74%Highly rated
?Highly ratedVote to see the score
Robust Diffusion Models via Divergence-Induced Weighted Denoising
Replacing diffusion denoising loss with f-divergence-induced weights improves contamination robustness via bounded-influence residual downweighting, cutting CIFAR-10 FID from 93.0 to 77.5 under 30% contamination.
Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026
– ReadersNo votes yet
9/20 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: 9 of 20 reviewers recommend it
lenient 2/5
medium 6/10
strict 1/5