Bruno Galerne
@bgalerne.bsky.social
Professor in applied mathematics at University of Orléans 🇫🇷 & IUF Junior 2022 on an innovation chair.
Interested in image processing and deep generative models.
I teach generative models for imaging at #MasterMVA.
Interested in image processing and deep generative models.
I teach generative models for imaging at #MasterMVA.
Reposted by Bruno Galerne
I'm now also looking for a postdoc with strong Bayesian background and interest in developing Bayesian cross-validation theory, methods and software. Apply by email with no specific deadline (see contact information at users.aalto.fi/~ave/).
Others, please share
Others, please share
I'm looking for a doctoral student with Bayesian background to work on Bayesian workflow and cross-validation (see my publication list users.aalto.fi/~ave/publica... for my recent work) at Aalto University.
Apply through the ELLIS PhD program (dl October 31) ellis.eu/news/ellis-p...
Apply through the ELLIS PhD program (dl October 31) ellis.eu/news/ellis-p...
ELLIS PhD Program: Call for Applications 2025
The ELLIS mission is to create a diverse European network that promotes research excellence and advances breakthroughs in AI, as well as a pan-European PhD program to educate the next generation of AI...
ellis.eu
October 29, 2025 at 2:37 PM
I'm now also looking for a postdoc with strong Bayesian background and interest in developing Bayesian cross-validation theory, methods and software. Apply by email with no specific deadline (see contact information at users.aalto.fi/~ave/).
Others, please share
Others, please share
Reposted by Bruno Galerne
Holy moly. The current WNBA salaries are (accounting for inflation) still below the salaries of the ABL, a player-centric WBB league that preceded and, for a moment, competed with the WNBA.
This new @secretbase.bsky.social video is great, especially for someone like me who didn't know the history AT ALL. Very telling/infuriating detail: WNBA players' salaries in 2025 are still below ABL salaries in 1996 *without accounting for inflation* 🤯
Also, @katestarbird.bsky.social gets a mention
Also, @katestarbird.bsky.social gets a mention
An MVP switching leagues was a big deal
YouTube video by Secret Base
www.youtube.com
September 19, 2025 at 5:59 PM
Holy moly. The current WNBA salaries are (accounting for inflation) still below the salaries of the ABL, a player-centric WBB league that preceded and, for a moment, competed with the WNBA.
Reposted by Bruno Galerne
One-day workshop on Diffusion models and Flow matching, October 24th at @ensdelyon.bsky.social
Registration and call for contributions (short talk and poster) are open at
gdr-iasis.cnrs.fr/reunions/mod...
Registration and call for contributions (short talk and poster) are open at
gdr-iasis.cnrs.fr/reunions/mod...
Modèles génératifs : diffusion, flow matching et leurs applications - GdR IASIS
Les modèles génératifs ont connu de récentes avancées spectaculaires, au point que leurs dernières versions sont désormais capables de produire des images et du texte synthétiques presque indiscernabl...
gdr-iasis.cnrs.fr
September 4, 2025 at 7:40 AM
One-day workshop on Diffusion models and Flow matching, October 24th at @ensdelyon.bsky.social
Registration and call for contributions (short talk and poster) are open at
gdr-iasis.cnrs.fr/reunions/mod...
Registration and call for contributions (short talk and poster) are open at
gdr-iasis.cnrs.fr/reunions/mod...
Reposted by Bruno Galerne
I can't* fathom why the top picture, and not the bottom picture, is the standard diagram for an autoencoder.
The whole idea of an autoencoder is that you complete a round trip and seek cycle consistency—why lay out the network linearly?
The whole idea of an autoencoder is that you complete a round trip and seek cycle consistency—why lay out the network linearly?
August 29, 2025 at 10:46 PM
I can't* fathom why the top picture, and not the bottom picture, is the standard diagram for an autoencoder.
The whole idea of an autoencoder is that you complete a round trip and seek cycle consistency—why lay out the network linearly?
The whole idea of an autoencoder is that you complete a round trip and seek cycle consistency—why lay out the network linearly?
Reposted by Bruno Galerne
Si on supprimait la CSG payée par les retraités et qu'en même temps on baissait les retraites du même montant, Rien n'aurait changé mais on pourrait dire "on a baissé le taux de prélèvement obligatoire de 0,75 point de PIB" et le niveau de dépense d'autant.
