Sign in

Samuel Vaiter

@samuelvaiter.com
3.1K followers 273 following 454 posts

CNRS Researcher website: samuelvaiter.com

PostsRepliesMedia
Samuel Vaiter @samuelvaiter.com · 08/09/2026
Navier-Stokes is cool, but did you see OoT remake trailer?
041
Samuel Vaiter @samuelvaiter.com · 29/07/2026
Reviewer #2
Official Review by Reviewer wTfF of *The Odysseus* (2026)

Summary: Odysseus is lost and try to find his way during three hours.

Strengths
- The images are crisp.
- The subject is timely.
Weaknesses
- Why does Leslie Groves is in this movie? This does not make sense in term of history, the director should revise antiquity 101.
- Who is Helen? I don't think this is correctly explained. I heard "Paris" but this does not make sense, Paris is a city!
- I think the cyclope eye was not in the right direction.
- At minute 203, the sound was not correctly mixed, which really break the immersion.

Question:
- Could you reframe the movie to portrait mode for better readability?

Rating : 2
Confidence : 5
0132
Reposted by Samuel Vaiter
Guillaume @guillaume-garrigos.com · 20/07/2026
As I am preparing my calculus notes for next year, the resolution of the jacobian conjecture comes at the perfect time! Today I've learned a few things surrounding this result, which i'll gather in a thread 1/n
1104
Reposted by Samuel Vaiter
CNRS Mathématiques @cnrs-insmi.bsky.social · 03/07/2026
Toutes nos félicitations à Sylvia Serfaty, lauréate du prix #Riemann 2025 🏅 La récompense lui a été décernée lors de la semaine du prix Riemann, organisée du 29 juin au 3 juillet 2026 à Varèse, en Italie. Pour en savoir plus : www.rism.it/riemann-priz...
094
Reposted by Samuel Vaiter
G'MIC @gmic-eu.bsky.social · 01/07/2026
🎉 G'MIC 4.0.0 is here — a major release focused on stability. It also opens a new chapter: fewer releases ahead, with more focus on framework robustness & performance rather than big changes. The core is mature — now we polish it. Developed @ GREYC lab (CNRS/ENSICAEN/UniCaen) ▶️ gmic.eu @cnrs.fr
0113
Samuel Vaiter @samuelvaiter.com · 25/06/2026
This is incredible. scrollprize.org/firstscroll
scrollprize.org
An entire Herculaneum scroll has been read for the first time
PHerc. 1667, sealed since the eruption of Vesuvius in 79 AD, has been virtually unwrapped and read from beginning to end — without ever being opened.
071
Reposted by Samuel Vaiter
LJAD-Off @ljad-off.bsky.social · 25/06/2026
Congratulations to Sophie Jaffard laureate of the prize Jacques Neveu from SMAI, for her phd on mathematical models of neuronal learning
031
Samuel Vaiter @samuelvaiter.com · 20/06/2026
Bienvenue à Nice, ville avec une des plus basses températures de France ! (ps: je recrute potentiellement un.e postdoc sur 24 mois d'ici fin 2026 sur des questions, plutôt théoriques, liées aux LLMs en post-training / alignment, je dis ça, je dis rien)
0135
Reposted by Samuel Vaiter
Gabriel Peyré @gabrielpeyre.bsky.social · 16/06/2026
The alpha version of my new book "Optimal Transport for Machine Learners" is out, with in particular an online version with interactive figures www.gpeyre.com/ot4ml/
09843
Samuel Vaiter @samuelvaiter.com · 15/06/2026
I’m back
010
Samuel Vaiter @samuelvaiter.com · 04/05/2026
Now accepted at ICML 2026! Congrats to Magamed :)
072
Reposted by Samuel Vaiter
Gabriel Peyré @gabrielpeyre.bsky.social · 16/04/2026
