Perception and Intelligence Lab (PINlab)
@SapienzaPINlab
Followers
75
Following
137
Media
8
Statuses
72
Research group at @SapienzaRoma focused on fundamental research and innovation transfer in the fields of computer vision and machine learning
Rome, Italy
Joined August 2022
RT @PascalMettes: A couple of months ago, I told you vision-language = hyperbolic. #ICLR2025 agrees and has made our latest paper an oral pβ¦.
arxiv.org
Image-text representation learning forms a cornerstone in vision-language models, where pairs of images and textual descriptions are contrastively aligned in a shared embedding space. Since visual...
0
19
0
RT @IndroSpinelli: The posters are set and the @SapienzaPINlab will be ready after a very much needed cup of coffee. See you later #WACV202β¦.
0
3
0
RT @GalassoFab10: "Following the Human Thread in Social Navigation" #ICLR25. has been π¬ππ₯πππππ ππ¬ π¬π©π¨ππ₯π’π π‘π π
. 5.1% of the submitted papersβ¦.
0
5
0
RT @GalassoFab10: "Compositional Entailment Learning for Hyperbolic Vision-Language Models" #ICLR25. has been π¬ππ₯πππππ ππ¨π« ππ§ π¨π«ππ₯ π©π«ππ¬ππ§ππβ¦.
0
2
0
RT @IndroSpinelli: AI Decodes the Brainβs "Stop" ! π§ β‘.Our custom spatio-temporal transformer (ST-T) predicts movement inhibition in monkeysβ¦.
0
6
0
RT @lambertoballan: #ICLR decisions are out! We have a paper on social navigation (this is an early version . Greatβ¦.
arxiv.org
The success of collaboration between humans and robots in shared environments relies on the robot's real-time adaptation to human motion. Specifically, in Social Navigation, the agent should be...
0
1
0
RT @GalassoFab10: Our @SapienzaPINlab has 2 #ICLR25 papers accepted!.I'm proud of the strong team and of the fantastic collaborators.
0
3
0
RT @AlessandroFlabo: Just a quick update on our HyCoCLIP paper: accepted to the #ICLR2025 conference with a avg score of 8!. A great collabβ¦.
arxiv.org
Image-text representation learning forms a cornerstone in vision-language models, where pairs of images and textual descriptions are contrastively aligned in a shared embedding space. Since visual...
0
1
0
RT @LeonardoPlini: I am very happy to share that I've received the Young Speaker Award at WIFAI 2024! π.I Β feel truly fortunate to be partβ¦.
0
2
0
RT @AlessandroFlabo: Excited to share our latest research, TI-PREGOβa follow-up to PREGO, our #CVPR2024 work! π. We explore how Chain of Tβ¦.
arxiv.org
Identifying procedural errors online from egocentric videos is a critical yet challenging task across various domains, including manufacturing, healthcare, and skill-based training. The nature of...
0
4
0
RT @GalassoFab10: ARIA glasses have arrived today at @SapienzaPINlab.Thanks @meta_aria and @AIatMeta for getting us onboard! .
0
4
0
RT @theAvikPal: (1/6)π₯³ Excited to share my latest research done as part of my MSc AI thesis! We introduced Hyperbolic Compositional CLIP (Hβ¦.
0
14
0
RT @_italai: To learn how Hyperbolic Neural Networks could help managing the uncertainty in AI models, check out the papers published by ouβ¦.
0
1
0
PINlab at @TEDxPadova! Prof. @GalassoFab10 had a talk about uncertainty in AI models and how Hyperbolic Neural Networks can handle it π₯.
On Oct 16, @GalassoFab10, founder of ItalAI & head of @SapienzaPINlab, spoke at @TEDxPadova dIAloghi_Conversazioni sull'AIπ‘about managing uncertainty in AI & the role of Hyperbolic Neural Networks in the ongoing search for solutions. #NeuralNetworks #MachineLearning #AI #Tech
0
0
8
RT @AlessandroFlabo: Today #IROS2024 starts and @SapienzaPINlab is present β
. @GuidoDamely will have the oral presentation of Hyp2Nav, workβ¦.
0
3
0
RT @_italai: On the last (but not least) day of the #ECCV2024, founder of ItalAI @GalassoFab10, together with @AlessioSampier1, @palm_alessβ¦.
0
2
0
RT @GalassoFab10: I look forward to discussing artificial intelligence at the upcoming TEDx in Padua. I'll present novel insights into theβ¦.
0
4
0
0
4
0
RT @AlessandroFlabo: Are you ready to proceed with us? π. Tomorrow we'll be showing our interactive demo during the morning demo session (9β¦.
procederai.com
Transform manufacturing procedures with AI. Extract from videos & manuals, reduce training time by 70%.
0
2
0
RT @_italai: @paolomandica and @FraLuca17 presenting their work on the first large-scale Hyperbolic vision-language model at the βBeyond Euβ¦.
0
2
0