Et alors ?
Et alors ?
August 28, 2025 at 1:42 PM
Si on supprimait la CSG payée par les retraités et qu'en même temps on baissait les retraites du même montant, Rien n'aurait changé mais on pourrait dire "on a baissé le taux de prélèvement obligatoire de 0,75 point de PIB" et le niveau de dépense d'autant.
Et alors ?
Et alors ?
Welcome @univorleans.bsky.social #ESR
August 28, 2025 at 10:16 AM
Welcome @univorleans.bsky.social #ESR
Reposted by Bruno Galerne
For Europeans, this is a reference to an iconic Norman Rockwell image painted during the desegregation of southern schools. The difference is that in that image the federal law enforcement officials were the good guys.
August 23, 2025 at 7:25 AM
For Europeans, this is a reference to an iconic Norman Rockwell image painted during the desegregation of southern schools. The difference is that in that image the federal law enforcement officials were the good guys.
Reposted by Bruno Galerne
I just discovered this tree view. Why isn't this enabled by default? Only this really makes sense for complex threads.
August 11, 2025 at 9:05 PM
I just discovered this tree view. Why isn't this enabled by default? Only this really makes sense for complex threads.
Reposted by Bruno Galerne
#IPAM (the institute for pure and applied mathematics) is facing a critical shortfall for operating expenses due to an unexpected suspension of NSF funding www.ipam.ucla.edu/news/nsf-fun... . Donations for emergency continuity of operations funding can be made at
giving.ucla.edu/Campaign/Donat
giving.ucla.edu/Campaign/Donat
www.ipam.ucla.edu
August 8, 2025 at 12:48 AM
#IPAM (the institute for pure and applied mathematics) is facing a critical shortfall for operating expenses due to an unexpected suspension of NSF funding www.ipam.ucla.edu/news/nsf-fun... . Donations for emergency continuity of operations funding can be made at
giving.ucla.edu/Campaign/Donat
giving.ucla.edu/Campaign/Donat
Reposted by Bruno Galerne
Oh crap #MathSky, that institute is IPAM! Having IPAM destroyed is a legit disaster for a large part of the math community 😭
www.ipam.ucla.edu
www.ipam.ucla.edu
August 1, 2025 at 10:20 PM
Oh crap #MathSky, that institute is IPAM! Having IPAM destroyed is a legit disaster for a large part of the math community 😭
www.ipam.ucla.edu
www.ipam.ucla.edu
20 years ago this day I had the chance to participate to the RIPS IPAM program… it was my first experience on research in image processing, a very impactful and enriching experience. I hope IPAM can be preserved!
Terence Tao (@teorth.bsky.social) has written a thread on Mastodon about the impact of the federal grant freeze to UCLA, particularly to his own field of Mathematics. UCLA's IPAM (Institute of Pure and Applied Mathematics) could shut down entirely
mathstodon.xyz/@tao/1149568...
mathstodon.xyz/@tao/1149568...
Terence Tao (@tao@mathstodon.xyz)
The current administration in the US has, through various funding agencies such as the NSF and NIH, has recently suspended virtually all federal grants to my home university, UCLA (including my own p...
mathstodon.xyz
August 3, 2025 at 6:06 AM
20 years ago this day I had the chance to participate to the RIPS IPAM program… it was my first experience on research in image processing, a very impactful and enriching experience. I hope IPAM can be preserved!
Reposted by Bruno Galerne
Terence Tao (@teorth.bsky.social) has written a thread on Mastodon about the impact of the federal grant freeze to UCLA, particularly to his own field of Mathematics. UCLA's IPAM (Institute of Pure and Applied Mathematics) could shut down entirely
mathstodon.xyz/@tao/1149568...
mathstodon.xyz/@tao/1149568...
Terence Tao (@tao@mathstodon.xyz)
The current administration in the US has, through various funding agencies such as the NSF and NIH, has recently suspended virtually all federal grants to my home university, UCLA (including my own p...
mathstodon.xyz
August 2, 2025 at 6:27 PM
Terence Tao (@teorth.bsky.social) has written a thread on Mastodon about the impact of the federal grant freeze to UCLA, particularly to his own field of Mathematics. UCLA's IPAM (Institute of Pure and Applied Mathematics) could shut down entirely
mathstodon.xyz/@tao/1149568...
mathstodon.xyz/@tao/1149568...
