Samuel Vaiter @samuelvaiter.com · 08/09/2026Oui : github.com/openai/Navie...github.comGitHub - openai/NavierStokesAndEuler: Lean certificates accompanying Navier-Stokes and Euler resultsLean certificates accompanying Navier-Stokes and Euler results - openai/NavierStokesAndEuler 130
Samuel Vaiter @samuelvaiter.com · 08/09/2026Navier-Stokes is cool, but did you see OoT remake trailer? 041
Samuel Vaiter @samuelvaiter.com · 02/08/2026Moi aussi j’aime utiliser k-NN. Mais seulement avec une métrique apprise basée sur un réseau à 1T de paramètres 😶 141
Reposted by Samuel VaiterGuillaume @guillaume-garrigos.com · 20/07/2026As 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 VaiterCNRS Mathématiques @cnrs-insmi.bsky.social · 03/07/2026Toutes 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 VaiterG'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 · 25/06/2026This is incredible. scrollprize.org/firstscrollscrollprize.orgAn entire Herculaneum scroll has been read for the first timePHerc. 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 VaiterLJAD-Off @ljad-off.bsky.social · 25/06/2026Congratulations 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 · 24/06/2026Si tu veux je t’héberges au LJAD. C’est un peu comme la Bretagne mais on a des montagnes et il fait plus frais. 120
Samuel Vaiter @samuelvaiter.com · 20/06/2026Bienvenue 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 VaiterGabriel Peyré @gabrielpeyre.bsky.social · 16/06/2026The 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
Reposted by Samuel VaiterGabriel Peyré @gabrielpeyre.bsky.social · 16/04/2026While 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 · 20/03/2026Our last plenary speaker was Stephane Gaubert on tropical geometry applied to optimization. 000
Samuel Vaiter @samuelvaiter.com · 20/03/2026For the last day, Julie Delon gives an introduction to Flow Matching with the PoV of an applied mathematician. 130
Samuel Vaiter @samuelvaiter.com · 19/03/2026And before our conference dinner, we had the pleasure to hear Yann Brenier with an outreach talk on the role of optimal transport in applied mathematics. 140
Samuel Vaiter @samuelvaiter.com · 19/03/2026The second day started with a brillant plenary talk of @pierreablin.bsky.social on LLM pretraining and some explanations of scaling laws. 120
Samuel Vaiter @samuelvaiter.com · 18/03/2026This afternoon, we start with Irène Waldspurger on semidefinite optimization 140
Samuel Vaiter @samuelvaiter.com · 18/03/2026We listened this morning to the talk of Francisco Silva Álvarez on mean field games in a packed room! 130
Samuel Vaiter @samuelvaiter.com · 17/03/2026We 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 VaiterLJAD-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 · 09/03/2026TL;DR: Steering strength α has precise, predictable effects on LLM outputs. Understanding these laws may help design better steering strategies. Paper: arxiv.org/abs/2602.02712 Code: github.com/MagamedT/steering 7/7arxiv.orgTowards Understanding Steering StrengthA popular approach to post-training control of large language models (LLMs) is the steering of intermediate latent representations. Namely, identify a well-chosen direction depending on the task at ha... 010
Samuel Vaiter @samuelvaiter.com · 09/03/2026We validate everything empirically on 11 models (GPT-2, Gemma 3, Qwen 3, Llama 2, Mistral 7B) across 8 safety-related concepts. All our theorems are confirmed experimentally. 6/7 100
Samuel Vaiter @samuelvaiter.com · 09/03/2026Result 3: Steering always hurts global performance. Cross-entropy increases quadratically around α = 0, i.e., there's no free lunch. For large α, performance plateaus because the output becomes input-independent. 5/7 110
Samuel Vaiter @samuelvaiter.com · 09/03/2026Result 2: Concept probability follows a sigmoidal curve. The probability that the target concept appears in the output increases smoothly with α, following a tanh shape. Off-target concepts decrease or vanish. 4/7 100
Samuel Vaiter @samuelvaiter.com · 09/03/2026Result 1: Next-token probabilities have a bump shape. As α increases, most token probabilities rise, peak for α>0, then fall. In particular, off-target tokens peak _before_ target tokens. 3/7 100
Samuel Vaiter @samuelvaiter.com · 09/03/2026Take contrastive prompts (for ex, safe vs malicious), evaluate them through the model, compute the mean difference of representations at layer ℓ. That's your steering vector v. Then shift activations by αv at layer ℓ. Question: what does α actually do? 2/7 100
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
Samuel Vaiter @samuelvaiter.com · 18/02/2026Je pensais que c'était une façon de parler le 30, du coup j'ai été voir. watzeactualfuk? 011
Reposted by Samuel VaiterRémi Flamary @rflamary.bsky.social · 29/01/2026Bullshit is like entropy nowadays it can only increase. 121
Samuel Vaiter @samuelvaiter.com · 29/01/2026My god I never thought about it in this way. This is just the second law of thermodynamics 😍! 120
Samuel Vaiter @samuelvaiter.com · 29/01/2026The issue is that fighting bullshit (LLMs or not) requires more effort than generating it (LLMs or not). We are doomed to lose. 100
Samuel Vaiter @samuelvaiter.com · 29/01/2026It’s incredible that the growth rate of administrative bullshit outpaces LLM progress, but here we are. 140
Samuel Vaiter @samuelvaiter.com · 22/01/2026Vu que le chauffage est visiblement un détail, on trouve des alternatives. Startup-nation 🤘 050
Reposted by Samuel VaiterYann Traonmilin @ytraonmilin.bsky.social · 19/01/2026Save 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.orgwmathsia2026.sciencesconf.orgWorkshop sur les mathématiques de l'IA - Sciencesconf.orgLe 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 · 17/01/2026Tu sais te mettre de bonne humeur le samedi matin toi 😐 110
Samuel Vaiter @samuelvaiter.com · 17/01/2026After 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
