Sign in

Paul Hagemann

@yungbayesian.bsky.social
881 followers 431 following 27 posts

PhD student at TU Berlin, working on generative models and inverse problems he/him

PostsRepliesMedia
Reposted by Paul Hagemann
Moritz Hürtgen @moritzhuertgen.de · 12/06/2026
Jede Wahrheit braucht einen Mutigen, der sie promptet
939336
Paul Hagemann @yungbayesian.bsky.social · 07/06/2026
deep down we all knew the mcmc ppl were somehow right
010
Reposted by Paul Hagemann
Aaron Roth @aaroth.bsky.social · 12/03/2026
My favorite translation use case is from informal english to precise mathematics.
092
Reposted by Paul Hagemann
Simon Olsson @smnlssn.bsky.social · 27/05/2025
We are looking for someone to join the group as a postdoc to help us with scaling implicit transfer operators. If you are interested in this, please reach out to me through email. Include CV, with publications and brief motivational statement. RTs appreciated!
1158
Reposted by Paul Hagemann
Simon Olsson @smnlssn.bsky.social · 06/05/2025
2025 CHAIR Structured Learning Workshop -- Apply to attend: ui.ungpd.com/Events/60bfc...
0135
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
Paul Hagemann @yungbayesian.bsky.social · 20/11/2024
In a somewhat recent paper we introduced conditional Wasserstein Distances. They generalize a property that basically explains why KL works well for generative modelling, the chain rule of KL! It says that if one wants to approximate the posterior, one can also minimize the KL between joints.
1150
Reposted by Paul Hagemann
Marvin Schmitt @marvin-schmitt.com · 17/11/2024
I created a starter pack for simulation-based inference (aka. likelihood-free inference). Let me know if you’d like me to add you. go.bsky.app/GVnJRoK
164218