# GALA: Generative Aligned Learning for Adaptive Multimodal Representation in the Taobao Shangou Recommender System

arXiv: https://arxiv.org/abs/2607.29213 · HTML: https://mlsanity.com/paper/2607.29213/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 28 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Deep Interest Evolution Network for Click-Through Rate Prediction](https://mlsanity.com/paper/1809.03672/) (2018)
- [Recommender Systems with Generative Retrieval](https://mlsanity.com/paper/2305.05065/) (2023)
- [Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation](https://mlsanity.com/paper/2311.09049/) (2023)
- [GME: Improving Universal Multimodal Retrieval by Multimodal LLMs](https://mlsanity.com/paper/2412.16855/) (2024)
- [Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese](https://mlsanity.com/paper/2211.01335/) (2022)
- [HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling](https://mlsanity.com/paper/2409.12740/) (2024)
- [NoteLLM-2: Multimodal Large Representation Models for Recommendation](https://mlsanity.com/paper/2405.16789/) (2024)
- [Enhancing Taobao Display Advertising with Multimodal Representations: Challenges, Approaches and Insights](https://mlsanity.com/paper/2407.19467/) (2024)
- [AlignRec: Aligning and Training in Multimodal Recommendations](https://mlsanity.com/paper/2403.12384/) (2024)
- [Unlocking Scaling Law in Industrial Recommendation Systems with a Three-step Paradigm based Large User Model](https://mlsanity.com/paper/2502.08309/) (2025)
- [MUST: An Effective and Scalable Framework for Multimodal Search of Target Modality](https://mlsanity.com/paper/2312.06397/) (2023)
- [Multi-Modality is All You Need for Transferable Recommender Systems](https://mlsanity.com/paper/2312.09602/) (2023)
- [MM-Rec: Multimodal News Recommendation](https://mlsanity.com/paper/2104.07407/) (2021)
- [Spatiotemporal-Enhanced Network for Click-Through Rate Prediction in Location-based Services](https://mlsanity.com/paper/2209.09427/) (2022)
- [End-to-end training of Multimodal Model and ranking Model](https://mlsanity.com/paper/2404.06078/) (2024)
- [LEMUR: Large scale End-to-end MUltimodal Recommendation](https://mlsanity.com/paper/2511.10962/) (2025)
- [CSPM: A Contrastive Spatiotemporal Preference Model for CTR Prediction in On-Demand Food Delivery Services](https://mlsanity.com/paper/2308.08446/) (2023)
- [Pre-train and Fine-tune: Recommenders as Large Models](https://mlsanity.com/paper/2501.14268/) (2025)

## Abstract (arXiv)

Modern recommender systems in food delivery increasingly leverage multimodal signals, including images, text, and user interaction histories, to enhance user experience, yet effective fusion of these heterogeneous modalities remains challenging, hindering both the joint modeling of multimodal signals and adaptation to evolving user intent. In mainstream two-stage approaches, the separation between content-semantic pretraining of image-text encoders and behavior-driven ranking models limits alignment between semantic understanding and user behavior patterns. To address these issues, we present GALA, a three-stage pipeline whose core innovation lies in an intermediate "generative RL alignment" stage that constructs multimodal pretraining data from user behavior and refines it via conversion-based rewards, effectively bridging the pretraining-fine-tuning gap to align with downstream objectives. GALA comprises three stages: first, behavior-aware triplet pretraining on query-image-text pairs from search logs to early capture user intent and content preferences; second, a novel intermediate stage that refines multimodal embeddings through reward-driven optimization (GRPO) to dynamically align them with user behavior and bridge the pretraining-fine-tuning gap; and finally, integration of multimodal and ID embeddings via adaptive gating with a hybrid loss, preserving multimodal contributions under long-term ID-dominant training. GALA has been deployed in the production environment at Taobao Shangou, serving over 200 million daily active users. Compared with state-of-the-art (SOTA) methods, it delivers consistent offline gains of +0.12/+0.20 AUC along with better PCOC metrics. Large-scale online A/B tests further report a 0.55 percent increase in order volume, confirming GALA's effectiveness at industrial scale and its robustness across diverse demand patterns.