Mathurin Massias
@mathurinmassias.bsky.social
Tenured Researcher @INRIA, Ockham team. Teacher @Polytechnique
and @ENSdeLyon
Machine Learning, Python and Optimization
and @ENSdeLyon
Machine Learning, Python and Optimization
Pinned
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 👇👇👇
🤯 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 👇👇👇
Reposted by Mathurin Massias
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/
All infos here: nkeriven.github.io/malaga/
MALAGA: Reinventing the Theory of Machine Learning on Large Graphs (ERC StG)
nkeriven.github.io
November 6, 2025 at 1:56 PM
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/
All infos here: nkeriven.github.io/malaga/
Reposted by Mathurin Massias
The JMLR story and operating model should be widely known in academia as a clear success story for full open access. I have friends in the humanities and pure sciences that have no clue this is even possible
November 5, 2025 at 1:16 AM
The JMLR story and operating model should be widely known in academia as a clear success story for full open access. I have friends in the humanities and pure sciences that have no clue this is even possible
🌀🌀🌀New paper on the generation phases of Flow Matching arxiv.org/abs/2510.24830
Are FM & diffusion models nothing else than denoisers at every noise level?
In theory yes, *if trained optimally*. But in practice, do all noise level equally matter?
with @annegnx.bsky.social, S Martin & R Gribonval
Are FM & diffusion models nothing else than denoisers at every noise level?
In theory yes, *if trained optimally*. But in practice, do all noise level equally matter?
with @annegnx.bsky.social, S Martin & R Gribonval
November 5, 2025 at 9:03 AM
🌀🌀🌀New paper on the generation phases of Flow Matching arxiv.org/abs/2510.24830
Are FM & diffusion models nothing else than denoisers at every noise level?
In theory yes, *if trained optimally*. But in practice, do all noise level equally matter?
with @annegnx.bsky.social, S Martin & R Gribonval
Are FM & diffusion models nothing else than denoisers at every noise level?
In theory yes, *if trained optimally*. But in practice, do all noise level equally matter?
with @annegnx.bsky.social, S Martin & R Gribonval
Kickstarting our workshop on Flow matching and Diffusion with a talk by Eric Vanden Eijnden on how to optimize learning and sampling in Stochastic Interpolants!
Broadcast available at gdr-iasis.cnrs.fr/reunions/mod...
Broadcast available at gdr-iasis.cnrs.fr/reunions/mod...
October 24, 2025 at 8:30 AM
Kickstarting our workshop on Flow matching and Diffusion with a talk by Eric Vanden Eijnden on how to optimize learning and sampling in Stochastic Interpolants!
Broadcast available at gdr-iasis.cnrs.fr/reunions/mod...
Broadcast available at gdr-iasis.cnrs.fr/reunions/mod...
Reposted by Mathurin Massias
My paper on Generalized Gradient Norm Clipping & Non-Euclidean (L0, L1)-Smoothness (together with collaborators from EPFL) was accepted as an oral at NeurIPS! We extend the theory for our Scion algorithm to include gradient clipping. Read about it here arxiv.org/abs/2506.01913
September 19, 2025 at 4:49 PM
My paper on Generalized Gradient Norm Clipping & Non-Euclidean (L0, L1)-Smoothness (together with collaborators from EPFL) was accepted as an oral at NeurIPS! We extend the theory for our Scion algorithm to include gradient clipping. Read about it here arxiv.org/abs/2506.01913
Our work on the generalization of Flow Matching got an oral at Neurips !
Go see @quentinbertrand.bsky.social present it there :)
Go see @quentinbertrand.bsky.social present it there :)
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 👇👇👇
🤯 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 👇👇👇
September 19, 2025 at 4:02 PM
Our work on the generalization of Flow Matching got an oral at Neurips !
Go see @quentinbertrand.bsky.social present it there :)
Go see @quentinbertrand.bsky.social present it there :)
Reposted by Mathurin Massias
🔥 Excited to announce the Workshop on the Principles of Generative Models at @euripsconf.bsky.social (the European conference parallel to NeurIPS 2025)
🇩🇰 Dec 6–7, Copenhagen
📝 Deadline for contributions: Oct 17
🔗 Website: sites.google.com/view/prigm-e...
🇩🇰 Dec 6–7, Copenhagen
📝 Deadline for contributions: Oct 17
🔗 Website: sites.google.com/view/prigm-e...
