Personalized Image Generation for Recommendations Beyond Catalogs
This addresses personalization in human-AI interaction for recommendation systems, offering a scalable solution beyond catalogs, though it appears incremental as it builds on existing diffusion models with a novel framework.
The paper tackled the problem of personalizing diffusion-based image generation for users without costly paired data or latency from Large Language Models, introducing REBECA, a lightweight framework that learns from implicit feedback like likes and clicks, and demonstrated it produces high-fidelity, tailored images while outperforming baselines and maintaining efficiency.
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.