paper-with-me

Papers

DashCLIP: Leveraging multimodal models for generating semantic embeddings for DoorDash

2025-03-18 · Omkar Gurjar, Kin Sum Liu, Praveen Kolli, Utsaw Kumar, Mandar Rahurkar

Despite the success of vision-language models in various generative tasks, obtaining high-quality semantic representations for products and user intents is still challenging due to the inability of off-the-shelf models to capture nuanced relationships between the entities. In this paper, we introduce a joint training framework for product and user queries by aligning uni-modal and multi-modal encoders through contrastive learning on image-text data. Our novel approach trains a query encoder with an LLM-curated relevance dataset, eliminating the reliance on engagement history. These embeddings demonstrate strong generalization capabilities and improve performance across applications, including product categorization and relevance prediction. For personalized ads recommendation, a significant uplift in the click-through rate and conversion rate after the deployment further confirms the impact on key business metrics. We believe that the flexibility of our framework makes it a promising solution toward enriching the user experience across the e-commerce landscape.

📄 PDF Abstract BibTeX arXiv:2504.07110

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningProduct Categorization

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

Similar Papers 제목 키워드 기반

ReMatch: Boosting Representation through Matching for Multimodal Retrieval

2025-11-24 · Qianying Liu, Xiao Liang, Zhiqiang Zhang, Zhongfei Qing 외 arxiv

We present ReMatch, a framework that leverages the generative strength of MLLMs for multimodal retrieval. Previous approaches treated an MLLM as a simple encoder, ignoring its generative nature, and under-utilising its c…

Zero-shot Generalization

Recall: Empowering Multimodal Embedding for Edge Devices

2024-09-09 · Dongqi Cai, Shangguang Wang, Chen Peng, Zeling Zhang 외

Human memory is inherently prone to forgetting. To address this, multimodal embedding models have been introduced, which transform diverse real-world data into a unified embedding space. These embeddings can be retrieved…

Retrieval

Multimodal Representation Learning Conditioned on Semantic Relations

2025-08-24 · Yang Qiao, Yuntong Hu, Bowen Zhu, Hasibul Haque 외 arxiv

Multimodal representation learning has been largely driven by contrastive models such as CLIP, which learn a shared embedding space by aligning paired image-text samples. While effective for general-purpose representatio…

Representation Learning

Leveraging Contextual Embeddings for Detecting Diachronic Semantic Shift

2019-12-02 · LREC 2020 5 · Matej Martinc, Petra Kralj Novak, Senja Pollak

We propose a new method that leverages contextual embeddings for the task of diachronic semantic shift detection by generating time specific word representations from BERT embeddings. The results of our experiments in th…

Domain AdaptationSemantic Shift Detection

Exploiting LMM-based knowledge for image classification tasks

2024-06-05 · Maria Tzelepi, Vasileios Mezaris

In this paper we address image classification tasks leveraging knowledge encoded in Large Multimodal Models (LMMs). More specifically, we use the MiniGPT-4 model to extract semantic descriptions for the images, in a mult…

Classificationimage-classificationImage Classification