Sign in

Anne Gagneux

@annegnx.bsky.social
54 followers 45 following 0 posts

PhD in Ockham Inria team @EnsDeLyon

PostsRepliesMedia
Reposted by Anne Gagneux
Mathurin Massias @mathurinmassias.bsky.social · 05/11/2025
🌀🌀🌀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
1204
Reposted by Anne Gagneux
Mathurin Massias @mathurinmassias.bsky.social · 18/06/2025
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 👇👇👇
25617
Reposted by Anne Gagneux
Mathurin Massias @mathurinmassias.bsky.social · 24/04/2025
On Saturday Anne will also present some very, very cool work on how to leverage Flow Matching models to obtain sota Plug and Play methods: PnP-Flow: Plug-and-Play Image Restoration with Flow Matching, poster #150 in poster session 6, Saturday at 3 pm arxiv.org/abs/2410.02423
arxiv.org
PnP-Flow: Plug-and-Play Image Restoration with Flow Matching
In this paper, we introduce Plug-and-Play (PnP) Flow Matching, an algorithm for solving imaging inverse problems. PnP methods leverage the strength of pre-trained denoisers, often deep neural networks...
151
Reposted by Anne Gagneux
Mathurin Massias @mathurinmassias.bsky.social · 24/04/2025
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.io
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...
1106
Reposted by Anne Gagneux
Paul Hagemann @yungbayesian.bsky.social · 23/01/2025
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.
1155
Reposted by Anne Gagneux
Mathurin Massias @mathurinmassias.bsky.social · 27/11/2024
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
1235299