puertas Gallardo, Mario Ceresa
Conformal Risk Control for Pulmonary Nodule Detection
https://arxiv.org/abs/2412.20167
Reposted by Lorenzo Bertolini
dr-adri.bsky.social
💤 As I approach the end of my PostDoc at IMT Lucca, I’m looking for a new job!

🧠 Ideally: Research roles related to sleep/dream/consciousness/cognitive science.

🤖 Open to scientific writing & data analysis, too.

📍 Milan, nearby areas, or Switzerland.

DMs open 💃🏼
lorenzoscottb.bsky.social
Would computational approaches like open source toolkit and/or trained models (e.g. LLMs) be of interest too?
Reposted by Lorenzo Bertolini
dr-adri.bsky.social
Contribute to our Research Topic "Understanding conscious experiences during sleep"!
💤 🧠 💤

Deadlines:
Manuscript Summary Submission: 20.12.24
Manuscript Submission: 28.02.25

www.frontiersin.org/research-top...

#consciousexperiences #sleep #REMdreams #NREMdreams #DreamEngineering #Hypnagogia
Understanding conscious experiences during sleep
Emerging research suggests that elements of awareness persist throughout various sleep stages, challenging conventional notions of unconsciousness during sleep. This dynamic and enigmatic interplay of...
www.frontiersin.org
Reposted by Lorenzo Bertolini
tomerullman.bsky.social
thinking of calling this "The Illusion Illusion"

(more examples below)
Reposted by Lorenzo Bertolini
francois.fleuret.org
My deep learning course at the University of Geneva is available on-line. 1000+ slides, ~20h of screen-casts. Full of examples in PyTorch.

fleuret.org/dlc/

And my "Little Book of Deep Learning" is available as a phone-formatted pdf (nearing 700k downloads!)

fleuret.org/lbdl/
Reposted by Lorenzo Bertolini
thomwolf.bsky.social
It's Sunday morning so taking a minute for a nerdy thread (on math, tokenizers and LLMs) of the work of our intern Garreth

By adding a few lines of code to the base Llama 3 tokenizer, he got a free boost in arithmetic performance 😮

[thread]
Reposted by Lorenzo Bertolini
ilpost.it
il Post @ilpost.it · Nov 21
E quindi come si sta da queste parti?
Reposted by Lorenzo Bertolini
amsterdamnlp.bsky.social
Work in progress -- suggestions for NLP-ers based in the EU/Europe & already on Bluesky very welcome!

go.bsky.app/NZDc31B
lorenzoscottb.bsky.social
Heya, happy to be on the list if there is still a slot 🙂
lorenzoscottb.bsky.social
Good question, but o don’t think so. I haven’t seen/found anyone yet.
lorenzoscottb.bsky.social
Thanks, but it seems that the response is quite full of errors/hallucinations. In the paper of the first two datasets, there is no mention of existing age-based metadata (nor in the dataset download web page), while the third I donìt think it qualifies as histopath.
lorenzoscottb.bsky.social
Hi alI quick dataset question:

I’m looking for a collection of histopathological images (no specific requirements wrt organ/disease/task) which includes metadata on participants’ (approximate) age.

Any suggestion?
lorenzoscottb.bsky.social
A useful and very informed add to the debate would also be @lampinen.bsky.social 🙂
Reposted by Lorenzo Bertolini
manlius.bsky.social
As a computational social scientist I could not miss to follow this beautiful creature: the BlueSky social network during its growth in the last hours!

In this video I show just a snapshot for about 210k users and their 500k-ish connections #academicsky

Zoom in the next post

youtu.be/JcmYZtWGnjQ
The “great Xodus” and the growth of BlueSky
YouTube video by Manlio De Domenico
youtu.be