Noise optimization during sampling recovers diversity in mode-collapsed diffusion models while preserving output fidelity.
Reward-guided iterative refinement in diffusion mod- els at test-time with applications to protein and dna design,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models
Noise optimization during sampling recovers diversity in mode-collapsed diffusion models while preserving output fidelity.