Romain Tavenard
@rtavenar.bsky.social
140 followers 120 following 13 posts
Prof. at Univ. Rennes 2 ML for time series + a bit of Optimal Transport Maintainer of tslearn rtavenar.github.io
Posts Media Videos Starter Packs
Pinned
rtavenar.bsky.social
⚔️ 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
Solutions to the PAWL problem in 1D for different amounts of mass to be transported
Reposted by Romain Tavenard
cnrsinformatics.bsky.social
#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
Reposted by Romain Tavenard
samuelvaiter.com
Now accepted at #NeurIPS2025 :)
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
rtavenar.bsky.social
My point is rather that typst language is much more human-readable than LaTeX and as a result, I feel cetz is a relief compared to TikZ
rtavenar.bsky.social
TikZ equivalent in typst is cetz, and it is such a pleasure to write code for TikZ-like diagrams in a language that is human-readable
rtavenar.bsky.social
tbh, if you could share a nice slide template in typst, I'm 100% sure I would fall into the trap next time I need to prepare a slide deck
Reposted by Romain Tavenard
rflamary.bsky.social
I missed it last month! Very happy to present POT next week at PyData Paris.
pydataparis.bsky.social
📢 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
rtavenar.bsky.social
So much deserved ! Congrats
Reposted by Romain Tavenard
akorba.bsky.social
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.
Reposted by Romain Tavenard
marazulv.bsky.social
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
Reposted by Romain Tavenard
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?
Reposted by Romain Tavenard
rtavenar.bsky.social
Same here, and one of the 2 reviewers whose score disappeared explicitly stated in their review that they would update their score.
Reposted by Romain Tavenard
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...
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
Reposted by Romain Tavenard
ulrikeluxburg.bsky.social
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?
euripsconf.bsky.social
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
Reposted by Romain Tavenard
rflamary.bsky.social
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
Reposted by Romain Tavenard
ambroiseodt.bsky.social
🚀 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
Reposted by Romain Tavenard
bgalerne.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/...
Graphs of Wasserstein errors for various diffusion model samplers
Reposted by Romain Tavenard
vletzelter.bsky.social
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
Reposted by Romain Tavenard
cslg-bot.bsky.social
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 Romain Tavenard
guillaumehiet.bsky.social
🔒 We’re hiring a postdoc at Inria SUSHI (Rennes, FR)! Work on formal verification of security across compilers, OS & hardware (e.g., RISC-V, CompCert).
📍 Rennes 🇫🇷 | 💶 ~€3K–3.2K/mo | 🛠️ Formal methods + security
📧 [email protected]
team.inria.fr/sushi/files/...
#Hiring #FormalMethods #RISC-V
team.inria.fr
rtavenar.bsky.social
Check out this paper for more on the topic !

bsky.app/profile/math...
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 👇👇👇
Reposted by Romain Tavenard
rflamary.bsky.social
Very honored to have given the keynote at the CAP 2025 conference in Dijon this morning. I talked about Domain adaptation, DA benchmark and applications of DA to sleep stating. Mostly work from the PhD of @tgnassou.bsky.social For those interested here are the slides remi.flamary.com/pres/OTDA_Ke...
remi.flamary.com