Co-founder of Procedo | PhD in Computer Science @SapienzaRoma | Member of the Perception and Intelligence Lab. @SapienzaPINlab
CTO and Founder of Procedo
Joined November 2012
- Tweets3.8K
- Following518
- Followers367
- Likes2.8K
Alessandro Flaborea retweeted
A couple of months ago, I told you vision-language = hyperbolic. #ICLR2025 agrees and has made our latest paper an oral presentation!
To present at ICLR: Compositional Entailment Learning for Hyperbolic Vision-Language Models.
Link: arxiv.org/abs/2410.06912
Alessandro Flaborea retweeted
"Compositional Entailment Learning for Hyperbolic Vision-Language Models" #ICLR25
has been 𝐬𝐞𝐥𝐞𝐜𝐭𝐞𝐝 𝐟𝐨𝐫 𝐚𝐧 𝐨𝐫𝐚𝐥 𝐩𝐫𝐞𝐬𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧 🏆
1.8% of the submitted papers were selected for an oral
"Compositional Entailment Learning for Hyperbolic Vision-Language Models" #ICLR25
On introducing text and image hierarchies in multi-modal learning with hyperbolic neural networks
arxiv.org/abs/2410.06912
Alessandro Flaborea retweeted
The #AlphaFold 3 model code and weights are now available for academic use. We @GoogleDeepMind are excited to see how the research community continues to use AlphaFold to address open questions in biology and new lines of research.
github.com/google-deepmind/a…
Alessandro Flaborea retweeted
ARIA glasses have arrived today at @SapienzaPINlab
Thanks @meta_aria and @AIatMeta for getting us onboard!
Alessandro Flaborea retweeted
I look forward to discussing artificial intelligence at the upcoming TEDx in Padua.
I'll present novel insights into the beliefs and certainties of intelligent machines based on the research of @SapienzaPINlab and the collaboration with international research partners
Gli ultimi due speaker del #TEDxPadovaSalon #dIAloghi
🙍♀️ Anna Spagnolli | Professoressa del Dipartimento di Psicologia Generale @UniPadova
👨 @GalassoFab10 | Perception and Intelligence Lab | Dipartimento di Informatica @SapienzaRoma
👉🏻 eventbrite.it/e/biglietti-te…
#TEDxPadova
Alessandro Flaborea retweeted
Today #ECCV2024 starts and PINlab is present!
This morning we're co-organizing the "Beyond Euclidean" workshop (@IndroSpinelli @GalassoFab10) where we're also presenting two posters:
"Hyp2Nav" (@AlessandroFlabo @GuidoDamely) and an Hyperbolic VLM from @paolomandica @FraLuca17 – at Milan, Lombardy
Alessandro Flaborea retweeted
PINlab 🤝 #CVPR2024
Part of our lab landed in Seattle last week to attend the @CVPR conference!
@AlessandroFlabo @LeonardoPlini @GalassoFab10 w/ the collab of @anfurnari and @GMFarinella presented the paper PREGO, accepted at the main conference and invited in two workshops 🍷 – at Seattle, WA
Alessandro Flaborea retweeted
If you're at @CVPR come and meet us today at 17:15, poster 374, where we'll present "PREGO: online mistake detection in PRocedural EGOcentric videos":
GitHub: github.com/aleflabo/PREGO
arXiv: arxiv.org/abs/2404.01933
A month ago, @AlessandroFlabo was awarded a PhD cum Laude from @SapienzaRoma.
Today, at @CVPR in Seattle, he is featured on the CVPR Daily (p.2) about his research with @SapienzaPINlab and tech transfer in ItalAI italailabs.com
Congratulations!
rsipvision.com/CVPR2024-Thur…
Alessandro Flaborea retweeted
A month ago, @AlessandroFlabo was awarded a PhD cum Laude from @SapienzaRoma.
Today, at @CVPR in Seattle, he is featured on the CVPR Daily (p.2) about his research with @SapienzaPINlab and tech transfer in ItalAI italailabs.com
Congratulations!
rsipvision.com/CVPR2024-Thur…
Alessandro Flaborea retweeted
We're restyling the PINlab logo! 🦉
The little owl (Athene Noctua) accompanies Minerva, representing wisdom, Sapienza.
Alessandro Flaborea retweeted
We will have the first workshop on “Hyperbolic and Hyperspherical Learning in Computer Vision” at ECCV'24!
With leading speakers and your latest works. Our submission site will open soon to receive your new or recently published work, join us in Milan!
sites.google.com/view/beyond…
Alessandro Flaborea retweeted
Alibaba releases DreaMoving demo on Hugging Face
A Human Video Generation Framework
based on Diffusion Models
demo: huggingface.co/spaces/jiayon…
Alessandro Flaborea retweeted
1/ We just made speech translation a whole lot better!
Introducing Seamless, an AI model that translates speech in real-time while also maintaining similar vocal style.
Github: github.com/facebookresearch/…
Site/Paper: ai.meta.com/research/seamles…
HF: huggingface.co/collections/f…
2️⃣ Seamless Communication
A family of AI research models that enable more natural & authentic communication across languages. The models deliver vocal style & prosody preservation capabilities as well as near real-time streaming translations.
Details ➡️ bit.ly/3Rj5Hdf
Alessandro Flaborea retweeted
Excited to share @GoogleDeepMind’s newest AI model GraphCast: the most accurate 10-day global weather forecasting system in the world. GraphCast can also offer earlier warnings of extreme weather events, including the path of hurricanes. In @Science today dpmd.ai/graphcast
Alessandro Flaborea retweeted
Introducing our new work @corl_conf 2023, a novel brain-robot interface system: NOIR (Neural Signal Operated Intelligent Robots).
Website: noir-corl.github.io/
Paper: arxiv.org/abs/2311.01454
🧠🤖
Alessandro Flaborea retweeted
PyTorch just released an awesome tool to visualize matrices and what's happening inside them.
Matrix multiplications (matmuls) are the building blocks of today’s ML models.
It can even run in browser: bhosmer.github.io/mm/
Blog:
pytorch.org/blog/inside-the-…