Reposted by Bruno Galerne
As a #NeurIPS AC I did a little stat. Paper reviews+responses in my batch contain 515k characters and 75k words. This is without including papers themselves or authors/reviewers discussions. So please be nice to your AC, we are doing our best. Also I miss the one page PDF response of old ICML.
August 1, 2025 at 7:06 AM
As a #NeurIPS AC I did a little stat. Paper reviews+responses in my batch contain 515k characters and 75k words. This is without including papers themselves or authors/reviewers discussions. So please be nice to your AC, we are doing our best. Also I miss the one page PDF response of old ICML.
La #RIPEC C1 c’est bien mais il y a mieux pour certains chercheurs :
- chargés de recherche : 6 290 € ;
- directeur de recherche : 8 230 €
- chargés de recherche : 6 290 € ;
- directeur de recherche : 8 230 €
[#JORF #JORFESR] Arrêté du 30 juillet 2025 fixant le montant annuel des composantes indemnitaires créées par l'article 2 du décret n° 2025-731 du 30 juillet 2025 portant création du régime indemnitaire des chercheurs ...
📰 https://www.legifrance.gouv.fr/jorf/id/JORFTEXT000052009675
📰 https://www.legifrance.gouv.fr/jorf/id/JORFTEXT000052009675
July 31, 2025 at 7:46 AM
La #RIPEC C1 c’est bien mais il y a mieux pour certains chercheurs :
- chargés de recherche : 6 290 € ;
- directeur de recherche : 8 230 €
- chargés de recherche : 6 290 € ;
- directeur de recherche : 8 230 €
Revalorisation historique !
#Salaires | En 2023, le salaire net moyen dans la fonction publique de l'État est de 2 886 € par mois en équivalent temps plein. Compte tenu du contexte de forte inflation (4,9 % en 2023), il baisse de nouveau en euros constants (-0,4 %).
👉 www.insee.fr/fr/statistiq...
👉 www.insee.fr/fr/statistiq...
July 24, 2025 at 3:05 PM
Revalorisation historique !
Eure-et-Loir forever !
On l’apprend grâce à @etiennecatalan.bsky.social : Guerschon Yabusele portera le numéro 28 aux Knicks !
July 22, 2025 at 6:16 AM
Eure-et-Loir forever !
Reposted by Bruno Galerne
On l’apprend grâce à @etiennecatalan.bsky.social : Guerschon Yabusele portera le numéro 28 aux Knicks !
July 19, 2025 at 7:48 AM
On l’apprend grâce à @etiennecatalan.bsky.social : Guerschon Yabusele portera le numéro 28 aux Knicks !
Reposted by Bruno Galerne
Malgré le rapport du Sénat sur les 211 Mds€ (!) d'aides aux entreprises, rien dans les propositions qui envisage de les réinterroger
retrouver le rapport du Sénat : www.senat.fr/rap/r24-808-...
3/6
retrouver le rapport du Sénat : www.senat.fr/rap/r24-808-...
3/6
July 21, 2025 at 2:45 PM
Malgré le rapport du Sénat sur les 211 Mds€ (!) d'aides aux entreprises, rien dans les propositions qui envisage de les réinterroger
retrouver le rapport du Sénat : www.senat.fr/rap/r24-808-...
3/6
retrouver le rapport du Sénat : www.senat.fr/rap/r24-808-...
3/6
Reposted by Bruno Galerne
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.
July 21, 2025 at 2:47 PM
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.
Reposted by Bruno Galerne
⚠️⬛ "Année blanche" ou annonce d'une série noire pour le service public ?
Il y aurait beaucoup à dire sur les annonces budgétaires du premier ministre ce mardi.
Mais le plus frappant, c'est peut-être combien les conséquences de ce plan sur les services publics sont invisibilisées.
Thread 1/14 ⤵️
Il y aurait beaucoup à dire sur les annonces budgétaires du premier ministre ce mardi.
Mais le plus frappant, c'est peut-être combien les conséquences de ce plan sur les services publics sont invisibilisées.
Thread 1/14 ⤵️
July 20, 2025 at 8:56 AM
⚠️⬛ "Année blanche" ou annonce d'une série noire pour le service public ?
