DiffusionNFT performs online RL for diffusion models on the forward process via flow matching and positive-negative contrasts, delivering up to 25x efficiency gains and rapid benchmark improvements over prior reverse-process methods.
Human preference score: Better aligning text-to-image models with human preference
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2025 2verdicts
UNVERDICTED 2roles
background 1polarities
unclear 1representative citing papers
CARINOX unifies noise optimization and exploration with human-correlated reward selection to boost compositional alignment in diffusion models, reporting +16% on T2I-CompBench++ and +11% on HRS while keeping quality and diversity.
citing papers explorer
-
DiffusionNFT: Online Diffusion Reinforcement with Forward Process
DiffusionNFT performs online RL for diffusion models on the forward process via flow matching and positive-negative contrasts, delivering up to 25x efficiency gains and rapid benchmark improvements over prior reverse-process methods.
-
CARINOX: Inference-time Scaling with Category-Aware Reward-based Initial Noise Optimization and Exploration
CARINOX unifies noise optimization and exploration with human-correlated reward selection to boost compositional alignment in diffusion models, reporting +16% on T2I-CompBench++ and +11% on HRS while keeping quality and diversity.