🧵 New preprint! Towards Understanding Steering Strength w/ M. Taimeskhanov and D. Garreau
Activation steering is a popular way to control LLM behavior at inference. But how much should you steer? We provide the first theoretical analysis of the steering strength α.
📄 arxiv.org/abs/2602.02712
1/7
On rappelle aux candidat·es dans les sections cnu 25, 26, 27, et 61 que l'opération postes fête ses 28 bougies cette année :
postes.smai.emath.fr/current/inde...
Tu as essayé bloctel ? Il me semble que j'en ai entendu du bien, mais pas essayé pour ma part.
Oh yes please ! My email is on my page there rtavenar.github.io/research/bio...
So please apply! Details in the document attached to the LinkedIn post
Is your code publicly available? Can these materials be reused by others?
If you are a master student and are interested by these topics, have a look at this internship offer, with possible continuation into a PhD.
www.linkedin.com/posts/romain...
Post-doc opportunity at EDF R&D on Time Series Foundation Models. It’s a great project and I’ll be closely involved in the collaboration!
Details for application at:
www.linkedin.com/posts/etienn...
This semester I have been given the chance to teach a course on "Deep Learning for Time Series" at @ipparis.bsky.social
If you're interested in the topics, have a look at rtavenar.github.io/x-dl4ts/
Repo has Typst code for the slides and Python code for the labs.
Feedback is very much welcome.
This year I'm teaching a new course on generative models for visual content (images, video, 3D, etc). It's mostly me rambling about recent papers, design choices I like/hate. The slides of the first lectures are here: davidpicard.github.io/teaching/
Use right arrow to navigate past the blank page.
With @quentinbertrand.bsky.social we have one offer for a Marie Sklodowska-Curie postdoctoral fellowships at Inria, to work on generative models : www.inria.fr/en/marie-skl...
contact me if interested! RT appreciated ❤️
Source Wikipedia. Vue de Peyresq, localité des Alpes-de-Haute-Provence, village pittoresque perché à 1 526 m d'altitude sur un éperon rocheux que surplombe la vallée de la Vaïre
Formez-vous en "Modèles génératifs et transport optimal" à 1500 mètres d'altitude : encore 10 jours, clôture le 27 février 2026 des inscriptions pour l'école d'été #Peyresq2026 (21 au 27 juin 2026) #GdR
gretsi.fr/peyresq2026
#GRETSI #gdrIASIS
We are recruiting four positions connected to Machine Learning, Statistical Learning, and AI for Science in the Applied Mathematics department at École polytechnique. Join our vibrant community at IP Paris and Hi! Paris IA center. List below🧵 tinyurl.com/3jpw9t26
There is an Associate Professor position in CS at ENS Lyon, with potential integration in my team, starting in sept 2026: DM me in interested!
Details at www.ens-lyon.fr/LIP/images/P...
Open position: Monge Assistant Professor (Tenure track) on graph learning and/or LLMs, in the applied math dpt. at École polytechnique. Reduced teaching load, many funding opportunities, good students and academic freedom. Contact me if interested. Deadline March 23rd tinyurl.com/MongeAssista...
Save the date : on organise un workshop sur les maths de l'IA à Bordeaux les 4-6 novembre. N'hésitez pas ! plus on est de fous plus on rit ! (dans les limites des capacités d'accueil haha)
Dates & infos :
wmathsia2026.sciencesconf.org
🏹 Job alert: 3 PhD positions in AI, Earth Observation, and Science-Policy interface
📍 Vannes 🇫🇷 & Ispra 🇮🇹
📅 Apply by Jan 15th
🔗 https://www-obelix.irisa.fr/job-offers/
L'école d'été #Peyresq2026 #GRETSI portera sur le thème "Modèles génératifs et transport optimal" du 21 au 27 juin 2026
gretsi.fr/peyresq2026
Inscription du 18 décembre 2025 au 27 février 2026
Ami-es du #GRETSI, qq chiffres pour "GRETSI Info" : progressions (LinkedIn, chaîne YouTube), relative déception en libre (Mastodon). Pour faire mieux : partagez ce QR code !
38 Bluesky
17 Mastodon
29 X
71 Youtube
186 LinkedIn page
294 LinkedIn contacts
354 LinkedIn abonnements
Openreview opened the door to continuous and major revisions that nobody has time to check properly.
I think that we should come back to short one pdf page replies to reviews. It would mean having decisions quicker so that we actually have time to work on papers before resubmitting them.
Ecole d'été de Peyresq sur les modèles génératifs et le transport optimal : www.gretsi.fr/peyresq2026 (cours en français). Date limite de candidature le 27 février
From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers. R. Kawata · Y. Song · A. Bietti · N. Nishikawa · T. Suzuki · SV · D. Wu. Wed, Dec 3, 2025 • 4:30 PM – 7:30 PM PST, #4001 (spotlight) Differentiable Generalized Sliced Wasserstein Plans. L. Chapel · R. Tavenard · SV. Fri, Dec 5, 2025 • 11:00 AM – 2:00 PM PST, #1000 Learning Theory for Kernel Bilevel Optimization. F. El Khoury · E. Pauwels · SV · M. Arbel. Fri, Dec 5, 2025 • 4:30 PM – 7:30 PM PST, #3005
I am at #NeurIPS2025, reach out if you want to chat!
Sonia and I will present this work this afternoon at the NeuripS@Paris poster session. Come see us if you are around.
I am happy to share that I will be at NeurIPS in San Diego to present our paper with @rflamary.bsky.social and Bertrand Thirion on optimal transport plan prediction between graphs.
If you are around come say hi!
Paper: arxiv.org/abs/2506.12025
Poster #3703 Friday 5 December 4:30 - 7:30 pm
🚗🌐 Working on domain adaptation for 3D point clouds / LiDAR?
We'll present MuDDoS at BMVC: a method that boosts multimodal distillation for 3D semantic segmentation under domain shift.
📍 BMVC
🕚 Monday, Poster Session 1: Multimodal Learning (11:00–12:30)
📌 Hadfield Hall #859
Simulation-based inference (SBI) has transformed parameter inference across a wide range of domains. To help practitioners get started and make the most of these methods, we joined forces with researchers from many institutions and wrote a practical guide to SBI.
📄 Paper: arxiv.org/abs/2508.12939
Une raison de plus de vous abonner à la chaîne YouTube du colloque #GRETSI :
"Transport optimal, de Monge à l’apprentissage profond", conférence plénière de Julie Delon au colloque #GRETSI2025
www.youtube.com/watch?v=ujYS...
One of those internships is on Gromov $\delta$-hyperbolicity for GNNs, and will be cosupervised together with Nicolas, myself and Laetitia Chapel. Take a look and spread the words !
Awesome thesis, awesome defense, congrats @tgnassou.bsky.social !