Il y aurait beaucoup à dire sur les annonces budgétaires du premier ministre ce mardi.
Mais le plus frappant, c'est peut-être combien les conséquences de ce plan sur les services publics sont invisibilisées.
Thread 1/14 ⤵️
Il y aurait beaucoup à dire sur les annonces budgétaires du premier ministre ce mardi.
Mais le plus frappant, c'est peut-être combien les conséquences de ce plan sur les services publics sont invisibilisées.
Thread 1/14 ⤵️
Reposted by Bruno Galerne
Organize your mathematical event in 2027 at CIRM!
APPEL D'OFFRES EN FRANÇAIS ➡️ fr-cirm-math.fr/appels-doffr...
CALL IN ENGLISH ➡️ cirm-math.com/calls-for-pr... MERCI DE PARTAGER - PLEASE SHARE THE POST @cnrs-insmi.bsky.social @cnrs-dr12.bsky.social @univ-amu.fr @euromathsoc.bsky.social
APPEL D'OFFRES EN FRANÇAIS ➡️ fr-cirm-math.fr/appels-doffr...
CALL IN ENGLISH ➡️ cirm-math.com/calls-for-pr... MERCI DE PARTAGER - PLEASE SHARE THE POST @cnrs-insmi.bsky.social @cnrs-dr12.bsky.social @univ-amu.fr @euromathsoc.bsky.social
July 16, 2025 at 10:11 AM
Organize your mathematical event in 2027 at CIRM!
APPEL D'OFFRES EN FRANÇAIS ➡️ fr-cirm-math.fr/appels-doffr...
CALL IN ENGLISH ➡️ cirm-math.com/calls-for-pr... MERCI DE PARTAGER - PLEASE SHARE THE POST @cnrs-insmi.bsky.social @cnrs-dr12.bsky.social @univ-amu.fr @euromathsoc.bsky.social
APPEL D'OFFRES EN FRANÇAIS ➡️ fr-cirm-math.fr/appels-doffr...
CALL IN ENGLISH ➡️ cirm-math.com/calls-for-pr... MERCI DE PARTAGER - PLEASE SHARE THE POST @cnrs-insmi.bsky.social @cnrs-dr12.bsky.social @univ-amu.fr @euromathsoc.bsky.social
Tommorrow Emile Pierret will present our paper "Diffusion models for Gaussian distributions: Exact solutions and Wasserstein errors". #ICML2025 Tue 15 Jul 11 a.m. West Exhibition Hall B2-B3 #W-1015. More details here: pierret.perso.math.cnrs.fr/publication/...
July 15, 2025 at 3:35 AM
Tommorrow Emile Pierret will present our paper "Diffusion models for Gaussian distributions: Exact solutions and Wasserstein errors". #ICML2025 Tue 15 Jul 11 a.m. West Exhibition Hall B2-B3 #W-1015. More details here: pierret.perso.math.cnrs.fr/publication/...
Reposted by Bruno Galerne
Emile Pierret, Bruno Galerne: Exact Evaluation of the Accuracy of Diffusion Models for Inverse Problems with Gaussian Data Distributions https://arxiv.org/abs/2507.07008 https://arxiv.org/pdf/2507.07008 https://arxiv.org/html/2507.07008
July 10, 2025 at 6:33 AM
Emile Pierret, Bruno Galerne: Exact Evaluation of the Accuracy of Diffusion Models for Inverse Problems with Gaussian Data Distributions https://arxiv.org/abs/2507.07008 https://arxiv.org/pdf/2507.07008 https://arxiv.org/html/2507.07008
Reposted by Bruno Galerne
After all these reports of authors adding language instructions for LLM reviews in their papers I wanted to check this myself and I downloaded the .tex source from one of these papers.
Here is an example.
(I will not share the identity of the paper)
Here is an example.
(I will not share the identity of the paper)
July 5, 2025 at 5:12 PM
After all these reports of authors adding language instructions for LLM reviews in their papers I wanted to check this myself and I downloaded the .tex source from one of these papers.
Here is an example.
(I will not share the identity of the paper)
Here is an example.
(I will not share the identity of the paper)
Reposted by Bruno Galerne
"in 2025 we will have flying cars" 😂😂😂
July 5, 2025 at 4:17 PM
"in 2025 we will have flying cars" 😂😂😂