MSDDA derives a closed-form optimal reverse denoising distribution for multi-objective diffusion alignment that is exactly equivalent to step-level RL fine-tuning with no approximation error.
Diffusion blend: Inference-time multi-preference alignment for diffusion models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
PG-MAP formulates inference-time alignment as joint MAP optimization over conditioning c and latent z_t via forward-consistency coupling for diffusion and flow-matching models, reporting gains in PickScore and HPS metrics.
citing papers explorer
-
Step-level Denoising-time Diffusion Alignment with Multiple Objectives
MSDDA derives a closed-form optimal reverse denoising distribution for multi-objective diffusion alignment that is exactly equivalent to step-level RL fine-tuning with no approximation error.
-
PG-MAP: Joint MAP Optimization for Inference-Time Alignment of Diffusion and Flow-Matching Models
PG-MAP formulates inference-time alignment as joint MAP optimization over conditioning c and latent z_t via forward-consistency coupling for diffusion and flow-matching models, reporting gains in PickScore and HPS metrics.