@inproceedings{singhal-etal-2026-grounded,
title = "Grounded Multimodal In-Context Learning for Product Weight Estimation at Scale in {E}-commerce",
author = "Singhal, Bhavuk and
Keshari, Arsh and
Yadav, Ravindra Kumar",
editor = "Li, Yunyao and
Rehm, Georg and
Tu, Mei",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-industry.41/",
pages = "592--603",
ISBN = "979-8-89176-394-4",
abstract = "Accurately inferring implicit physical attributes of products, such as weight, is critical for large-scale e-commerce logistics but challenging due to sparse or unreliable textual metadata and high visual variability. We formulate weight estimation as a grounded multimodal reasoning problem and investigate whether large vision-language models (LVLMs) can infer discretized weight buckets through in-context learning (ICL) over product images and descriptions. We introduce a scalable inference framework that conditions predictions on automatically retrieved, category-specific exemplars and propose a distribution-calibrated retrieval strategy that aligns few-shot contexts with the empirical weight distribution of each product sub-category. This calibration substantially improves few-shot multimodal reasoning compared to random or embedding-based retrieval baselines. Across 14 high-variance categories, our approach significantly outperforms strong multimodal KNN baselines in both exact-match accuracy and near-bucket reliability. Deployed in production on a large e-commerce platform, our system processes millions of listings daily and reduces shipping-related revenue leakage by $\sim$22{\%}, demonstrating that multimodal ICL can serve as a practical and cost-effective alternative to manual or hardware-based verification."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singhal-etal-2026-grounded">
<titleInfo>
<title>Grounded Multimodal In-Context Learning for Product Weight Estimation at Scale in E-commerce</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bhavuk</namePart>
<namePart type="family">Singhal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arsh</namePart>
<namePart type="family">Keshari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ravindra</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Yadav</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-394-4</identifier>
</relatedItem>
<abstract>Accurately inferring implicit physical attributes of products, such as weight, is critical for large-scale e-commerce logistics but challenging due to sparse or unreliable textual metadata and high visual variability. We formulate weight estimation as a grounded multimodal reasoning problem and investigate whether large vision-language models (LVLMs) can infer discretized weight buckets through in-context learning (ICL) over product images and descriptions. We introduce a scalable inference framework that conditions predictions on automatically retrieved, category-specific exemplars and propose a distribution-calibrated retrieval strategy that aligns few-shot contexts with the empirical weight distribution of each product sub-category. This calibration substantially improves few-shot multimodal reasoning compared to random or embedding-based retrieval baselines. Across 14 high-variance categories, our approach significantly outperforms strong multimodal KNN baselines in both exact-match accuracy and near-bucket reliability. Deployed in production on a large e-commerce platform, our system processes millions of listings daily and reduces shipping-related revenue leakage by \sim22%, demonstrating that multimodal ICL can serve as a practical and cost-effective alternative to manual or hardware-based verification.</abstract>
<identifier type="citekey">singhal-etal-2026-grounded</identifier>
<location>
<url>https://aclanthology.org/2026.acl-industry.41/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>592</start>
<end>603</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Grounded Multimodal In-Context Learning for Product Weight Estimation at Scale in E-commerce
%A Singhal, Bhavuk
%A Keshari, Arsh
%A Yadav, Ravindra Kumar
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F singhal-etal-2026-grounded
%X Accurately inferring implicit physical attributes of products, such as weight, is critical for large-scale e-commerce logistics but challenging due to sparse or unreliable textual metadata and high visual variability. We formulate weight estimation as a grounded multimodal reasoning problem and investigate whether large vision-language models (LVLMs) can infer discretized weight buckets through in-context learning (ICL) over product images and descriptions. We introduce a scalable inference framework that conditions predictions on automatically retrieved, category-specific exemplars and propose a distribution-calibrated retrieval strategy that aligns few-shot contexts with the empirical weight distribution of each product sub-category. This calibration substantially improves few-shot multimodal reasoning compared to random or embedding-based retrieval baselines. Across 14 high-variance categories, our approach significantly outperforms strong multimodal KNN baselines in both exact-match accuracy and near-bucket reliability. Deployed in production on a large e-commerce platform, our system processes millions of listings daily and reduces shipping-related revenue leakage by \sim22%, demonstrating that multimodal ICL can serve as a practical and cost-effective alternative to manual or hardware-based verification.
%U https://aclanthology.org/2026.acl-industry.41/
%P 592-603
Markdown (Informal)
[Grounded Multimodal In-Context Learning for Product Weight Estimation at Scale in E-commerce](https://aclanthology.org/2026.acl-industry.41/) (Singhal et al., ACL 2026)
ACL