面向大规模电商理解的视觉-语言模型适配 / Adapting Vision-Language Models for E-commerce Understanding at Scale
1️⃣ 一句话总结
这篇论文提出了一种有效的方法，通过针对性的适配，让通用的视觉-语言模型在保持原有广泛能力的同时，能更好地处理电商场景中多图像、属性密集且数据嘈杂的商品理解任务。
arXiv 提交日期: 2026-02-12
Abstract - Adapting Vision-Language Models for E-commerce Understanding at Scale
E-commerce product understanding demands by nature, strong multimodal comprehension from text, images, and structured attributes. General-purpose Vision-Language Models (VLMs) enable generalizable multimodal latent modelling, yet there is no documented, well-known strategy for adapting them to the attribute-centric, multi-image, and noisy nature of e-commerce data, without sacrificing general performance. In this work, we show through a large-scale experimental study, how targeted adaptation of general VLMs can substantially improve e-commerce performance while preserving broad multimodal capabilities. Furthermore, we propose a novel extensive evaluation suite covering deep product understanding, strict instruction following, and dynamic attribute extraction.
源自 arXiv: 2602.11733