Rémi Emonet

Rémi Emonet

@remiemonet.bsky.social

64 followers21 following42 posts

Rémi Emonet reposted

aboisbunon.bsky.social
@aboisbunon.bsky.social

I'm happy to announce the #NeurIPS2026 workshop TS-LIMITS (Generalization for Time Series in Tight Settings: Latency, Inference, Memory, prIvacy and susTainability), which will be hosted in Paris, France 🇫🇷, Dec 12–13 2026! 🔗 Check out details and call for papers: ts-limits.github.io

Rémi Emonet reposted

Samuel Vaiter
@samuelvaiter.com

Now accepted at #NeurIPS2025 :)

Samuel Vaiter@samuelvaiter.com

📣 New preprint 📣 **Differentiable Generalized Sliced Wasserstein Plans** w/ L. Chapel @rtavenar.bsky.social We propose a Generalized Sliced Wasserstein method that provides an approximated transport plan and which admits a differentiable approximation. arxiv.org/abs/2505.22049 1/5

Rémi Emonet reposted

Mathurin Massias
@mathurinmassias.bsky.social

Our work on the generalization of Flow Matching got an oral at Neurips ! Go see @quentinbertrand.bsky.social present it there :)

Mathurin Massias@mathurinmassias.bsky.social

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 👇👇👇

Rémi Emonet reposted

Mathurin Massias
@mathurinmassias.bsky.social

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...

gdr-iasis.cnrs.frModèles génératifs : diffusion, flow matching et leurs applications - GdR IASISLes 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...
Rémi Emonet
@remiemonet.bsky.social

Maybe there should also be an equivalent EurIPS workshop www.eurips.cc for people who cannot or don't want to travel there?

eurips.ccEurIPS Copenhagen 2025 - A NeurIPS-endorsed conference in EuropeA NeurIPS-endorsed conference in Europe held in Copenhagen, Denmark
Nicolas Mathevon@nicolasmathevon.bsky.social

NeurIPS workshop (6 dec 2025, San Diego): "AI for non-human animal communication": aiforanimalcomms.org It will explore the intersection of artificial intelligence and bioacoustics, aiming to address challenges in processing complex #bioacoustics data and interpreting animal signals.

aiforanimalcomms.orgAI for Non-Human Animal Communication - NeurIPS 2025 WorkshopJoin leading researchers and practitioners at the NeurIPS 2025 workshop to explore AI applications in understanding and facilitating non-human animal communication.

Rémi Emonet reposted

Rémi Flamary
@rflamary.bsky.social

SKADA-Bench : Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation On Diverse Modalities, has been published published in TMLR today 🚀. It was a huge team effort to design (and publish) an open source fully reproducible DA benchmark 🧵1/n. openreview.net/forum?id=k9F...

openreview.netSKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods...Unsupervised Domain Adaptation (DA) consists of adapting a model trained on a labeled source domain to perform well on an unlabeled target domain with some data distribution shift. While many...

Rémi Emonet reposted

Camille
@k1000journaliste.bsky.social

🔴 [TUTO] : Comment économiser légalement PLUSIEURS CENTAINES D'EUROS sur son loyer chaque mois à Paris. Il suffit de faire respecter ✨l'encadrement des loyers✨ à son propriétaire. Petit tuto en thread pour vous montrer comment faire. Pour l'exemple on va prendre cet appart.

Rémi Emonet reposted

Mathurin Massias
@mathurinmassias.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 👈

iclr-blogposts.github.ioA Visual Dive into Conditional Flow Matching | ICLR Blogposts 2025Conditional 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...

Rémi Emonet reposted

Scott H. Hawley
@drscotthawley.bsky.social

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...

Mathurin Massias@mathurinmassias.bsky.social

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

Rémi Emonet reposted

Rémi Flamary
@rflamary.bsky.social

Titouan Vayer and I are organizing a one day workshop on optimal transport and machine learning in ENS Lyon on Feb. 17. Registration is free but mandatory. The incredible keynote speakers are Laetitia Chapel, Filippo Santambrogio and @brunolevy01.bsky.social. gdr-iasis.cnrs.fr/reunions/tra...

gdr-iasis.cnrs.frTransport optimal et ses applications en machine learning et analyse de données - GdR IASISPour les journées scientifiques organisées en 2025 : les inscriptions seront ouvertes à partir de mi-janvier et les demandes de prise en charge de missions seront traitées à partir du 27 janvier. En r...

Rémi Emonet reposted

Rémi Flamary
@rflamary.bsky.social

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

Rémi Emonet
@remiemonet.bsky.social

About Conditional Flow Matching (CFM) with **linear interpolation**. (1/3) In Optimal Transport (OT) terms, this CFM induces a probability path that corresponds to the (much non-optimal) independent coupling. That means every cat point is split and sent to every donut point.

Gabriel Peyré@gabrielpeyre.bsky.social

Optimal transport computes an interpolation between two distributions using an optimal coupling. Flow matching, on the other hand, uses a simpler “independent” coupling, which is the product of the marginals.

View full thread
Rémi Emonet
@remiemonet.bsky.social

It is still not optimal from the OT perspective (same path as before). Indeed, the points do not move in a constant-speed manner (as they would do with optimal transport). However, we see that the mapping between cat and donut points has a strong spatial coherence (colors don't get shuffled).

Rémi Emonet
@remiemonet.bsky.social

About Conditional Flow Matching (CFM) with **linear interpolation**. (1/3) In Optimal Transport (OT) terms, this CFM induces a probability path that corresponds to the (much non-optimal) independent coupling. That means every cat point is split and sent to every donut point.

Gabriel Peyré@gabrielpeyre.bsky.social

Optimal transport computes an interpolation between two distributions using an optimal coupling. Flow matching, on the other hand, uses a simpler “independent” coupling, which is the product of the marginals.

Rémi Emonet
@remiemonet.bsky.social

Now, we look at the mapping/correspondance that is induced by CFM, a mapping between cat points and donut points. To get a clearer view, let's map a stripped cat to a donut. Color encodes the initial position of the points on the cat.