Romain Tavenard
rtavenar.bsky.social
Romain Tavenard
@rtavenar.bsky.social
Prof. at Univ. Rennes 2

ML for time series + a bit of Optimal Transport
Maintainer of tslearn

rtavenar.github.io
Pinned
⚔️ One for all and all for one ⚔️
Efficient computation of PArtial Wasserstein distances on the Line (PAWL)

is accepted to @iclr-conf.bsky.social

Joint work with Laetitia Chapel: we introduce an 𝑂(𝑛 𝑙𝑜𝑔 𝑛) solver for partial Optimal Transport (OT) in 1D

openreview.net/forum?id=kzE...

🧵 1/2
Reposted by Romain Tavenard
One of those internships is on Gromov $\delta$-hyperbolicity for GNNs, and will be cosupervised together with Nicolas, myself and Laetitia Chapel. Take a look and spread the words !
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/
MALAGA: Reinventing the Theory of Machine Learning on Large Graphs (ERC StG)
nkeriven.github.io
November 7, 2025 at 1:45 PM
Reposted by Romain Tavenard
Yesterday @tgnassou.bsky.social successfully defended his PhD thesis on domain adaptation of signals and in particular EEG. Huge congrats to him for all his work and his wonderful slides. It was a pleasure to be his advisor with @agramfort.bsky.social and I can't wait to see what he will do next!
November 7, 2025 at 11:10 AM
Reposted by Romain Tavenard
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/
MALAGA: Reinventing the Theory of Machine Learning on Large Graphs (ERC StG)
nkeriven.github.io
November 6, 2025 at 1:56 PM
Reposted by Romain Tavenard
🌀🌀🌀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
November 5, 2025 at 9:03 AM
Reposted by Romain Tavenard
Want to work on generative models and Earth Observation? 🌍

I'm looking for:
🧑‍💻 an intern on generative models for change detection
🧑‍🔬 a PhD student on neurosymbolic generative models for geospatial data

Both starting beginning of 2026.

Details are below, feel free to email me!
November 4, 2025 at 10:08 AM
Reposted by Romain Tavenard
I’m recruiting a postdoctoral researcher on a fully funded 2-year contract. The topic is developing and implementing new parallel graph algorithms, with applications to data-driven transportation and logistics.
Details and application procedure below ⬇️ Reach out if you have any questions!
acme-mobidec.github.io
October 27, 2025 at 5:43 PM
Reposted by Romain Tavenard
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...
October 24, 2025 at 8:30 AM
Reposted by Romain Tavenard
Probably the best paper title of my career. To read with the Indiana jones soundtrack. And yes we solved and differentiated quite well 80 millions (small) Fused Gromov Wasserstein problems per epoch using a neural network on GPU.
Our latest paper “The Quest for the GRAph Level autoEncoder (GRALE)” was accepted at NeurIPS 2025!

arxiv.org/abs/2505.22109

🏆 GRALE 🏆 can encode and decode graphs into and from a shared Euclidean space.

Training such a model should require solving the graph matching problem but...
The quest for the GRAph Level autoEncoder (GRALE)
Although graph-based learning has attracted a lot of attention, graph representation learning is still a challenging task whose resolution may impact key application fields such as chemistry or biolog...
arxiv.org
October 16, 2025 at 3:17 PM
Reposted by Romain Tavenard
blogbinaire.larecherche.fr/2025/10/10/l...

Sur le blog binaire de La recherche
Julie Josse : L’intelligence artificielle et la fabrique du savoir clinique

Julie Josse a reçu le Prix Jeune Chercheur 2024 de l’Académie de Sciences.
L’intelligence artificielle et la fabrique du savoir clinique – Blog binaire
blogbinaire.larecherche.fr
October 11, 2025 at 7:20 AM
Reposted by Romain Tavenard
#Distinction 🏆| Charlotte Pelletier, lauréate d'une chaire #IUF, développe des méthodes d’intelligence artificielle appliquées aux séries temporelles d’images satellitaires.
➡️ www.ins2i.cnrs.fr/fr/cnrsinfo/...
🤝 @irisa-lab.bsky.social @cnrs-bretagneloire.bsky.social
October 8, 2025 at 9:30 AM
Reposted by Romain Tavenard
Now accepted at #NeurIPS2025 :)
📣 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
September 29, 2025 at 10:48 AM
Reposted by Romain Tavenard
I am happy to share that our paper "Unsupervised Learning for Optimal Transport plan prediction between unbalanced graphs" was accepted at Neurips 2025 ! 🥳

Huge thanks to my co-authors @rflamary.bsky.social and Bertrand Thirion !

