Information Theoretic Text-to-Image Alignment

ICLR 2025 Conference Submission378 Authors

Keywords: Diffusion model, Text-image alignment, Mutual information

TL;DR: A novel fine-tuning method for text-to-image generative diffusion models, that uses mutual information to align generated images to user intentions through natural prompts.

Abstract:

Diffusion models for Text-to-Image (T2I) conditional generation have recently achieved
tremendous success. Yet, aligning these models with user’s intentions still involves a
laborious trial-and-error process, and this challenging alignment problem has attracted
considerable attention from the research community. In this work, instead of relying on
fine-grained linguistic analyses of prompts, human annotation, or auxiliary vision-language
models, we use Mutual Information (MI) to guide model alignment. In brief, our method
uses self-supervised fine-tuning and relies on a point-wise MI estimation between prompts
and images to create a synthetic fine-tuning set for improving model alignment. Our
analysis indicates that our method is superior to the state-of-the-art, yet it only requires
the pre-trained denoising network of the T2I model itself to estimate MI, and a simple
fine-tuning strategy that improves alignment while maintaining image quality.

Primary Area: generative models

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 378