Pascal Mettes retweeted
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 retweeted
🚀 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.
Pascal Mettes retweeted
✨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:
careers.universiteitleiden.n…
Pascal Mettes retweeted
✨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➡️ eventbrite.es/e/ellis-unit-s…
Pascal Mettes retweeted
✨ 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 ➡️ellisbarcelona.eu/ellis-unit…
Pascal Mettes retweeted
We are getting ready for the second edition of Beyond Euclidean Workshop @ICCVConference
We hope to see you there on Sunday!
Pascal Mettes retweeted
Finally the next @iclr_conf location is revealed...
iclr.cc
#ICLR2026 will be in Rio de Janeiro from 23 to 27 April!
Pascal Mettes retweeted
Starting now!
Leveraging context in prototypes for learning representations. Come find out more!
📍East Exhibition Hall A-B #E-2406
Pascal Mettes retweeted
Nice one!
Want the best possible embeddings in hyperbolic space while still maintaining GPU compatibility? Check out our #ICML2025 poster!
We show how to minimize distortion and get more precision with hyperbolic floating point expansions.
#1 method for embedding any tree-like structure.
Pascal Mettes retweeted
I’ll be at my first @CVPR this week presenting our #Highlight paper on (hyperbolic) safety-awareness in VLMs along with my co-author @tobiapoppi! Friends on twitter, DM me if you are going too and let’s catch up to discuss research and other banter 🥳
#CVPR2025
Pascal Mettes retweeted
After a very successful 1st edition at @eccvconf our Beyond Euclidean workshop is back, now at @ICCVConference in October! We will update our webpage (sites.google.com/view/beyond…) with information on our keynote speakers and open a call for full and short papers in the coming days!
Pascal Mettes retweeted
Hyperbolic Safety-Aware Vision-Language Models
arxiv.org/abs/2503.12127
Important problem. Nice idea. Cool embedding visualizations.
Pascal Mettes retweeted
I have an open PhD position on Multimodal Learning and Computer Vision. It will be under my supervision! 💫
The position is available until 19th of January to apply under utwentecareers.nl/en/vacanci…
Pascal Mettes retweeted
Meet "Hyperbolic Active Learning for Semantic Segmentation under Domain Shift' - a game changer for data labelling 🌐
HALO maximizes model performance, leveraging hyperbolic NNs & active learning to prioritise the least-known data points.
🔗The paper: arxiv.org/abs/2306.11180
Pascal Mettes retweeted
Today #IROS2024 starts and @SapienzaPINlab is present ✅
@GuidoDamely will have the oral presentation of Hyp2Nav, work done while we were visiting @PascalMettes, on the 18th.
He'll show how hyperbolic NNs improve explainability and reduce dimensionality for RL.
@GalassoFab10
Pascal Mettes retweeted
Reconstructing 3D human-object interactions from images/videos is a key step towards realistic #3D humans for #AR/#VR and assistive #robots/#AI.
To tackle this challenging problem my team and I have received an ERC Starting Grant 🎉 #ERCStG
📢 We look for 3x #PhD candidates!
We highly value a strong programming and mathematical background in candidates, along with a strong creativity, curiosity, self-motivation and team spirit!
We offer an exciting opportunity to conduct internationally visible #research in the stimulating environment of the University of Amsterdam (@UvA_Amsterdam, @UvA_Science, @Ellis_Amsterdam) along with a strong network of international collaborators, with a competitive compensation, while working in the brand new Lab42 building and living in one of the world’s most lively and liveable cities!
The goal is performing cutting-edge fundamental research, publishing at top-tier venues, releasing data and code for the community, and introducing new research problems.
If you are attending #ECCV2024 and have questions, I am happy to discuss with you at MiCo! (plz ping me via email)
🆘 Application deadline: Oct 31 🆘 CEST timezone
👉👉 We accept applications only through the portal below (includes a general description, application requirements, and employment conditions & benefits:
vacatures.uva.nl/UvA/job/PhD…
As a closing remark, a big thanks to @ERC_Research, all reviewers and panel members, as well as to all collaborators that contributed along the years for this exciting opportunity to arise! 🙏
Pascal Mettes retweeted
🚀 Excited to present our work on Self-Expertise at #ECCV2024 in Milan!
Join us at poster #89 on Friday, Oct 4 at 10:30 AM to see how self-expertise outperforms self-supervision in tackling unknown data in open-world settings! 🌍 #SelfSupervision #GeneralizedCategoryDiscovery
Pascal Mettes retweeted
Our paper "Embedding Geometries of Contrastive Language-Image Pre-Training" (arxiv.org/abs/2409.13079) by @nahidalam and yours truly has been accepted by ECCV '24 Beyond Euclidean Workshop! 1/8
Pascal Mettes retweeted
Amazing overview paper on geometric deep learning with lots of visualizations 👏
Great to see that people are not only working on new models, but rather investigate how all the methods out there relate!
Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structures
New review out with @ninamiolane, co-led by myself, @johmathe & @mathildepapillo
Check out our visual taxonomies of non-Euclidean structure in data & ML models































