Marco Pegoraro
@MPegoraro42
Followers
95
Following
42
Media
1
Statuses
13
Announcing Neo-1: the worldβs most advanced atomistic foundation model, unifying structure prediction and all-atom de novo generation for the first time - to decode and design the structure of life π§΅(1/10)
39
373
2K
π Don't miss this week's talk with @jeremyWohlwend and @GabriCorso where they will talk about their new model Boltz-1. ποΈFriday - 4pm CET / 10am ET
π’ Join us for a talk with @jeremyWohlwend & @GabriCorso on their recent paper Boltz-1 - a new open source SOTA for 3D structure prediction of biomolecular complexes. As always with @mmbronstein & @befcorreia When: Fri, Dec 06 - 4p CET/10a ET Sign-up: https://t.co/lBY0bTsTtM
0
9
14
Excited to present "Latent Functional Maps" at #NeurIPS ! We show how neural models can be aligned by matching function spaces on representation manifolds, providing a unified framework for model comparison, matching, and information transfer. π: https://t.co/78ifaXRAER ππ§΅
3
39
182
Discover how geometric DL π enhances paratope and epitope prediction through inner (I-GEP) and outer (O-GEP) protein structures. Our analysis with AF2 data showcase the robustness and generalizability of our models. Read our paper in Bioinformatics! 𧬠https://t.co/DMMZH5gMo5β¦
Another recent piece of happy news: our GEP paper (geometric DL π for predicting antibody-antigen binding sites π§¬) is now published in Bioinformatics! π https://t.co/c7xktGNlyv Led by Marco Pegoraro & @ClementineDomi6, jointly advised with @EmanueleRodola & @andreeadeac22 π
0
5
17
Another recent piece of happy news: our GEP paper (geometric DL π for predicting antibody-antigen binding sites π§¬) is now published in Bioinformatics! π https://t.co/c7xktGNlyv Led by Marco Pegoraro & @ClementineDomi6, jointly advised with @EmanueleRodola & @andreeadeac22 π
0
18
128
What a happy conclusion for this year and a great result for the outstanding perseverance of @MPegoraro42! Looking forward to enjoying more collaborations with the whole team :)
Congratulations to Marco Pegoraro, Riccardo Marin, Arianna Rampini, Simone Melzi, Luca Cosmo, and Emanuele Rodola for winning our best paper award in the category of topology and graphs ! π©π This award recognizes their work on spectral maps for learning on subgraphs !
0
1
11
Congratulations to Marco Pegoraro, Riccardo Marin, Arianna Rampini, Simone Melzi, Luca Cosmo, and Emanuele Rodola for winning our best paper award in the category of topology and graphs ! π©π This award recognizes their work on spectral maps for learning on subgraphs !
1
13
54
We're excited to announce the first edition of π΅π΄ UniReps: the Workshop on Unifying Representations in Neural Models! π§ To be held at @NeurIPSConf 2023! SUBMISSION DEADLINE: 4 October Check out our Call for Papers, lineup of speakers and schedule at: https://t.co/JV82wxz9Ze
3
31
91
Welcome Relative Representations, enabling zero-shot communication between latent spaces without any training! https://t.co/jnEJkMDFII It turns out that distinct neural networks learn intrinsically equivalent latent spaces [1/6]
22
229
1K
Have you ever wondered what a tiger with a hippo's head could look like? In our work https://t.co/ndi2elUPh7 presented at #SGP2022 @GeometryProcess, we try to answer this and similar questions. A work with: Simone Melzi, Umberto Castellani, @_R_Marin_, @EmanueleRodola
0
5
28
Published today. A survey paper on AI for animal conservation! https://t.co/NrwmujqUSM
nature.com
Nature Communications - Animal ecologists are increasingly limited by constraints in data processing. Here, Tuia and colleagues discuss how collaboration between ecologists and data scientists can...
0
2
12
Click and play as Galileo! π¨βπ¬β¨ππ©βπ¬ We simulated the process of scientific discovery through a game. Can you discover the laws of nature of the Odeen world? https://t.co/NyxCGBnxjS Check how we created an artificial scientist in our latest work: https://t.co/qGW49zfskJ
2
10
27