PriGM@EurIPS2025
Workshop summary
Machine learning theory has long focused on classical supervised learning settings, where a model is trained on input–label pairs drawn from a well-defined data distribution, with the...
sites.google.com
September 16, 2025 at 3:15 PM
🔥 Excited to announce the Workshop on the Principles of Generative Models at @euripsconf.bsky.social (the European conference parallel to NeurIPS 2025)
🇩🇰 Dec 6–7, Copenhagen
📝 Deadline for contributions: Oct 17
🔗 Website: sites.google.com/view/prigm-e...
🇩🇰 Dec 6–7, Copenhagen
📝 Deadline for contributions: Oct 17
🔗 Website: sites.google.com/view/prigm-e...
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...
Super elegant approach !
Distributional Reduction paper with H. Van Assel, @ncourty.bsky.social, T. Vayer , C. Vincent-Cuaz, and @pfrossard.bsky.social is accepted at TMLR. We show that both dimensionality reduction and clustering can be seen as minimizing an optimal transport loss 🧵1/5. openreview.net/forum?id=cll...
June 27, 2025 at 9:09 AM
Super elegant approach !
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 👇👇👇
🤯 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 👇👇👇
June 18, 2025 at 8:08 AM
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 👇👇👇
🤯 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 👇👇👇
It was received quite enthusiastically here so time to share it again!!!
Our #ICLR2025 blog post on Flow Matching was published yesterday : iclr-blogposts.github.io/2025/blog/co...
My PhD student @annegnx.bsky.social will present it tomorrow in ICLR, 👉poster session 4, 3 pm, #549 in Hall 3/2B 👈
Our #ICLR2025 blog post on Flow Matching was published yesterday : iclr-blogposts.github.io/2025/blog/co...
My PhD student @annegnx.bsky.social will present it tomorrow in ICLR, 👉poster session 4, 3 pm, #549 in Hall 3/2B 👈
A Visual Dive into Conditional Flow Matching | ICLR Blogposts 2025
Conditional flow matching (CFM) was introduced by three simultaneous papers at ICLR 2023, through different approaches (conditional matching, rectifying flows and stochastic interpolants). <br/> The m...
iclr-blogposts.github.io
April 24, 2025 at 1:45 PM
It was received quite enthusiastically here so time to share it again!!!
Our #ICLR2025 blog post on Flow Matching was published yesterday : iclr-blogposts.github.io/2025/blog/co...
My PhD student @annegnx.bsky.social will present it tomorrow in ICLR, 👉poster session 4, 3 pm, #549 in Hall 3/2B 👈
Our #ICLR2025 blog post on Flow Matching was published yesterday : iclr-blogposts.github.io/2025/blog/co...
My PhD student @annegnx.bsky.social will present it tomorrow in ICLR, 👉poster session 4, 3 pm, #549 in Hall 3/2B 👈
Reposted by Mathurin Massias
The proximal operator generalizes projection in convex optimization. It converts minimisers to fixed points. It is at the core of nonsmooth splitting methods and was first introduced by Jean-Jacques Moreau in 1965. www.numdam.org/article/BSMF...
April 15, 2025 at 5:00 AM
The proximal operator generalizes projection in convex optimization. It converts minimisers to fixed points. It is at the core of nonsmooth splitting methods and was first introduced by Jean-Jacques Moreau in 1965. www.numdam.org/article/BSMF...
Reposted by Mathurin Massias
🚢🚢 deepinv v0.3.0 is here, with many new features! 🚢 🚢
Our passionate team of contributors keeps shipping more exciting tools!
Deepinverse (deepinv.github.io) is a library for solving imaging inverse problems with deep learning.
Our passionate team of contributors keeps shipping more exciting tools!
Deepinverse (deepinv.github.io) is a library for solving imaging inverse problems with deep learning.
Redirecting to https://deepinv.github.io/deepinv/
deepinv.github.io
April 14, 2025 at 6:33 AM
🚢🚢 deepinv v0.3.0 is here, with many new features! 🚢 🚢
Our passionate team of contributors keeps shipping more exciting tools!
Deepinverse (deepinv.github.io) is a library for solving imaging inverse problems with deep learning.
Our passionate team of contributors keeps shipping more exciting tools!
Deepinverse (deepinv.github.io) is a library for solving imaging inverse problems with deep learning.
