PailitaoGR: Latent Think-with-Images for Generative Image Retrieval
cs.CV, cs.AI, cs.IR
Submitted: 2026-08-27
Updated: 2026-08-27
License: http://creativecommons.org/licenses/by-nc-nd/4.0/
The gist: Generative retrieval has demonstrated strong performance by directly generating product semantic identifiers (SIDs).
Terminology
Abstract
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 Zooming without Cropping and Reading 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.
Sources
- OneSearch: A Preliminary Exploration of the Unified End-to-End Generative Framework for E-commerce Search
- OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework
- Pailitao-VL: Unified Embedding and Reranker for Real-Time Multi-Modal Industrial Search
- RAD-DPO: Robust Adaptive Denoising Direct Preference Optimization for Generative Retrieval in E-commerce
- OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment
- TRACE: Task-Adaptive Reasoning and Representation Learning for Universal Multimodal Retrieval
- Embed-RL: Reinforcement Learning for Reasoning-Driven Multimodal Embeddings
- Generative Retrieval with Preference Optimization for E-commerce Search
- Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
- DINOv3
- MOON3.0: Reasoning-aware Multimodal Representation Learning for E-commerce Product Understanding
- O1 Embedder: Let Retrievers Think Before Action
- Qwen3 Technical Report
- TSGR: Taobao Search Generative Retrieval
- Beyond Matching: Category-Guided Latent Intent Reasoning for Generative Retrieval in E-Commerce
- GME: Improving Universal Multimodal Retrieval by Multimodal LLMs
- OneVision: An End-to-End Generative Framework for Multi-view E-commerce Vision Search
- Efficient Generative Retrieval for E-commerce Search with Semantic Cluster IDs and Expert-Guided RL
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models