arxiv.org/abs/2506.12025

(1/5)
Unsupervised Learning for Optimal Transport plan prediction between unbalanced graphs
Optimal transport between graphs, based on Gromov-Wasserstein and other extensions, is a powerful tool for comparing and aligning graph structures. However, solving the associated non-convex optimizat...
arxiv.org
September 29, 2025 at 8:55 AM
Reposted by Romain Tavenard
Vous pouvez soutenir ma proposition à la Cour des Comptes d'examiner les marchés publics de voyagistes, notamment dans l'ESR :
participationcitoyenne.ccomptes.fr/processes/co...
Les marchés publics de voyagistes - Contributions - 2025 - Aidez-nous à enrichir notre programme de travail - Plateforme de participation de la Cour des Comptes
Corps de la contributionLes administrations et opérateurs publics, notamment ceux de l'enseignement supérieur et de la recherche, fond appel à des agences de voyage (FCM, TravelPlanet…) pour l'hôtelle...
participationcitoyenne.ccomptes.fr
September 25, 2025 at 10:28 AM
Reposted by Romain Tavenard
I missed it last month! Very happy to present POT next week at PyData Paris.
📢 Talk Announcement

"Optimal Transport in Python: A Practical Introduction with POT", by Rémi Flamary.

📜 Talk info: pretalx.com/pydata-paris-2025/talk/FNCKXU
📅 Schedule: pydata.org/paris2025/schedule
🎟 Tickets: pydata.org/paris2025/tickets
September 23, 2025 at 6:29 PM
Reposted by Romain Tavenard
I'm thrilled to announce that my #ERCStG project **Optinfinite : Efficient infinite-dimensional optimization over measures**
has been accepted. Thank you
@erc.europa.eu !
Many thanks also to @crestumr.bsky.social @ipparis.bsky.social for they support, as well as to my collaborators and friends.
September 8, 2025 at 6:39 AM
Reposted by Romain Tavenard
Thanks @ellis.eu !
ellis.eu ELLIS @ellis.eu · Aug 27
Meet @marazulv.bsky.social, Associate Prof. at EURECOM 🇫🇷 & ELLIS Member, researching AI for health. She recently received an @erc.europa.eu Consolidator Grant to advance her work on the cerebrovascular tree’s role in brain health with novel AI tools.

#WomenInELLIS
August 27, 2025 at 8:44 AM
Reposted by Romain Tavenard
Maybe there should also be an equivalent EurIPS workshop www.eurips.cc for people who cannot or don't want to travel there?
August 8, 2025 at 3:05 PM
Reposted by Romain Tavenard
Eloi Tanguy, Laetitia Chapel, Julie Delon: Sliced Optimal Transport Plans https://arxiv.org/abs/2508.01243 https://arxiv.org/pdf/2508.01243 https://arxiv.org/html/2508.01243
August 5, 2025 at 6:40 AM
Reposted by Romain Tavenard
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...
SKADA-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...
openreview.net
July 29, 2025 at 12:54 PM
Reposted by Romain Tavenard
I love the #eurips initiative! But to live up to its potential, it should be accepted an official #neurips conference location (similar to Mexico City) and not just an addon! Then we would save C02, rather than adding to it!!! What can we do to achieve this?
EurIPS is coming! 📣 Mark your calendar for Dec. 2-7, 2025 in Copenhagen 📅

EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu

eurips.cc
July 21, 2025 at 4:30 PM
Reposted by Romain Tavenard
This is awful! We need to treat our scientists better if we want to do good science. This means consistent funding for tenure that allows time for risky but novel discoveries and not only short-time projects and infinite post-docs. www.science.org/content/arti...
My academic job offer was rescinded. I’ll keep going—but U.S. researchers are running out of road
Despite an uncertain future, this postdoc will “keep doing the science I love while I still have a bench”
www.science.org
July 23, 2025 at 1:16 PM
Reposted by Romain Tavenard
🚀 We are happy to organize the BERT²S workshop @neuripsconf.bsky.social 2025 on Recent Advances in Time Series Foundation Models.
🌐 berts-workshop.github.io
📜Submit by August 22
🎓Speakers and panelists: Chenghao Liu, Mingsheng Long, Zoe Piran, Danielle C. Maddix, Ameet Talwalkar, Qingsong Wen
July 22, 2025 at 2:41 PM
Reposted by Romain Tavenard
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
Reposted by Romain Tavenard
Interested in time series forecasting or data uncertainty quantification?
Check out our latest paper with Adrien Cortés at @icmlconf !

Paper: arxiv.org/abs/2506.05515
Code: github.com/Victorletzel...
Poster #2211 , Tue 15 Jul 11 a.m. PDT East
#timeseries #quantization #uncertainty #icml2025
July 14, 2025 at 9:40 PM