paper-with-me

홈 › Papers

Reinforcement Learning from Diffusion Feedback: Q* for Image Search

2023-11-27 · Aboli Marathe

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.

📄 PDF Abstract BibTeX arXiv:2311.15648

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationDiversityImage GenerationImage RetrievalQ-Learningreinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Alignment and Safety of Diffusion Models via Reinforcement Learning and Reward Modeling: A Survey

2025-05-23 · Preeti Lamba, Kiran Ravish, Ankita Kushwaha, Pawan Kumar

Diffusion models have emerged as leading generative models for images and other modalities, but aligning their outputs with human preferences and safety constraints remains a critical challenge. This thesis proposal inve…

Active LearningReinforcement Learning (RL)Safety Alignment

DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models

2023-05-25 · Ying Fan, Olivia Watkins, Yuqing Du, Hao liu 외

Learning from human feedback has been shown to improve text-to-image models. These techniques first learn a reward function that captures what humans care about in the task and then improve the models based on the learne…

reinforcement-learningReinforcement Learning (RL)

Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models

2023-09-21 · NeurIPS 2023 11

Learning from human feedback has been shown to improve text-to-image models. These techniques first learn a reward function that captures what humans care about in the task and then improve the models based on the learne…

Rich Human Feedback for Text-to-Image Generation

2023-12-15 · CVPR 2024 1 · Youwei Liang, Junfeng He, Gang Li, Peizhao Li 외

Recent Text-to-Image (T2I) generation models such as Stable Diffusion and Imagen have made significant progress in generating high-resolution images based on text descriptions. However, many generated images still suffer…

Image GenerationText to Image GenerationText-to-Image Generation

Pixel-wise RL on Diffusion Models: Reinforcement Learning from Rich Feedback

2024-04-05 · Mo Kordzanganeh, Danial Keshvary, Nariman Arian

Latent diffusion models are the state-of-the-art for synthetic image generation. To align these models with human preferences, training the models using reinforcement learning on human feedback is crucial. Black et. al 2…

DenoisingImage GenerationNavigatereinforcement-learning