Federico Bergamin (@fedebergamin) 's Twitter Profile
Federico Bergamin

@fedebergamin

Postdoc in machine learning at @CogSys. PhD from @CogSys. Spent time @CambridgeMLG, @DTUtweet, @UBC, and @UniPadova.

ID: 4217443875

linkhttps://federicobergamin.github.io/ calendar_today18-11-2015 11:23:51

78 Tweet

209 Takipçi

708 Takip Edilen

Richard Moore (@richardmoore73) 's Twitter Profile Photo

An odd sport where the guy who’s currently the best in the world, who could have won the first two stages, is fetching drinks for his teammates... 😱🤔

Alison (@a_ppln) 's Twitter Profile Photo

Are you interested in Normalizing flows? Feel free to join our online seminar this Wednesday (21/10) at 16:00 CET. Dimitris Kalatzis, Polina Kirichenko and Antoine Wehenkel will give us a short introduction and present their research. More info: cogsystalks.github.io/event-5/

Jes Frellsen (@jesfrellsen) 's Twitter Profile Photo

If you are interested in working with me as a PhD student or Postdoc, then there is an open call for scholarships from DDSA with a deadline on March 19, 2023. ddsa.dk/phdfellowshipp… ddsa.dk/postdocfellows…

Jes Frellsen (@jesfrellsen) 's Twitter Profile Photo

Join us for the Generative Modeling Summer School in Copenhagen on June 26-30, co-organised with the two fantastic @jmtomcza and Pierre-Alexandre Mattei and with an amazing lineup of guest lectures! Apply before April 10, 2023. gemss.ai #GeMSS23 @DataScienceDK Pioneer Centre for AI

Team Bahrain Victorious (@bhrvictorious) 's Twitter Profile Photo

🙏🏻 Gino, thank you for the light, the joy, and the laughs you brought us all, we will miss you as a rider and as a person. ❤️ Today and every day, we ride for you, Gino. 🔗 bit.ly/3qSoyRx

🙏🏻 Gino, thank you for the light, the joy, and the laughs you brought us all, we will miss you as a rider and as a person.

❤️ Today and every day, we ride for you, Gino.

🔗 bit.ly/3qSoyRx
Runa Eschenhagen (@runame_) 's Twitter Profile Photo

My supervisor Rich Turner has written an introduction to transformers. I highly recommend anyone wanting to learn (more) about transformers to take a look, it is precise and concise at the same time. arxiv.org/abs/2304.10557

Federico Bergamin (@fedebergamin) 's Twitter Profile Photo

On my way to #NeurIPS23 for the first time. I’ll be there presenting our work "Riemannian Laplace approximations for Bayesian Neural Networks". Work done together with Pablo Moreno-Muñoz, Søren Hauberg, and Georgios Arvanitidis. I’ll be at poster #1223 on Wednesday from 17pm (Session 4).

On my way to #NeurIPS23 for the first time. I’ll be there presenting our work "Riemannian Laplace approximations for Bayesian Neural Networks". Work done together with <a href="/pablorenoz/">Pablo Moreno-Muñoz</a>, Søren Hauberg, and <a href="/arvanitg/">Georgios Arvanitidis</a>. I’ll be at poster #1223 on Wednesday from 17pm (Session 4).
Vincent Dutordoir (@vdutor) 's Twitter Profile Photo

A highlight of the #NeurIPS2023 meetup in Cambridge for me was Carl Rasmussen's keynote on "Halting Climate Change". Spoiler: it has nothing to do with AI. Worth a watch: youtube.com/watch?v=naFaQs…

Nicholas Krämer (@pnkraemer) 's Twitter Profile Photo

🛩️ On my way to #NeurIPS2024 and excited to chat about (ML applications of) linear algebra, differentiable programming, and probabilistic numerics! Feel free to DM if you’d like to meet up, hang out, and/or discuss any of these topics 😊

Leonardo Piccione (@ledep) 's Twitter Profile Photo

Non c'è un corridore più adatto di Van Aert a completare questo capolavoro; non esistono tre parole più dolci di "Ritrovare Van Aert" in questo sport, forse nella vita.

Federico Bergamin (@fedebergamin) 's Twitter Profile Photo

In an hour, François and I are presenting at ICML our paper on crystalline material generation using diffusion models, where the key innovation is a diffusion process for the fractional coordinates that is inspired by kinetic Langevin dynamics. Paper: arxiv.org/abs/2507.03602

In an hour, François and I are presenting at ICML our paper on crystalline material generation using diffusion models, where the key innovation is a diffusion process for the fractional coordinates that is inspired by kinetic Langevin dynamics. 

Paper: arxiv.org/abs/2507.03602