While it is intuitively clear that straighter trajectories should reduce discretization error when integrating an ODE (for instance, in flow matching), I could not find a precise bound. I therefore rewrote the proof of Cauchy-Lipschitz to make this explicit. github.com/gpeyre/Discr...
1286
Samuel Vaiter @samuelvaiter.com · 27/03/2026
PS5 beats S&P500. Rethink your investment strategy.
110
Samuel Vaiter @samuelvaiter.com · 17/03/2026
We hosted in Nice @aymericdieuleveut.bsky.social & A. Taylor for the SMAI-MODE 2026 mini-course on Performance Estimation Problems with 9 hours of lectures + practicals in two days All material freely available 👇 performanceestimation.github.io/Tutorial-SMA... Thanks to both of them!
1113
Reposted by Samuel Vaiter
LJAD-Off @ljad-off.bsky.social · 09/03/2026
🔎 Journée internationale des droits des femmes : portrait de Simona Rota Nodari, chercheuse en mathématiques au LJAD, à découvrir dans « Ces femmes qui font bouger les lignes » 👉 univ-cotedazur.shorthandstories.com/ces-femmes-q... #8mars #FemmesEnScience #UniversiteCoted'Azur #VilledeNice #CNRS
035
Samuel Vaiter @samuelvaiter.com · 09/03/2026
🧵 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
1103
Reposted by Samuel Vaiter
Rémi Flamary @rflamary.bsky.social · 29/01/2026
Bullshit is like entropy nowadays it can only increase.
121
Samuel Vaiter @samuelvaiter.com · 29/01/2026
It’s incredible that the growth rate of administrative bullshit outpaces LLM progress, but here we are.
140
Samuel Vaiter @samuelvaiter.com · 22/01/2026
Vu que le chauffage est visiblement un détail, on trouve des alternatives. Startup-nation 🤘
050
Reposted by Samuel Vaiter
Yann Traonmilin @ytraonmilin.bsky.social · 19/01/2026
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
wmathsia2026.sciencesconf.org
Workshop sur les mathématiques de l'IA - Sciencesconf.org
Le workshop se déroulera sous forme de présentations sur appel à contribution (résumé d'une page). Une session poster sera organisée au besoin selon le nombre de contributions.
1136
Samuel Vaiter @samuelvaiter.com · 17/01/2026
After the 2168 series, I read @fabinou.bsky.social series on building a Quake PC fabiensanglard.net/quake_pc/ (late 90s-style), it brings back so much memories 😍!
fabiensanglard.net
030
Samuel Vaiter @samuelvaiter.com · 16/01/2026
I tested Pocket TTS from Kyutai. It's fun to use for generating French sentences: the accent is strong, but it's still perfectly understandable, even though French doesn't seem to be in the training dataset! Beyond that, the model is quite impressive especially knowing it has only 100M parameters
github.com
GitHub - kyutai-labs/pocket-tts: A TTS that fits in your CPU (and pocket)
A TTS that fits in your CPU (and pocket). Contribute to kyutai-labs/pocket-tts development by creating an account on GitHub.
1120
Samuel Vaiter @samuelvaiter.com · 16/01/2026
Extension pour soumettre une communication : deadline au 21 janvier 23:59 !
011
Samuel Vaiter @samuelvaiter.com · 15/12/2025
Les inscriptions aux journées MODE 2026 à Nice sont désormais ouvertes. Elles se dérouleront du 18 au 20 mars à l'Hôtel Saint-Paul. Les inscriptions sont ouvertes jusqu'au 1 mars (majoration > 9/02). La deadline pour soumettre une communication est le **15 janvier**.
157
Samuel Vaiter @samuelvaiter.com · 11/12/2025
Mail annuel du CNRS pour savoir si tu as obtenu le prix Nobel ✅
140
Samuel Vaiter @samuelvaiter.com · 03/12/2025
I am at #NeurIPS2025, reach out if you want to chat!
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
011
Reposted by Samuel Vaiter
