Lightnews — Scholar-powered news

Ilyass Moummad

@ilyassmoummad.bsky.social

370 followers 330 following 55 posts

Postdoctoral Researcher @ Inria Montpellier (IROKO, Pl@ntNet) SSL for plant images Interested in Computer Vision, Natural Language Processing, Machine Listening, and Biodiversity Monitoring Website: ilyassmoummad.github.io

Posts Media Videos Starter Packs

Pinned

Ilyass Moummad @ilyassmoummad.bsky.social · Nov 19

Hi everyone! I'm Ilyass, a PhD student at IMT Atlantique, France, working on representation learning and few-shot learning, currently focusing on species recognition (audio/vision) until the end of 2024. I love sharing cool ideas and papers in Deep Learning—let's learn together!

Reposted by Ilyass Moummad

Dan Stowell @danstowell.mastodon.social.ap.brid.gy · 6d

BioDCASE workshop - registration closes next week Oct 10th https://biodcase.github.io/workshop2025/ - Hope to see you there! #bioacoustics

BioDCASE Workshop - BioDCASE

Join us for the BioDCASE Workshop held in Barcelona, Spain on the 29th of October! The workshop will be held at the Campus del Poblenou of Universitat Pompeu Fabra. The BioDCASE workshop will be hosted the day before the DCASE workshop on the 30-31st of October at the same venue …

biodcase.github.io

10 8

Ilyass Moummad @ilyassmoummad.bsky.social · Sep 9

I heard that the Linux client is buggy, I use it on the browser and it's working ok.

1 1

Ilyass Moummad @ilyassmoummad.bsky.social · Aug 29

for the curious, the code, slides and the article are on Github: github.com/BastienPasde...

1 4

Ilyass Moummad @ilyassmoummad.bsky.social · Aug 29

love it haha wish I were there to hear Prostitute Disfigurement in an amphitheater

2 1

Ilyass Moummad @ilyassmoummad.bsky.social · Aug 27

A website to visually browse and explore the ImageNet-1k dataset (there are other supported datasets: IN-12M, WikiMedia, ETH Images, Pixabay, Fashion) navigu.net#imagenet
(Maybe this is already known, but I was happy to discover it this morning)

NAVIGU: a powerful image collection explorer.

NAVIGU lets you dive into the ocean of images. Drag the image sphere or double-click on an image you like to browse large collections.

navigu.net

Ilyass Moummad @ilyassmoummad.bsky.social · Aug 23

Im interested in the quantum and footnotesize, how much params should they have 😂

Ilyass Moummad @ilyassmoummad.bsky.social · Aug 23

Learning Deep Representations of Data Distributions
Sam Buchanan · Druv Pai · Peng Wang · Yi Ma

ma-lab-berkeley.github.io/deep-represe...

The best Deep Learning book is out, I've been waiting for its release for more than a year. Let's learn how to build intelligent systems via compression.

Learning Deep Representations of Data Distributions

Landing page for the book Learning Deep Representations of Data Distributions.

ma-lab-berkeley.github.io

Ilyass Moummad @ilyassmoummad.bsky.social · Aug 19

It feels like we can now fit more noise with more model capacity 🤔 (Figure 6), maybe we need newer architectures and/or newer training losses.

Reposted by Ilyass Moummad

Andrei Bursuc @abursuc.bsky.social · Jul 21

1/ Can open-data models beat DINOv2? Today we release Franca, a fully open-sourced vision foundation model. Franca with ViT-G backbone matches (and often beats) proprietary models like SigLIPv2, CLIP, DINOv2 on various benchmarks setting a new standard for open-source research.

