Pascal Mettes

🚨🚨📄 Check out our new preprint!
Our results reveal novel insights on how continuous visual input is integrated in the human brain💡, beyond the standard temporal processing hierarchy from low to high-level representations

31.10.2025 13:32 — 👍 5    🔁 2    💬 0    📌 0

The Human Brain as a Dynamic Mixture of Expert Models in Video Understanding The human brain is the most efficient and versatile system for processing dynamic visual input. By comparing representations from deep video models to brain activity, we can gain insights into mechani...

📢 New preprint, together with @sargechris.bsky.social!

Building on @sargechris.bsky.social's previous work, we benchmark 100+ image and video models 🤖 on brain representational alignment, this time to EEG data of humans 🧠 watching videos! 🧵⬇️

www.biorxiv.org/content/10.1...

31.10.2025 13:03 — 👍 3    🔁 1    💬 1    📌 2

We are thrilled to welcome Aiden Durrant as a Winter School speaker at NLDL 2026 🤖 ❄️

His tutorial will give you an understanding of the rationale behind non-Euclidean methods and prepare you to explore them for your own research problems.

More info in the comments 👇

03.09.2025 06:45 — 👍 4    🔁 3    💬 1    📌 0

Sure, but now it is used to compare people and reduce careers to 3 numbers. My strong preference would be to have a qualitative google scholar, where only the top X (5, 10, ?) papers can be highlighted by the author. The rest of the papers are in a list but don't contribute to an aggregate number.

20.08.2025 07:57 — 👍 0    🔁 0    💬 1    📌 0

Many thanks @pascalmettes.bsky.social @ellisamsterdam.bsky.social for visiting us @bristoluni.bsky.social to examine (now Dr) Adriano Fragomeni (supervised by myself and Michael Wray) and give a great talk on hyperbolic deep learning. Enjoyed your visit

23.07.2025 21:16 — 👍 7    🔁 1    💬 0    📌 0

Beyond Euclidean - Call for Papers Important Dates: Submission Portal Opens: 29th of April 2025 Submission Deadline: 1st of June 2025 (AOE) Preliminary Author Notification Deadline: 27th of June 2025 Camera-ready deadline (Proceeding...

We are back at #ICCV2025 for the second workshop on Hyperbolic and Hyperspherical Learning for Computer Vision.

We will have 2 tracks: one for new research (to be published in proceedings) and one for recently published works.

Deadline: June 1st
Link: sites.google.com/view/beyonde...

01.05.2025 06:21 — 👍 22    🔁 6    💬 0    📌 0

Today I will give a keynote on "Hyperbolic Visual Understanding" at the Non-Euclidean Foundation Models and Geometric Learning (NEGEL) workshop at the Web Conference in Sydney.

If you are at #WWW2025 and want to discuss hyperbolic learning, I'm around all week!

28.04.2025 23:16 — 👍 2    🔁 0    💬 0    📌 0

Great to see you all at #ICLR2025, it was fun discussing our works on hyperbolic vision-language models, a better way to do object detection, and brain-aligned image generation.

See you at the next one!

28.04.2025 23:14 — 👍 2    🔁 0    💬 0    📌 0

I am very excited to present at the Pattern Recognition and Computer Vision Colloquium at CTU Prague. I will be there Wednesday afternoon and Friday morning as well if you are around and want to discuss hyperbolic learning!

07.04.2025 14:53 — 👍 7    🔁 1    💬 0    📌 0

This is long overdue and there seems to be no valid reason to host CVPR in North America only. Is it because of funding sources? Either way, time to overhaul the setup, please let me know if you need help with the motion.

12.03.2025 09:25 — 👍 5    🔁 0    💬 0    📌 0

Who's up for writing a CVF motion proposing to vary the location of CVPR?

It being forever in the US, with the concerning (euphemism) situation there, is a recipe for losing this amazing community.
But even without the current events, it should have been done ages ago.

11.03.2025 07:59 — 👍 61    🔁 7    💬 9    📌 2

Vision-language models are hierarchical and asymmetrical, hence all models benefit from hyperbolic embeddings.

Our new #ICLR2025 oral paper shows how image-box compositions create cool new hierarchies and powerful vision-language models when used during training!

Link: arxiv.org/abs/2410.06912

04.03.2025 09:48 — 👍 12    🔁 1    💬 0    📌 1

Wow, great news! Many congratulations.

03.03.2025 11:43 — 👍 1    🔁 0    💬 0    📌 0

"Compositional Entailment Learning for Hyperbolic Vision-Language Models" #ICLR25

With: Avik Pal, Max van Spengler, Guido Maria D'Amely di Melendugno, Alessandro Flaborea, and @pascalmettes.bsky.social

Paper: arxiv.org/abs/2410.06912

25.01.2025 13:17 — 👍 7    🔁 3    💬 0    📌 1

A deep dive into mathematics for more accurate AI Deep learning networks underpin many of today's AI applications, such as image recognition. Those networks can still fail massively when they need to name an object, such as an animal. According to Uv...

Hyperbolic learning is growing rapidly by the day. From weekly alerts in 2023 to daily digests in 2024!

From our current research, it is clear that 2025 will be a huge year for hyperbolic learning research.

I had an interview to elaborate our research:
shorturl.at/CQD53

16.12.2024 09:45 — 👍 12    🔁 5    💬 0    📌 0

Thank you both!

01.12.2024 09:52 — 👍 3    🔁 0    💬 0    📌 0