Transactions on Machine Learning Research @tmlrorg.bsky.social · 01/12/2025
🏅Finalist: Gradient Scarcity in Graph Learning with Bilevel Optimization, by Hashem GHANEM, Samuel Vaiter, Nicolas Keriven 5/n openreview.net/forum?id=10Y...
openreview.net
Gradient Scarcity in Graph Learning with Bilevel Optimization
Gradient scarcity emerges when learning graphs by minimizing a loss on a subset of nodes under the semi-supervised setting. It consists in edges between unlabeled nodes that are far from the...
151
Reposted by Samuel Vaiter
Fares El Khoury @fareselkhoury.bsky.social · 01/12/2025
Happy to be at #NeurIPS in San Diego to present our poster ‘Learning Theory for Kernel Bilevel Optimization’ #3005, Fri at 4:30 p.m. Stop by/ping me to chat, especially about statistics, causality, generative models! Let's connect! Joint w/ E. Pauwels, @samuelvaiter.com, @michael-arbel.bsky.social
031
Reposted by Samuel Vaiter
Nicolas Keriven @nicolaskeriven.bsky.social · 06/11/2025
I have several offers for Master internships / PhDs on graph ML funded by ERC MALAGA for 2026. Don't hesitate to contact me to apply! All infos here: nkeriven.github.io/malaga/
nkeriven.github.io
MALAGA: Reinventing the Theory of Machine Learning on Large Graphs (ERC StG)
088
Samuel Vaiter @samuelvaiter.com · 05/11/2025
Drame : je me suis gouré de bus à Massy et là je visite *toute* la startup-nation
150
Samuel Vaiter @samuelvaiter.com · 29/10/2025
Est-ce que certain d'entre vous #ESR sont dans un laboratoire qui gère les missions / conférences avec un système de ticket genre GLPI ou Jira ? Si oui, est-ce que c'est l'apocalypse ou plutôt mieux qu'une gestion traditionnel ? Si non, quel niveau d'enthousiasme ou de dégout cela vous inspire ?
321
Samuel Vaiter @samuelvaiter.com · 14/10/2025
Les journées SMAI-MODE 2026 auront lieu à Nice du 18 au 20 mars 2026, précédées par un mini-cours les 16/17. Vous pouvez déposer votre proposition de contrib sur mode2026.sciencesconf.org Inscription à partir du 1er décembre pour finir le 1 mars (avec un tarif majoré à compter du 1 février).
mode2026.sciencesconf.org
Journées SMAI-MODE 2026 - Sciencesconf.org
Du 18 au 20 mars 2025, l'Université Côte d'Azur accueille les journées SMAI-MODE, la conférence biennale du groupe MODE de la Société de Mathématiques Appliquées et Industrielles (SMAI).
144
Samuel Vaiter @samuelvaiter.com · 02/10/2025
Now accepted to #NeurIPS2025, congrats to @fareselkhoury.bsky.social for his first ML paper!
070
Samuel Vaiter @samuelvaiter.com · 01/10/2025
Happy to share that I have been promoted to senior research scientist (directeur de recherche (*)) at @cnrs.fr effective today! Grateful to my amazing students, collaborators and mentors who made this journey possible. I will continue my research at the math lab of UniCA @ljad-off.bsky.social.
1170
Samuel Vaiter @samuelvaiter.com · 29/09/2025
Je viens de réaliser que mon employeur, sans me donner la possibilité d'acquérir un téléphone pro, exige une politique de sécurité sur mon code de smartphone pour accéder aux emails. Je viens donc de faire ce que j'aurai du faire il y a dix ans : enlever mes mails pros de mon téléphone perso 🤷‍♂️
050
Samuel Vaiter @samuelvaiter.com · 29/09/2025
Now accepted at #NeurIPS2025 :)
2186
Reposted by Samuel Vaiter
CNRS @cnrs.fr · 11/09/2025
#Communiqué 🗞️ La médaille d'or 2025 du CNRS est décernée à Stéphane Mallat, mondialement reconnu pour ses travaux autour des mathématiques appliquées au traitement du signal et à l’intelligence artificielle. 👏 👉 cnrs.fr/fr/presse/en... #TalentsCNRS 🏅
