PaperSatisDive论文
Traversing the Satisfaction-Diversity Frontier in Text-to-Image Diffusion
An academic paper published on arXiv that proposes the SatisDive method to address the balance between satisfaction and diversity in text-to-image diffusion models. The generation task is reformulated as a satisficing optimization problem.
Timeline (last 90 days)
Oct 5
SatisDive is a text-to-image generation method proposed in the arXiv paper "Traversing the Satisfaction-Diversity Frontier in Text-to-Image Diffusion," which reformulates the generation process as a satisficing problem rather than a pure optimization problem.
Unverified50%