mlsanityData to 14 Oct 2026

FashionM3: Multimodal, Multitask, and Multiround Fashion Assistant based on Unified Vision-Language Model

arXiv 2504.17826 ↗First posted 24 Apr 2025cs.CV cs.AIcited by 2

On the map: Multimodal LLMs / vision-language models → Document understanding and multimodal RAG

Abstract (arXiv)

Fashion styling and personalized recommendations are pivotal in modern retail, contributing substantial economic value in the fashion industry. With the advent of vision-language models (VLM), new opportunities have emerged to enhance retailing through natural language and visual interactions. This work proposes FashionM3, a multimodal, multitask, and multiround fashion assistant, built upon a VLM fine-tuned for fashion-specific tasks. It helps users discover satisfying outfits by offering multiple capabilities including personalized recommendation, alternative suggestion, product image generation, and virtual try-on simulation. Fine-tuned on the novel FashionRec dataset, comprising 331,124 multimodal dialogue samples across basic, personalized, and alternative recommendation tasks, FashionM3 delivers contextually personalized suggestions with iterative refinement through multiround interactions. Quantitative and qualitative evaluations, alongside user studies, demonstrate FashionM3's superior performance in recommendation effectiveness and practical value as a fashion assistant.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Document understanding and multimodal RAG, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 27 of its 66 references that are in the map. First posted on arXiv 24 Apr 2025.

Builds on

27 of 66 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation21 Aug

Other references · 26

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  5. 2024GPT-4o System Cardcited by 4,588
  6. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 752
  7. 2015Image-based Recommendations on Styles and Substitutescited by 706
  8. 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 640
  9. 2023Textbooks Are All You Needcited by 569
  10. 2024JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generationcited by 163
  11. 2024MEDEC: A Benchmark for Medical Error Detection and Correction in Clinical Notescited by 80
  12. 2023Generative Recommendation: Towards Next-generation Recommender Paradigmcited by 70
14 more
  1. 2019POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashioncited by 64
  2. 2018Learning Type-Aware Embeddings for Fashion Compatibilitycited by 61
  3. 2024Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editingcited by 49
  4. 2019Fashion Outfit Complementary Item Retrievalcited by 42
  5. 2019Learning Similarity Conditions Without Explicit Supervisioncited by 36
  6. 2024Diffusion Models for Generative Outfit Recommendationcited by 29
  7. 2020Hierarchical Fashion Graph Network for Personalized Outfit Recommendationcited by 27
  8. 2022A Review of Modern Fashion Recommender Systemscited by 25
  9. 2018Explainable Outfit Recommendation with Joint Outfit Matching and Comment Generationcited by 16
  10. 2023Leveraging Multimodal Features and Item-level User Feedback for Bundle Constructioncited by 10
  11. 2019Toward Explainable Fashion Recommendationcited by 6
  12. 2019Fashion Outfit Generation for E-commercecited by 6
  13. 2019Theme-Matters: Fashion Compatibility Learning via Theme Attentioncited by 4
  14. 2025Integrating Domain Knowledge into Large Language Models for Enhanced Fashion Recommendationscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Discrete Tokenization for Multimodal LLMs: A Comprehensive Surveycited by 8
  2. 2026OmniFashion: Towards Generalist Fashion Intelligence via Multi-Task Vision-Language Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Decoding Style: Efficient Fine-Tuning of LLMs for Image-Guided Outfit Recommendation with Preference
  2. 2025VOGUE: A Multimodal Dataset for Conversational Recommendation in Fashion
  3. 2025Agentic Personalized Fashion Recommendation in the Age of Generative AI: Challenges, Opportunities, and Evaluation
  4. 2024What should I wear to a party in a Greek taverna? Evaluation for Conversational Agents in the Fashion Domain
  5. 2026FashionStylist: An Expert Knowledge-enhanced Multimodal Dataset for Fashion Understanding
  6. 2026Diverse-Intent Multi-Turn Fashion Image Retrieval
  7. 2024Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond
  8. 2023Fashion Matrix: Editing Photos by Just Talking