2 21 84

Ilyass Moummad @ilyassmoummad.bsky.social · Jul 18

👋 I worked on bioacoustics during my PhD, but I post mostly about AI

Reposted by Ilyass Moummad

ELLIS @ellis.eu · Jul 4

🏹 Job alert: Research Scientist at Prior Labs

📍Freiburg or Berlin 🇩🇪
📅 Apply by Dec 31 - preferably earlier
🔗 More info: https://bit.ly/4kqn5rY

Research Scientist

Build tabular foundation models and shape how the world works with its most valuable data. Opportunity to work on fundamental breakthroughs such as multimodal, causality and specialized architectures.

bit.ly

3 6

Ilyass Moummad @ilyassmoummad.bsky.social · Jul 3

Congratz! 👏

Ilyass Moummad @ilyassmoummad.bsky.social · Jun 19

my new addiction today: youtu.be/dSyJqwN36ow
I can't wait to see them this summer in Motocultor Festival

Of Petrichor Weaves Black Noise

YouTube video by Ne Obliviscaris - Topic

youtu.be

Ilyass Moummad @ilyassmoummad.bsky.social · Jun 19

the best discovery I've had in recent years, I'm addicted to it now as well 😁

1 1

Ilyass Moummad @ilyassmoummad.bsky.social · Jun 16

Thank you for making this accessible to everyone! I've read some sections, it is very instructive.

Reposted by Ilyass Moummad

Phillip Isola @phillipisola.bsky.social · Jun 15

Our computer vision textbook is now available for free online here:
visionbook.mit.edu

We are working on adding some interactive components like search and (beta) integration with LLMs.

Hope this is useful and feel free to submit Github issues to help us improve the text!

Foundations of Computer Vision

The print version was published by

visionbook.mit.edu

3 31 110

Reposted by Ilyass Moummad

Klara Janouskova @klara-cz.bsky.social · Jun 9

⚠️❗Open PhD and Postdoc positions in Prague with Lukas Neumann! ❗⚠️

We rank #5 in computer vision in Europe and Lukas is a great supervisor, so this is a great opportunity!

If you are interested, contact him, he will also be at CVPR with his group :)

1 5 14

Reposted by Ilyass Moummad

Klara Janouskova @klara-cz.bsky.social · Jun 6

We will be presenting the 🍄 FungiTastic 🍄, a multimodal, highly challenging dataset and benchmark covering many ML problems at @fgvcworkshop.bsky.social CVPR-W on Wednesday!

⏱️ 16:15
📍104 E, Level 1
📸 www.kaggle.com/datasets/pic...
📃 arxiv.org/abs/2408.13632

@cvprconference.bsky.social

3 6 18

Ilyass Moummad @ilyassmoummad.bsky.social · Jun 7

One of the best conferences that I have been to, happy to have met old friends and having made new ones, hopefully future collaborations as well. Many thanks for organizing this 🙏

1 3

Reposted by Ilyass Moummad

David Nordström @davnords.bsky.social · May 23

Want stronger Vision Transformers? Use octic-equivariant layers (arxiv.org/abs/2505.15441).

TLDR; We extend @bokmangeorg.bsky.social's reflection-equivariant ViTs to the (octic) group of 90-degree rotations and reflections and... it just works... (DINOv2+DeiT)

Code: github.com/davnords/octic-vits

2 4 29

Reposted by Ilyass Moummad

David Picard @davidpicard.bsky.social · Jun 3

Interesting paper on getting representations from unconditional diffusion models: arxiv.org/abs/2506.01912
(Was excepting more theoretical insights, but nice nonetheless)

Elucidating the representation of images within an unconditional diffusion model denoiser

Generative diffusion models learn probability densities over diverse image datasets by estimating the score with a neural network trained to remove noise. Despite their remarkable success in generatin...

arxiv.org

2 14

Reposted by Ilyass Moummad

rbalestr.bsky.social @rbalestr.bsky.social · May 20

Want to use SOTA Self Supervised Learning (SSL) methods on noisy data? We provide a novel training curriculum that significantly improves test performance on clean and noisy samples! The approach is fully SSL and works on any method (DINOv2, MoCo, ...)
arxiv.org/abs/2505.12191

Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum

Self-Supervised Learning (SSL) has become a powerful solution to extract rich representations from unlabeled data. Yet, SSL research is mostly focused on clean, curated and high-quality datasets. As a...

arxiv.org

1 1 4

Ilyass Moummad @ilyassmoummad.bsky.social · May 20

Super présentation, bravo et félicitations ! 👏 👏

Ilyass Moummad @ilyassmoummad.bsky.social · May 9

Thanks a lot!

Ilyass Moummad @ilyassmoummad.bsky.social · May 7

@emmanouilb.bsky.social for AI and Audio

1 2