# TailorMind: Towards Preference-Aligned Multimodal Content Generation

arXiv: https://arxiv.org/abs/2606.23643 · HTML: https://mlsanity.com/paper/2606.23643/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Builds on (most cited first, 22 of 22)

- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Seedance 2.0: Advancing Video Generation for World Complexity](https://mlsanity.com/paper/2604.14148/) (2026)
- [Representation Learning with Large Language Models for Recommendation](https://mlsanity.com/paper/2310.15950/) (2023)
- [CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation](https://mlsanity.com/paper/2310.19488/) (2023)
- [Aligning LLM Agents by Learning Latent Preference from User Edits](https://mlsanity.com/paper/2404.15269/) (2024)
- [LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendations](https://mlsanity.com/paper/2406.12433/) (2024)
- [LLM-Powered User Simulator for Recommender System](https://mlsanity.com/paper/2412.16984/) (2024)
- [Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation](https://mlsanity.com/paper/2408.09698/) (2024)
- [IISAN: Efficiently Adapting Multimodal Representation for Sequential Recommendation with Decoupled PEFT](https://mlsanity.com/paper/2404.02059/) (2024)
- [One Model for All: Large Language Models are Domain-Agnostic Recommendation Systems](https://mlsanity.com/paper/2310.14304/) (2023)
- [Content-Rich AIGC Video Quality Assessment via Intricate Text Alignment and Motion-Aware Consistency](https://mlsanity.com/paper/2502.04076/) (2025)
- [NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results](https://mlsanity.com/paper/2505.03007/) (2025)
- [NTIRE 2025 Challenge on Short-form UGC Video Quality Assessment and Enhancement: KwaiSR Dataset and Study](https://mlsanity.com/paper/2504.15003/) (2025)
- [Aligning LLMs by Predicting Preferences from User Writing Samples](https://mlsanity.com/paper/2505.23815/) (2025)
- [RAGAR: Retrieval Augmented Personalized Image Generation Guided by Recommendation](https://mlsanity.com/paper/2505.01657/) (2025)
- [Symmetric Graph Contrastive Learning against Noisy Views for Recommendation](https://mlsanity.com/paper/2408.02691/) (2024)
- [Efficient and Effective Adaptation of Multimodal Foundation Models in Sequential Recommendation](https://mlsanity.com/paper/2411.02992/) (2024)
- [Exploring the Individuality and Collectivity of Intents behind Interactions for Graph Collaborative Filtering](https://mlsanity.com/paper/2405.09042/) (2024)
- [MoRE: A Mixture of Reflectors Framework for Large Language Model-Based Sequential Recommendation](https://mlsanity.com/paper/2409.06377/) (2024)
- [Intent Representation Learning with Large Language Model for Recommendation](https://mlsanity.com/paper/2502.03307/) (2025)
- [Qilin: A Multimodal Information Retrieval Dataset with APP-level User Sessions](https://mlsanity.com/paper/2503.00501/) (2025)

## 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.