Personalized Image Generation for Recommendations Beyond Catalogs

TL;DR

REBECA is a scalable, lightweight framework for personalized image generation that learns from implicit user feedback without fine-tuning diffusion models, achieving high-fidelity, user-specific images efficiently.

Contribution

The paper introduces REBECA, a novel two-stage, fine-tuning-free approach for personalized image generation from implicit feedback, scalable to large user bases.

Findings

REBECA outperforms baseline methods in personalization accuracy.

It maintains high image quality and fidelity.

The approach is computationally efficient and scalable.

Abstract

Personalization is central to human-AI interaction, yet current diffusion-based image generation systems remain largely insensitive to user diversity. Existing attempts to address this often rely on costly paired preference data or introduce latency through Large Language Models. In this work, we introduce REBECA (REcommendations BEyond CAtalogs), a lightweight and scalable framework for personalized image generation that learns directly from implicit feedback signals such as likes, ratings, and clicks. Instead of fine-tuning the underlying diffusion model, REBECA employs a two-stage process: training a conditional diffusion model to sample user- and rating-specific image embeddings, which are subsequently decoded into images using a pretrained diffusion backbone. This approach enables efficient, fine-tuning-free personalization across large user bases. We rigorously evaluate REBECA on real-world datasets, proposing a novel statistical personalization verifier and a permutation-based hypothesis test to assess preference alignment. Our results demonstrate that REBECA consistently produces high-fidelity images tailored to individual tastes, outperforming baselines while maintaining computational efficiency.