I had a blast giving a summer school on generative models at AI Hub Senegal, in particular flow matching, with @quentinbertrand.bsky.social and @remiemonet.bsky.social
Our material is publicly available !!! github.com/QB3/SenHubIA...
ensdelyon.bsky.social
Our material is publicly available !!! github.com/QB3/SenHubIA...
ensdelyon.bsky.social
April 14, 2025 at 7:50 AM
I had a blast giving a summer school on generative models at AI Hub Senegal, in particular flow matching, with @quentinbertrand.bsky.social and @remiemonet.bsky.social
Our material is publicly available !!! github.com/QB3/SenHubIA...
ensdelyon.bsky.social
Our material is publicly available !!! github.com/QB3/SenHubIA...
ensdelyon.bsky.social
Reposted by Mathurin Massias
Wow, this tutorial is really a tour de force! The one I had written is super "dumbed down" as a basic intro for beginners, but to really learn the material on an intermediate/advanced level, you should check out this post...
Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition!
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
March 25, 2025 at 9:32 PM
Wow, this tutorial is really a tour de force! The one I had written is super "dumbed down" as a basic intro for beginners, but to really learn the material on an intermediate/advanced level, you should check out this post...
Reposted by Mathurin Massias
🎓🌞 Join the PhD course on Theoretical Foundations of Machine Learning at 🇮🇹 ELLIS Unit Genoa, June 23-27, 2025, hosted by Machine Learning Genoa Center.
🗓️ Apply by: March 16, 2025
📍 University of Genoa (in-person only)
💡 More info: malga.unige.it/education/sc...
🗓️ Apply by: March 16, 2025
📍 University of Genoa (in-person only)
💡 More info: malga.unige.it/education/sc...
TFMLUniGe ¦ MaLGa
malga.unige.it
February 28, 2025 at 10:25 AM
🎓🌞 Join the PhD course on Theoretical Foundations of Machine Learning at 🇮🇹 ELLIS Unit Genoa, June 23-27, 2025, hosted by Machine Learning Genoa Center.
🗓️ Apply by: March 16, 2025
📍 University of Genoa (in-person only)
💡 More info: malga.unige.it/education/sc...
🗓️ Apply by: March 16, 2025
📍 University of Genoa (in-person only)
💡 More info: malga.unige.it/education/sc...
1-day workshop on Bilevel optimization and hyperparameter tuning at ENS de Lyon, on March 25th : gdr-iasis.cnrs.fr/reunions/bil...
Keynote talks by @jmairal.bsky.social @tonysf.bsky.social @samuelvaiter.com, Saverio Salzo and Luce Brotcorne, contributed talks are welcome!
Keynote talks by @jmairal.bsky.social @tonysf.bsky.social @samuelvaiter.com, Saverio Salzo and Luce Brotcorne, contributed talks are welcome!
Bilevel Optimization and Hyperparameter Learning - GdR IASIS
Bilevel optimization has become a crucial framework in machine learning for addressing hierarchical problems, where one optimization task depends on the outcome of another. This approach plays a pivot...
gdr-iasis.cnrs.fr
February 28, 2025 at 8:56 AM
1-day workshop on Bilevel optimization and hyperparameter tuning at ENS de Lyon, on March 25th : gdr-iasis.cnrs.fr/reunions/bil...
Keynote talks by @jmairal.bsky.social @tonysf.bsky.social @samuelvaiter.com, Saverio Salzo and Luce Brotcorne, contributed talks are welcome!
Keynote talks by @jmairal.bsky.social @tonysf.bsky.social @samuelvaiter.com, Saverio Salzo and Luce Brotcorne, contributed talks are welcome!
Reposted by Mathurin Massias
Our paper "PnP-Flow: Plug-and-Play Image Restoration with Flow Matching" has been accepted to ICLR 2025. Here a short explainer: We want to restore images (i.e., solve inverse problems) using pretrained velocity fields from flow matching. However, using change of variables is super costly.
January 23, 2025 at 10:53 AM
Our paper "PnP-Flow: Plug-and-Play Image Restoration with Flow Matching" has been accepted to ICLR 2025. Here a short explainer: We want to restore images (i.e., solve inverse problems) using pretrained velocity fields from flow matching. However, using change of variables is super costly.
Reposted by Mathurin Massias
Today something crazy happened. POT has reached 1000 citations (total) 🤩🚀. Very proud to be part of a scientific community that acknowledges open source research software. Please continue to use, cite and contribute to POT ! Small🧵below for those interested pythonot.github.io
December 13, 2024 at 9:54 AM
Today something crazy happened. POT has reached 1000 citations (total) 🤩🚀. Very proud to be part of a scientific community that acknowledges open source research software. Please continue to use, cite and contribute to POT ! Small🧵below for those interested pythonot.github.io
MLSS coming to Senegal !
