Recent works have demonstrated that using reinforcement learning (RL) with multiple
quality rewards can improve the quality of generated images in text-to-image (T2I) …

Preference tuning is a crucial process for aligning deep generative models with human
preferences. This survey offers a thorough overview of recent advancements in preference …

Direct Preference Optimization (DPO) has emerged as a powerful approach to align text-to-
image (T2I) models with human feedback. Unfortunately, successful application of DPO to …

Advanced diffusion models like RPG, Stable Diffusion 3 and FLUX have made notable
strides in compositional text-to-image generation. However, these methods typically exhibit …

The practical use of text-to-image generation has evolved from simple, monolithic models to
complex workflows that combine multiple specialized components. While workflow-based …

Fine-tuning foundation models via reinforcement learning (RL) has proven promising for
aligning to downstream objectives. In the case of diffusion models (DMs), though RL training …

Text-to-Image (T2I) models have made significant advancements in recent years, but they
still struggle to accurately capture intricate details specified in complex compositional …

Aligning diffusion models with downstream objectives is essential for their practical
applications. However, standard alignment methods often struggle with step generalization …

Aligning text-to-image (T2I) diffusion models with preference optimization is valuable for
human-annotated datasets, but the heavy cost of manual data collection limits scalability …

Recent research has shown that fine-tuning diffusion models (DMs) with arbitrary rewards,
including non-differentiable ones, is feasible with reinforcement learning (RL) techniques …