# TATTOO: Training-free AesTheTic-aware Outfit recOmmendation

arXiv: https://arxiv.org/abs/2509.23242 · HTML: https://mlsanity.com/paper/2509.23242/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 27 Sep 2025.

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)](https://mlsanity.com/paper/2203.13366/) (2022)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [Large Language Models are Zero-Shot Rankers for Recommender Systems](https://mlsanity.com/paper/2305.08845/) (2023)
- [M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems](https://mlsanity.com/paper/2205.08084/) (2022)
- [Vision-by-Language for Training-Free Compositional Image Retrieval](https://mlsanity.com/paper/2310.09291/) (2023)
- [Learning Fashion Compatibility with Bidirectional LSTMs](https://mlsanity.com/paper/1707.05691/) (2017)
- [Learning Type-Aware Embeddings for Fashion Compatibility](https://mlsanity.com/paper/1803.09196/) (2018)
- [Fashion Outfit Complementary Item Retrieval](https://mlsanity.com/paper/1912.08967/) (2019)
- [Contrastive language and vision learning of general fashion concepts](https://mlsanity.com/paper/2204.03972/) (2022)
- [Learning Similarity Conditions Without Explicit Supervision](https://mlsanity.com/paper/1908.08589/) (2019)
- [Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation](https://mlsanity.com/paper/2408.09698/) (2024)
- [Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval](https://mlsanity.com/paper/2412.11077/) (2024)
- [Diffusion Models for Generative Outfit Recommendation](https://mlsanity.com/paper/2402.17279/) (2024)
- [Hierarchical Fashion Graph Network for Personalized Outfit Recommendation](https://mlsanity.com/paper/2005.12566/) (2020)
- [OutfitTransformer: Learning Outfit Representations for Fashion Recommendation](https://mlsanity.com/paper/2204.04812/) (2022)
- [UniFashion: A Unified Vision-Language Model for Multimodal Fashion Retrieval and Generation](https://mlsanity.com/paper/2408.11305/) (2024)
- [Explainable Outfit Recommendation with Joint Outfit Matching and Comment Generation](https://mlsanity.com/paper/1806.08977/) (2018)
- [Knowledge Prompt-tuning for Sequential Recommendation](https://mlsanity.com/paper/2308.08459/) (2023)
- [Sequential LLM Framework for Fashion Recommendation](https://mlsanity.com/paper/2410.11327/) (2024)
- [Deciphering Compatibility Relationships with Textual Descriptions via Extraction and Explanation](https://mlsanity.com/paper/2312.11554/) (2023)

## Built on by (most cited first, 2 of 2)

- [Transferable Physical-World Adversarial Patches Against Pedestrian Detection Models](https://mlsanity.com/paper/2604.22552/) (2026)
- [Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Driving](https://mlsanity.com/paper/2604.23105/) (2026)

## Abstract (arXiv)

The global fashion e-commerce market relies significantly on intelligent and aesthetic-aware outfit-completion tools to promote sales. While previous studies have approached the problem of fashion outfit-completion and compatible-item retrieval, most of them require expensive, task-specific training on large-scale labeled data, and no effort is made to guide outfit recommendation with explicit human aesthetics. In the era of Multimodal Large Language Models (MLLMs), we show that the conventional training-based pipeline could be streamlined to a training-free paradigm, with better recommendation scores and enhanced aesthetic awareness. We achieve this with TATTOO, a Training-free AesTheTic-aware Outfit recommendation approach. It first generates a target-item description using MLLMs, followed by an aesthetic chain-of-thought used to distill the images into a structured aesthetic profile including color, style, occasion, season, material, and balance. By fusing the visual summary of the outfit with the textual description and aesthetics vectors using a dynamic entropy-gated mechanism, candidate items can be represented in a shared embedding space and be ranked accordingly. Experiments on a real-world evaluation set Aesthetic-100 show that TATTOO achieves state-of-the-art performance compared with existing training-based methods. Another standard Polyvore dataset is also used to measure the advanced zero-shot retrieval capability of our training-free method.