@inproceedings{prabhakaran-etal-2025-vit,
title = "{VIT}-Pro: Visual Instruction Tuning for Product Images",
author = "Prabhakaran, Vishnu and
Aggarwal, Purav and
Kulshreshtha, Vishruit and
Das, Arunita and
Sruti, Sahini Venkata Sitaram and
Saladi, Anoop",
editor = "Chen, Weizhu and
Yang, Yi and
Kachuee, Mohammad and
Fu, Xue-Yong",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-industry.57/",
doi = "10.18653/v1/2025.naacl-industry.57",
pages = "695--707",
ISBN = "979-8-89176-194-0",
abstract = "General vision-language models (VLMs) trained on web data struggle to understand and converse about real-world e-commerce product images. We propose a cost-efficient approach for collecting training data to train a generative VLM for e-commerce product images. The key idea is to leverage large-scale, loosely-coupled image-text pairs from e-commerce stores, use a pretrained LLM to generate multimodal instruction-following data, and fine-tune a general vision-language model using LoRA. Our instruction-finetuned model, VIT-Pro, can understand and respond to queries about product images, covering diverse concepts and tasks. VIT-Pro outperforms several general-purpose VLMs on multiple vision tasks in the e-commerce domain."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="prabhakaran-etal-2025-vit">
<titleInfo>
<title>VIT-Pro: Visual Instruction Tuning for Product Images</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vishnu</namePart>
<namePart type="family">Prabhakaran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Purav</namePart>
<namePart type="family">Aggarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishruit</namePart>
<namePart type="family">Kulshreshtha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arunita</namePart>
<namePart type="family">Das</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahini</namePart>
<namePart type="given">Venkata</namePart>
<namePart type="given">Sitaram</namePart>
<namePart type="family">Sruti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Saladi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weizhu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="family">Kachuee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xue-Yong</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-194-0</identifier>
</relatedItem>
<abstract>General vision-language models (VLMs) trained on web data struggle to understand and converse about real-world e-commerce product images. We propose a cost-efficient approach for collecting training data to train a generative VLM for e-commerce product images. The key idea is to leverage large-scale, loosely-coupled image-text pairs from e-commerce stores, use a pretrained LLM to generate multimodal instruction-following data, and fine-tune a general vision-language model using LoRA. Our instruction-finetuned model, VIT-Pro, can understand and respond to queries about product images, covering diverse concepts and tasks. VIT-Pro outperforms several general-purpose VLMs on multiple vision tasks in the e-commerce domain.</abstract>
<identifier type="citekey">prabhakaran-etal-2025-vit</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-industry.57</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-industry.57/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>695</start>
<end>707</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VIT-Pro: Visual Instruction Tuning for Product Images
%A Prabhakaran, Vishnu
%A Aggarwal, Purav
%A Kulshreshtha, Vishruit
%A Das, Arunita
%A Sruti, Sahini Venkata Sitaram
%A Saladi, Anoop
%Y Chen, Weizhu
%Y Yang, Yi
%Y Kachuee, Mohammad
%Y Fu, Xue-Yong
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-194-0
%F prabhakaran-etal-2025-vit
%X General vision-language models (VLMs) trained on web data struggle to understand and converse about real-world e-commerce product images. We propose a cost-efficient approach for collecting training data to train a generative VLM for e-commerce product images. The key idea is to leverage large-scale, loosely-coupled image-text pairs from e-commerce stores, use a pretrained LLM to generate multimodal instruction-following data, and fine-tune a general vision-language model using LoRA. Our instruction-finetuned model, VIT-Pro, can understand and respond to queries about product images, covering diverse concepts and tasks. VIT-Pro outperforms several general-purpose VLMs on multiple vision tasks in the e-commerce domain.
%R 10.18653/v1/2025.naacl-industry.57
%U https://aclanthology.org/2025.naacl-industry.57/
%U https://doi.org/10.18653/v1/2025.naacl-industry.57
%P 695-707
Markdown (Informal)
[VIT-Pro: Visual Instruction Tuning for Product Images](https://aclanthology.org/2025.naacl-industry.57/) (Prabhakaran et al., NAACL 2025)
ACL
- Vishnu Prabhakaran, Purav Aggarwal, Vishruit Kulshreshtha, Arunita Das, Sahini Venkata Sitaram Sruti, and Anoop Saladi. 2025. VIT-Pro: Visual Instruction Tuning for Product Images. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track), pages 695–707, Albuquerque, New Mexico. Association for Computational Linguistics.