Pascal Mettes

Assistant Professor - University of Amsterdam | Hyperbolic deep learning

[Pascal Mettes @PascalMettes]

Our survey "Hyperbolic Deep Learning in Computer Vision: A Survey" has been accepted to #IJCV!

The survey provides an organization of supervised and unsupervised hyperbolic literature.

Online now: https://t.co/pHbOZKWqeq

w/ @GhadimiAtigMina @mkellerressel @jeffhygu
@syeung10

[Pascal Mettes @PascalMettes]

Do you have a new research on hyperbolic learning or did you have a paper accepted on this topic in the last year?

Submit your work to our ECCV 2026 Beyond Euclidean workshop on Hyperbolic Deep Learning for Computer Vision!

Deadline: June 24th
Details: https://t.co/8DLKeOk44W

[Georgios Leontidis @geleonti]

We are back at ECCV 2026! Our workshop will feature work in the beyond Euclidean space and we are accepting full paper submissions as part of our springer proceedings! Openreview link will open shortly but in the meantime check our call for papers out! @eccvconf

[Pascal Mettes @PascalMettes]

If you're at #ICLR2026, come check out our poster on the alignment between video understanding in the brain and in deep learning!

[Christina Sartzetaki @ ICLR 🇧🇷 @sargechris]

Curious about this AND attending #ICLR 26 🇧🇷?
Come to our poster 📆 Sat Apr 25, Poster session 5, 10:30-13:00 📍Pavillion 3 P3 - #1525, to learn how video models align with dynamic brain representations!
🕸️ https://t.co/ytGHGphsgt

[Pascal Mettes @PascalMettes]

Thank you inviting me to the winter school, it was great to meet everyone!

[Yuki @y_m_asano]

Third talk of Day 1: the pope of Hyperbolic Learning, @PascalMettes from @VISLab_UvA, @Ellis_Amsterdam! Add hyperbolic layers/loss, get uncertainty estimates!

[Pascal Mettes @PascalMettes]

@adn_twitts Perhaps not a perfect match, but scattering networks: https://t.co/xOZHcqsr9s

[ELLISBarcelona @ELLISBarcelona]

🚀 Yesterday we held the fourth session of our Seminar Series!

🧠Prof. @PascalMettes delivered a talk on "Hyperbolic Deep Learning" He explained that hyperbolic geometry is especially suited for hierarchical deep learning, offering better accuracy with fewer dimensions.

[Hazel Doughty @doughty_hazel]

✨PhD vacancy alert✨ Joost Batenburg and I are looking for someone that wants to work on fine-grained visual understanding in #ComputerVision @LIACS

Apply here before 20 Feb:
https://t.co/aL47KnBsoK

[ELLISBarcelona @ELLISBarcelona]

✨Only one week to go! The ELLIS Unit Barcelona is hosting its fourth Scientific Seminar.

Join us for the Scientific Seminar on January 28th with a talk by Prof. @PascalMettes on "Hyperbolic Deep Learning".

Don't miss out! Register here➡️ https://t.co/eFyCtqrOzP

[Pascal Mettes @PascalMettes]

@CSProfKGD Same here, no need for emergency reviews in my batch. Although verbose, it seems that the messages from the PCs are taken seriously by the reviewers.

[ELLISBarcelona @ELLISBarcelona]

✨ Kind reminder! The ELLIS Unit Barcelona is hosting its fourth Scientific Seminar.

Join us for the Scientific Seminar on January 28th with a talk by Prof. @PascalMettes on "Hyperbolic Deep Learning".

Don't miss out ➡️https://t.co/3nx3L3f9D4

[Pascal Mettes @PascalMettes]

@2ptmvd @CVPR Yes, one month between submission and reviewer assignment is a huge gap. I wonder whether the openreview issues of this year played a role.

[Pascal Mettes @PascalMettes]

I am very excited to visit the ELLIS Unit in Barcelona next month!

[ELLISBarcelona @ELLISBarcelona]

✨ Exciting news! The ELLIS Unit Barcelona is hosting its fourth Scientific Seminar.

Join us for the Scientific Seminar on January 28th with a talk by Prof. @PascalMettes on "Hyperbolic Deep Learning".

[Pascal Mettes @PascalMettes]

@BlackHC @iclr_conf Unfortunately, the latter is a realistic scenario and already happened. Beyond bribing, people can hold grudges, threaten, sabotage papers in future conferences, etc. We care too much about careers instead of science and people end up doing unhealthy things to advance them.

[Pascal Mettes @PascalMettes]

I have funding for 2 new PhD students on hyperbolic deep learning. Interested in joining this exciting research direction? Check out the vacancy and consider applying!

Link: https://t.co/pHYizo0jHU

[Pascal Mettes @PascalMettes]

I will even go as far as to say that the review quality has been stable over the last decade (seen as author and AC). My advice, especially for new students, is to not go to twitter after reviews have been released, too many frustrated people with ill-intended messages. [4/4]

[Pascal Mettes @PascalMettes]

It is shocking to me how much of an echo chamber AI twitter has become regarding peer review. There are 80k reviews for ICLR and people here loose their minds about noise that has always been there. LLM reviews are bad, noise is bad. But this discussion is so un-scientific. [1/4]

[Pascal Mettes @PascalMettes]

In my experience, most reviews contribute to the process and with 4 reviews per paper, a noise review can be compensated by others. There are still plenty of cases with errors, but this problem is as old as peer review itself. [3/4]