Good Papers

Showing papers from TU Dortmund Show all papers

76%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Johannes-Gutenberg Universität MTU DortmundU MainzJulius-Maximilians-Universität WDomain adaptation

We Need to Rethink Benchmarking in Anomaly Detection

Current anomaly detection benchmarks stagnate because trivial feature-extreme methods match deep learning, so evaluation must shift to scenario-specific taxonomies with tailored metrics.

Philipp Röchner, Simon Klüttermann, Kevin Kammler, Franz Rothlauf and 2 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 10 of 20 reviewers recommend it
lenient 5/5
medium 4/10
strict 1/5
76%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Max Planck Institute for InformaMax-Planck Institute for InformaTU DortmundFlow matching

CSFlow: Aligning Flow Matching with Human Contrast Sensitivity

CSFlow aligns flow matching with human contrast sensitivity via timestep weights that match generated spatial frequencies to visual perception, improving image quality and reducing FID by 4.7%.

Malgorzata Galinska, Bart Pogodzinski, Jan Eric Lenssen

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
10/20 AI panelreviewers recommend it

Readers and the AI panel: vote on this paper to see what they said.

Only vote on papers you've read. Sign in with GitHub to vote.

AI panel: 10 of 20 reviewers recommend it
lenient 4/5
medium 6/10
strict 0/5