English

Reinforcement Learning from Diffusion Feedback: Q* for Image Search

Computer Vision and Pattern Recognition 2023-11-28 v1 Artificial Intelligence Computation and Language Machine Learning Robotics

Abstract

Large vision-language models are steadily gaining personalization capabilities at the cost of fine-tuning or data augmentation. We present two models for image generation using model-agnostic learning that align semantic priors with generative capabilities. RLDF, or Reinforcement Learning from Diffusion Feedback, is a singular approach for visual imitation through prior-preserving reward function guidance. This employs Q-learning (with standard Q*) for generation and follows a semantic-rewarded trajectory for image search through finite encoding-tailored actions. The second proposed method, noisy diffusion gradient, is optimization driven. At the root of both methods is a special CFG encoding that we propose for continual semantic guidance. Using only a single input image and no text input, RLDF generates high-quality images over varied domains including retail, sports and agriculture showcasing class-consistency and strong visual diversity. Project website is available at https://infernolia.github.io/RLDF.

Keywords

Cite

@article{arxiv.2311.15648,
  title  = {Reinforcement Learning from Diffusion Feedback: Q* for Image Search},
  author = {Aboli Marathe},
  journal= {arXiv preprint arXiv:2311.15648},
  year   = {2023}
}
R2 v1 2026-06-28T13:32:25.360Z