mlsanityData to 7 Oct 2026

TailorMind: Towards Preference-Aligned Multimodal Content Generation

arXiv 2606.23643 ↗First posted 22 Jun 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Personalized content systems depend on available UGC and struggle when suitable content is absent, delayed, or costly to create. Although multimodal generators can synthesize content on demand, how to translate behavioral traces into generation-ready preferences remains underexplored. We study personalized multimodal content generation: creating user-tailored multimodal content without existing item pools or waiting for matching UGC. We propose TailorMind, linking collaborative preference modeling with controllable multimodal generation. TailorMind enriches sparse user histories via hypergraph collaborative filtering and optimizes textual profiles with ranking-error feedback and textual gradient descent. Retrieval-augmented style control grounds outputs in authentic UGC patterns, while cross-modal cohesion reflection reduces semantic drift. We construct TailorBench, a benchmark from three mainstream platforms evaluated along five dimensions: coherence, novelty, aesthetic, hallucination, profiling. Experiments show that TailorMind achieves competitive or stronger coherence, improves novelty and aesthetic quality over representative generation baselines and ground-truth UGC, demonstrating advantages over retrieving available content or comparable UGC, while achieving up to 29% Recall gains in reranking. Our code is released at: https://github.com/iLearn-Lab/TailorMind.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 37 references that are in the map. First posted on arXiv 22 Jun 2026.

Builds on

22 of 37 references.

References · 22

  1. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,388
  2. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
  3. 2023Representation Learning with Large Language Models for Recommendationcited by 155
  4. 2026Seedance 2.0: Advancing Video Generation for World Complexitycited by 142
  5. 2023CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendationcited by 99
  6. 2024Aligning LLM Agents by Learning Latent Preference from User Editscited by 66
  7. 2024LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendationscited by 40
  8. 2024LLM-Powered User Simulator for Recommender Systemcited by 38
  9. 2024Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendationcited by 33
  10. 2024IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFTcited by 26
  11. 2023One Model for All: Large Language Models are Domain-Agnostic Recommendation Systemscited by 17
  12. 2025Content-Rich AIGC Video Quality Assessment via Intricate Text Alignment and Motion-Aware Consistencycited by 12
10 more
  1. 2025NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Resultscited by 12
  2. 2025NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: KwaiSR Dataset and Studycited by 11
  3. 2025Aligning LLMs by Predicting Preferences from User Writing Samplescited by 11
  4. 2025RAGAR: Retrieval Augmented Personalized Image Generation Guided by Recommendationcited by 8
  5. 2024Symmetric Graph Contrastive Learning against Noisy Views for Recommendationcited by 7
  6. 2024Efficient and Effective Adaptation of Multimodal Foundation Models in Sequential Recommendationcited by 7
  7. 2024Exploring the Individuality and Collectivity of Intents behind Interactions for Graph Collaborative Filteringcited by 4
  8. 2024MoRE: A Mixture of Reflectors Framework for Large Language Model-Based Sequential Recommendationcited by 4
  9. 2025Intent Representation Learning with Large Language Model for Recommendationcited by 4
  10. 2025Qilin: A Multimodal Information Retrieval Dataset with APP-level User Sessionscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Generate, Not Recommend: Personalized Multimodal Content Generation
  2. 2025Learning User Preferences for Image Generation Model
  3. 2025PrefGen: Multimodal Preference Learning for Preference-Conditioned Image Generation
  4. 2024Multimodal Pretraining, Adaptation, and Generation for Recommendation: A Survey
  5. 2026ICG: Improving Cover Image Generation via MLLM-based Prompting and Personalized Preference Alignment
  6. 2024PMG : Personalized Multimodal Generation with Large Language Models
  7. 2026Premier: Personalized Preference Modulation with Learnable User Embedding in Text-to-Image Generation
  8. 2025Instant Preference Alignment for Text-to-Image Diffusion Models