Full Professor @IMTAtlantique. Better Representations for Artificial Intelligence team. Neuroscience, AI, music cognition. Jazz vibraphone
France
Joined October 2009
- Tweets888
- Following2.1K
- Followers784
- Likes1.7K
Nicolas Farrugia retweeted
Read our full open-access paper in Communications Biology, where we use MEG to reveal how LSD reshapes brain rhythms, spectral dynamics, and neural complexity.
nature.com/articles/s42003-0…
by @Venkateshness /w @RCarhartHarris @milthampton @giulia_lioi @AnnalisaPascar1 @yharel109 🙏
Big news! Our paper, REVE: A Foundation Model for EEG, accepted at #NeurIPS2025! 🎉
🧠 Largest EEG pretraining (25K subjects, 60k+ hrs). 🌐 Novel 4D positional encoding for ANY EEG setup. SOTA on 10 tasks.
Paper, models & Colab: brain-bzh.github.io/reve/
#EEG #FoundationModels
2
2
139
Authors Yassine El Ouahidi, Jonathan Lys, Bastien Pasdeloup and Giulia Lioi will be in San Diego to present it next week.
Huge shoutout to all authors, @karimjerbineuro , Philipp Tholke and Vincent Gripon
Nicolas Farrugia retweeted
🐦Simplifying access to bird audio data with 6-sec segments selected via PANN in PyTorch (.pt) format! Xeno-Canto, a large pre-training dataset: huggingface.co/datasets/ilya…
Eval datasets from BIRB for few-shot learning: zenodo.org/records/13994373
More info: github.com/ilyassmoummad/Pro…
Nicolas Farrugia retweeted
#RésultatScientifique 🔎
🌍🔊 Une collaboration internationale de 261 chercheurs de 35 pays a recueilli des sons urbains pendant le confinement. Les données sont maintenant disponibles en open access pour diverses recherches.
👉 occitanie-ouest.cnrs.fr/fr/c…
Nicolas Farrugia retweeted
We address the challenge of domain shift when training on focal recordings and testing on soundscape recordings by using supervised contrastive learning. We evaluate our approach on a large-scale few-shot benchmark for bird sound classification.
``Domain-Invariant Representation Learning of Bird Sounds,'' Ilyass Moummad, Romain Serizel, Emmanouil Benetos, Nicolas Farrugia, ift.tt/6iW9vf1
Congratulations to our PhD student @raflaf_ for his new paper !
🎉 Thrilled to announce our paper "Oops, I Sampled it Again: Reinterpreting Confidence Intervals in Few-Shot Learning" accepted at #TMLR2024 ! 🎉
Big thanks to my amazing coauthors, including @jvlmdr @GriponVincent ! 🙌
🔗 tinyurl.com/yc35wpnt
📽️ tinyurl.com/4k79j49m
4
193
Nicolas Farrugia retweeted
🥳 Excited to share that our latest work on generating sample-based instruments from text or audio prompts has been accepted at #ISMIR2024! 🎹 — Our take on making AI-based music generation models useful for musicians!
🔊 gen-inst.netlify.app
📜 arxiv.org/abs/2407.15641
(1/6)
Nicolas Farrugia retweeted
Thrilled to share a review on THE LANGUAGE NETWORK AS A NATURAL KIND—a culmination of ~20 yrs of thinking about+studying language from linguistic, psycholinguistic, and cog neuro perspectives. @NatRevNeurosci rdcu.be/dEylV
With the amazing @neuranna @tamaregev 🥳
🧵1/n
Nicolas Farrugia retweeted
The end of 3 yrs of "ah this looks reassuring, but,"
biorxiv.org/content/10.1101/… let's dive in🧵
We investigated the link b/w source-localized continuous EEG (Movie &Rest) and individual anatomical scaffold using Eigenmodes / Graph Signal Processing(GSP)
Nicolas Farrugia retweeted
I am pleased to anounce that our work "Regularized Contrastive Pre-training for Few-shot Bioacoustic Sound Detection" (with @RSerizeland @milthampton) has been accepted for presentation at ICASSP 2024 !
Preprint: arxiv.org/abs/2309.08971
Github: github.com/ilyassmoummad/RCL…
Nicolas Farrugia retweeted
Aligning the activity of artificial and biological neural networks to build personalised models of auditory processing in a massive ... biorxiv.org/cgi/content/shor… #biorxiv_neursci
Nicolas Farrugia retweeted
I am looking for two postdocs to join us at Giessen University @jlugiessen, in collab. with the Max Planck Institute @MPI_CBS in Leipzig, funded by @ERC_Research & @ProLOEWE. We have exciting projects lined up but also offer a lot of freedom with implementing own ideas!👇 pls RT!
Our team BRAIn is hiring a tenured associate professor. Research in DL/ML with interests in few shot, graphs, signal processing and applications to neuro and audio. DM/ or eamil for more info or see here institutminestelecom.recruit…
Very honored to give a talk tomorrow at USC !
We are delighted to host Dr Nicolas Farrugia @milthampton this Monday Feb 13 @ 11 am (PST / Los Angeles) for a seminar at USC @USCViterbi
Title: Interpreting Brain Activity Through Connectivity Using Graph Signal Processing
👉 Join us at EEB 539 or DM me for a zoom link!
ALT Picture of Dr. Nicolas Farrugia Department of Mathematical and Electrical Engineering Better Representations for Artificial INtelligence (BRAIn) IMT Atlantique
ALT USC Viterbi
ALT University of Southern California
Content d avoir contribué à ce sujet pour @brutofficiel , merci @ChandrouKoumar !
Vous savez, cette petite mélodie qui sort de nulle part et qui squatte toute la journée dans votre tête… On appelle ça un "ver d'oreille".
À deux doigts de craquer, notre journaliste @ChandrouKoumar a voulu comprendre, alors il a demandé directement à un neuroscientifique.
A great hackathon organized by the BOB lab ! Awesome lineup of speakers too, check it out !
The BOB Hack!
Neuroimaging Hackathon
TO REGISTER: boblab.info
Dates and time:
30th November 8:30 - 20:00
1st December 9:00 - 19:30
2nd December 9:00 - 19:30
Students: €50*
Non-students/academic: €100
Corporate: €300
All levels of experience welcome!
Nicolas Farrugia retweeted
Jeudi soir, Sciences Po organisait un hommage à Bruno Latour, où quelques compagnons de pensée ont évoqué son oeuvre, scientifique et institutionnelle.
On m’a demandé d’y participer, et j’en ai profité pour dire ce qui à mon sens serait un héritage digne de cette oeuvre.
1/x
#ScPoLatour @LaurenceTubiana @picharbonnier et @Gemenne rendent hommage à l'expérimentateur Bruno Latour.
Comment fait-on de la vérité ? Éléments de réponse ici ➡️ youtu.be/D37nS_9eZGk
Nicolas Farrugia retweeted
A new position paper on why the emerging field of Neuro-AI is attracting a lot of interest + opening important paths for basic and applied research!
🧠🤖 #neuroai
👇👇
Massive whitepaper just dropped on why neuroscience progress should continue to drive AI progress: arxiv.org/pdf/2210.08340.pdf Argues for an embodied turing test. Needed: real interdisciplinary people, shared platform(s), fundamental research