39844
Samuel Vaiter @samuelvaiter.com · 04/09/2025
Sur le marché public de ma fac, il y a deux hotels de disponible paris intra-muros (1 mois et demi en avance). Et pas "deux" comme une manière de dire peu, DEUX = D-E-U-X = 2. Putain de marché public à la con. Putain de règles administratives à la con.
130
Samuel Vaiter @samuelvaiter.com · 15/08/2025
20 years later I still love this city!
040
Reposted by Samuel Vaiter
Nicolas Keriven @nicolaskeriven.bsky.social · 05/08/2025
I'm BEYOND THRILLED to tell you that our first original song is now available on all platforms! Plz share if you like it 🙏🏼🙏🏼😊 Cheers
141
Samuel Vaiter @samuelvaiter.com · 09/07/2025
Congratulations to Dr. Sophie Jaffard @sophiejaffard.bsky.social for a brillant PhD defense! We were very lucky with Patricia to have you as a PhD student, and I am sure that you will have a brillant career ahead.
1141
Reposted by Samuel Vaiter
Mathemarium (LJAD) @mathemarium.bsky.social · 04/07/2025
1/2 Julia Brun (M1) «Modèles particulaires de type Cucker-Smale et limites de champ moyen» gagne le prix K. Johnson 🎉 avec un voyage à Paris et visite de la Maison Poincaré #parité #maths #Nice06 #fillesEtMaths @cnrs-insmi.bsky.social @univcotedazur.bsky.social @cnrscotedazur.bsky.social
182
Samuel Vaiter @samuelvaiter.com · 03/07/2025
A reviewer in my batch submitted a review shorter than a tweet. wtf
010
Samuel Vaiter @samuelvaiter.com · 23/06/2025
AWS chatbot is amazing. Q: I cant login neither I can reset my password because phone number verification is not working. A: If you cant reset your password, login into your account to reset your MFA.
030
Samuel Vaiter @samuelvaiter.com · 21/06/2025
Expedition 33 might be overhyped. Let me add my contribution: This is an incredibile masterpiece.
130
Reposted by Samuel Vaiter
Mathurin Massias @mathurinmassias.bsky.social · 18/06/2025
New paper on the generalization of Flow Matching www.arxiv.org/abs/2506.03719 🤯 Why does flow matching generalize? Did you know that the flow matching target you're trying to learn *can only generate training points*? w @quentinbertrand.bsky.social @annegnx.bsky.social @remiemonet.bsky.social 👇👇👇
25617
Samuel Vaiter @samuelvaiter.com · 17/06/2025
I am sure that the number of faculty follows the same curve /s
020
Samuel Vaiter @samuelvaiter.com · 16/06/2025
Ma matinée
120
Reposted by Samuel Vaiter
Romain Tavenard @rtavenar.bsky.social · 16/06/2025
It seems other authors* have just reached similar conclusions (large minibatches help for OT-CFM), using entropic-reg OT in place of our bilevel-sliced OT * Michal Klein, Alireza Mousavi-Hosseini, Stephen Zhang, @marcocuturi.bsky.social arxiv.org/abs/2506.05526
arxiv.org
On Fitting Flow Models with Large Sinkhorn Couplings
Flow models transform data gradually from one modality (e.g. noise) onto another (e.g. images). Such models are parameterized by a time-dependent velocity field, trained to fit segments connecting pai...
052
Samuel Vaiter @samuelvaiter.com · 13/06/2025
I wrote in my notes few years ago a *suboptimal* (and maybe wrong 😅) lower bounds of GD for smooth strongly convex function. Nesterov's proof uses seq w/ values in ℝ^ℕ (so infinite dimensional), whereas I do a similar strategy as in the convex case, ie in ℝ^n 1/3 samuelvaiter.com/intro-to-low...
samuelvaiter.com
Introduction to lower bounds in optimization | Samuel Vaiter
222