# PailitaoGR: Latent Think-with-Images for Generative Image Retrieval

arXiv: https://arxiv.org/abs/2608.26658 · HTML: https://mlsanity.com/paper/2608.26658/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 34 references that are in the map.
- First posted on arXiv 27 Aug 2026.

## Builds on (most cited first, 26 of 26)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Finite Scalar Quantization: VQ-VAE Made Simple](https://mlsanity.com/paper/2309.15505/) (2023)
- [DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning](https://mlsanity.com/paper/2505.14362/) (2025)
- [Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking](https://mlsanity.com/paper/2601.04720/) (2026)
- [VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks](https://mlsanity.com/paper/2410.05160/) (2024)
- [OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment](https://mlsanity.com/paper/2502.18965/) (2025)
- [GME: Improving Universal Multimodal Retrieval by Multimodal LLMs](https://mlsanity.com/paper/2412.16855/) (2024)
- [MM-Embed: Universal Multimodal Retrieval with Multimodal LLMs](https://mlsanity.com/paper/2411.02571/) (2024)
- [MTGR: Industrial-Scale Generative Recommendation Framework in Meituan](https://mlsanity.com/paper/2505.18654/) (2025)
- [Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings](https://mlsanity.com/paper/2602.13823/) (2026)
- [IRGen: Generative Modeling for Image Retrieval](https://mlsanity.com/paper/2303.10126/) (2023)
- [O1 Embedder: Let Retrievers Think Before Action](https://mlsanity.com/paper/2502.07555/) (2025)
- [Generative Retrieval and Alignment Model: A New Paradigm for E-commerce Retrieval](https://mlsanity.com/paper/2504.01403/) (2025)
- [Generative Retrieval with Preference Optimization for E-commerce Search](https://mlsanity.com/paper/2407.19829/) (2024)
- [UniECS: Unified Multimodal E-Commerce Search Framework with Gated Cross-modal Fusion](https://mlsanity.com/paper/2508.13843/) (2025)
- [TRACE: Task-Adaptive Reasoning and Representation Learning for Universal Multimodal Retrieval](https://mlsanity.com/paper/2603.02929/) (2026)
- [MOON2.0: Dynamic Modality-balanced Multimodal Representation Learning for E-commerce Product Understanding](https://mlsanity.com/paper/2511.12449/) (2025)
- [MOON3.0: Reasoning-aware Multimodal Representation Learning for E-commerce Product Understanding](https://mlsanity.com/paper/2604.00513/) (2026)
- [Towards Context-aware Reasoning-enhanced Generative Searching in E-commerce](https://mlsanity.com/paper/2510.16925/) (2025)
- [OneVision: An End-to-End Generative Framework for Multi-view E-commerce Vision Search](https://mlsanity.com/paper/2510.05759/) (2025)
- [Pailitao-VL: Unified Embedding and Reranker for Real-Time Multi-Modal Industrial Search](https://mlsanity.com/paper/2602.13704/) (2026)
- [RAD-DPO: Robust Adaptive Denoising Direct Preference Optimization for Generative Retrieval in E-commerce](https://mlsanity.com/paper/2602.23964/) (2026)
- [Efficient Generative Retrieval for E-commerce Search with Semantic Cluster IDs and Expert-Guided RL](https://mlsanity.com/paper/2605.14434/) (2026)
- [Beyond Matching: Category-Guided Latent Intent Reasoning for Generative Retrieval in E-Commerce](https://mlsanity.com/paper/2606.07075/) (2026)
- [TSGR: Taobao Search Generative Retrieval](https://mlsanity.com/paper/2607.18796/) (2026)

## Abstract (arXiv)

Generative retrieval has demonstrated strong performance by directly generating product semantic identifiers (SIDs). Extending this paradigm to image search, however, is nontrivial because real-world query images contain diverse information, including the search target, useful auxiliary evidence, and irrelevant visual content. This requires the model to identify and focus on the search target while selectively utilizing auxiliary evidence. In this paper, we propose PailitaoGR, a Latent Think-with-Images method for generative image retrieval, which internalizes target-focused perception and selective auxiliary-evidence utilization into a the generative retrieval model, enabling textitZooming without Cropping and textitReading without OCR. Specifically, we design a target-focused perception mechanism that identifies and enhances visual tokens of the search target, consisting of a target Enhancer and a learning strategy based on on-policy distillation and attention guidance loss, enabling the model to focus on search-target regions. We also design a selective auxiliary-evidence utilization mechanism that identifies and enhances visual tokens of auxiliary evidence, including an auxiliary enhancer and an in-capacity incremental contrastive distillation strategy, enabling the model to exploit auxiliary evidence. We construct training and validation sets sampled from real-world online image-search logs. Experiments show that our method outperforms existing baselines by an average of 13.8%, validating its effectiveness.