RewardFlow unifies differentiable rewards including a new VQA-based one and uses a prompt-aware adaptive policy with Langevin dynamics to achieve state-of-the-art image editing and compositional generation.
Pixart- α: Fast training of diffusion transformer for photorealistic text-to-image synthesis
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
RewardFlow: Generate Images by Optimizing What You Reward
RewardFlow unifies differentiable rewards including a new VQA-based one and uses a prompt-aware adaptive policy with Langevin dynamics to achieve state-of-the-art image editing and compositional generation.