📍 AIMS Mbour, Senegal
📅 June 23 - July 4, 2025
An international summer school to explore, collaborate, and deepen your understanding of machine learning in a unique and welcoming environment.
Details: mlss-senegal.github.io
📍 AIMS Mbour, Senegal
📅 June 23 - July 4, 2025
An international summer school to explore, collaborate, and deepen your understanding of machine learning in a unique and welcoming environment.
Details: mlss-senegal.github.io
MLSS Senegal 2025
mlss-senegal.github.io
December 12, 2024 at 8:45 AM
MLSS coming to Senegal !
📍 AIMS Mbour, Senegal
📅 June 23 - July 4, 2025
An international summer school to explore, collaborate, and deepen your understanding of machine learning in a unique and welcoming environment.
Details: mlss-senegal.github.io
📍 AIMS Mbour, Senegal
📅 June 23 - July 4, 2025
An international summer school to explore, collaborate, and deepen your understanding of machine learning in a unique and welcoming environment.
Details: mlss-senegal.github.io
Reposted by Mathurin Massias
every cool thing I've ever done happened because I had one-or-two people I could constantly annoy with messages like "ooh look what I found" "ooh look what I learned" "ooh look what I broke" and who did the same in return
November 27, 2024 at 2:06 PM
every cool thing I've ever done happened because I had one-or-two people I could constantly annoy with messages like "ooh look what I found" "ooh look what I learned" "ooh look what I broke" and who did the same in return
Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition!
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
November 27, 2024 at 9:00 AM
Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition!
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423
Johnson-Lindenstrauss lemma in action:
it is possible to embed any cloud of N points from R^d into R^k without distorting their respective distances too much, provided k is not too small (independently of d!)
Better: any random Gaussian embedding works with high proba!
it is possible to embed any cloud of N points from R^d into R^k without distorting their respective distances too much, provided k is not too small (independently of d!)
Better: any random Gaussian embedding works with high proba!
November 25, 2024 at 9:58 AM
Johnson-Lindenstrauss lemma in action:
it is possible to embed any cloud of N points from R^d into R^k without distorting their respective distances too much, provided k is not too small (independently of d!)
Better: any random Gaussian embedding works with high proba!
it is possible to embed any cloud of N points from R^d into R^k without distorting their respective distances too much, provided k is not too small (independently of d!)
Better: any random Gaussian embedding works with high proba!
Reposted by Mathurin Massias
This year, there are 16 positions at CNRS in computer science (8 in "applied" domains → ask me - 8 on "fundamental" domains → ask the other David).
@mathurinmassias.bsky.social has a good list of advice mathurinm.github.io/cnrs_inria_a...
Official 🔗 www.ins2i.cnrs.fr/en/cnrsinfo/...
Don't wait!
@mathurinmassias.bsky.social has a good list of advice mathurinm.github.io/cnrs_inria_a...
Official 🔗 www.ins2i.cnrs.fr/en/cnrsinfo/...
Don't wait!
November 23, 2024 at 7:33 PM
This year, there are 16 positions at CNRS in computer science (8 in "applied" domains → ask me - 8 on "fundamental" domains → ask the other David).
@mathurinmassias.bsky.social has a good list of advice mathurinm.github.io/cnrs_inria_a...
Official 🔗 www.ins2i.cnrs.fr/en/cnrsinfo/...
Don't wait!
@mathurinmassias.bsky.social has a good list of advice mathurinm.github.io/cnrs_inria_a...
Official 🔗 www.ins2i.cnrs.fr/en/cnrsinfo/...
Don't wait!
Conditioning of a function = ratio between highest and smallest eigenvalues of its Hessian.
Higher conditioning => harder to minimize the function
Gradient Descent gets faster on function with decreasing conditioning L/mu 👇
Higher conditioning => harder to minimize the function
Gradient Descent gets faster on function with decreasing conditioning L/mu 👇
November 22, 2024 at 1:52 PM
Conditioning of a function = ratio between highest and smallest eigenvalues of its Hessian.
Higher conditioning => harder to minimize the function
Gradient Descent gets faster on function with decreasing conditioning L/mu 👇
Higher conditioning => harder to minimize the function
Gradient Descent gets faster on function with decreasing conditioning L/mu 👇