Quentin Bertrand
@quentinbertrand.bsky.social
📤 132
📥 33
📝 4
Machine Learning Researcher at Inria
reposted by
Quentin Bertrand
Tony S.F.
4 months ago
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
1
14
3
reposted by
Quentin Bertrand
Mathurin Massias
4 months ago
Our work on the generalization of Flow Matching got an oral at Neurips ! Go see
@quentinbertrand.bsky.social
present it there :)
add a skeleton here at some point
3
25
3
reposted by
Quentin Bertrand
Mathurin Massias
7 months ago
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
👇👇👇
loading . . .
2
55
20
What an amazing week with insightful discussions and interactions!
@franceausenegal.bsky.social
add a skeleton here at some point
9 months ago
0
1
0
reposted by
Quentin Bertrand
Olivier Grisel
10 months ago
Recently merged in scikit-learn's main branch: display the maximum predicted class probability in 2D continuous feature spaces (mostly for didactic purposes):
scikit-learn.org/dev/auto_exa...
The linked example has been updated to include some conclusions we can draw from this plot.
2
31
6
reposted by
Quentin Bertrand
Rémi Emonet
about 1 year ago
Visit the playground at the end of our blog post (with co-authors
@annegnx.bsky.social
, Ségolène Martin,
@mathurinmassias.bsky.social
,
@quentinbertrand.bsky.social
)
dl.heeere.com/cfm#cfm-play...
0
0
1
reposted by
Quentin Bertrand
Gaël Varoquaux
about 1 year ago
👩🎓👨🎓 Internship offers (1st step to PhD program) in my group:
team.inria.fr/soda/job-off...
Topics: ◼ Health AI & causality, accounting for censoring (for people who love health impact) ◼ Foundation models for tabular learning (for people into bigger models) Come work with us!
0
40
12
This blog post provides intuition and nice illustrations to understand normalizing flows and flow matching techniques! w.
@annegnx.bsky.social
, Ségolène Martin,
@mathurinmassias.bsky.social
, and
@remiemonet.bsky.social
(the king for figures)
add a skeleton here at some point
about 1 year ago
0
5
1
Very cool ref! Did not know about it!
add a skeleton here at some point
about 1 year ago
1
2
0
reposted by
Quentin Bertrand
Valentin De Bortoli
about 1 year ago
Nice blogpost and very cool illustrations 😍. I will die on the hill that most of the FM ideas where introduced back in 2021 by Stefano Peluchetti in his underappreciated paper
openreview.net/forum?id=oVf...
2
11
3
reposted by
Quentin Bertrand
Mathurin Massias
about 1 year ago
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
loading . . .
12
354
113
you reached the end!!
feeds!
log in