@inproceedings{channa-etal-2026-maddies,
title = "Maddies at {G}round{LM} 2026 Shared Tasks: Answer-Preserving Visual Re-grounding for Multi-View Driving {VQA}",
author = "Channa, Aditya and
Kapoor, Madhav and
Singh, Jastej",
editor = "Wang, Yimu and
Choi, Yee Man and
Wu, Di and
Ouyang, Siqi and
Azadani, Mozhgan Nasr and
Fung, Yi R. (May)",
booktitle = "Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently ({G}round{LM} 2026)",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.groundlm-1.85/",
pages = "1174--1178",
ISBN = "979-8-89176-478-1",
abstract = "GoldenViewVQA asks a multimodal model to answer a driving-scene question and identify the synchronized camera view that supports its answer. Our first system, QAVEL, used option blind routing, local image inspection, pairwise view selection, and a final verifier. Tests with GPT-5.6 Luna and Terra showed a recurring problem: extra stages often replaced correct direct predictions, and higher reasoning effort did not repair the cascade. We therefore built Joint Answer-preserving Visual Re-grounding (JAVR) around a GPT-5.6 Sol joint prediction. JAVR freezes the answer, aligns the queried actor or condition across all six views, revisits disputed cameras with target-specific crops, and changes only the view when a restricted comparator certifies an exact, direct, and complete evidence source. On the 55-item development set, JAVR produced a descriptive one item increase over its Sol anchor, from 46 to 47 jointly correct predictions, without changing any answer. Our official 59-item test submission reached 79.66{\%} joint accuracy, 81.36{\%} view accuracy, and 94.92{\%} answer accuracy"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="channa-etal-2026-maddies">
<titleInfo>
<title>Maddies at GroundLM 2026 Shared Tasks: Answer-Preserving Visual Re-grounding for Multi-View Driving VQA</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Channa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Madhav</namePart>
<namePart type="family">Kapoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jastej</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yimu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yee</namePart>
<namePart type="given">Man</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Di</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siqi</namePart>
<namePart type="family">Ouyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mozhgan</namePart>
<namePart type="given">Nasr</namePart>
<namePart type="family">Azadani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="given">R</namePart>
<namePart type="given">(May)</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-478-1</identifier>
</relatedItem>
<abstract>GoldenViewVQA asks a multimodal model to answer a driving-scene question and identify the synchronized camera view that supports its answer. Our first system, QAVEL, used option blind routing, local image inspection, pairwise view selection, and a final verifier. Tests with GPT-5.6 Luna and Terra showed a recurring problem: extra stages often replaced correct direct predictions, and higher reasoning effort did not repair the cascade. We therefore built Joint Answer-preserving Visual Re-grounding (JAVR) around a GPT-5.6 Sol joint prediction. JAVR freezes the answer, aligns the queried actor or condition across all six views, revisits disputed cameras with target-specific crops, and changes only the view when a restricted comparator certifies an exact, direct, and complete evidence source. On the 55-item development set, JAVR produced a descriptive one item increase over its Sol anchor, from 46 to 47 jointly correct predictions, without changing any answer. Our official 59-item test submission reached 79.66% joint accuracy, 81.36% view accuracy, and 94.92% answer accuracy</abstract>
<identifier type="citekey">channa-etal-2026-maddies</identifier>
<location>
<url>https://aclanthology.org/2026.groundlm-1.85/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1174</start>
<end>1178</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Maddies at GroundLM 2026 Shared Tasks: Answer-Preserving Visual Re-grounding for Multi-View Driving VQA
%A Channa, Aditya
%A Kapoor, Madhav
%A Singh, Jastej
%Y Wang, Yimu
%Y Choi, Yee Man
%Y Wu, Di
%Y Ouyang, Siqi
%Y Azadani, Mozhgan Nasr
%Y Fung, Yi R. (May)
%S Proceedings of the 1st Workshop on Grounding Language Models: Learning Faithfully and Efficiently (GroundLM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-478-1
%F channa-etal-2026-maddies
%X GoldenViewVQA asks a multimodal model to answer a driving-scene question and identify the synchronized camera view that supports its answer. Our first system, QAVEL, used option blind routing, local image inspection, pairwise view selection, and a final verifier. Tests with GPT-5.6 Luna and Terra showed a recurring problem: extra stages often replaced correct direct predictions, and higher reasoning effort did not repair the cascade. We therefore built Joint Answer-preserving Visual Re-grounding (JAVR) around a GPT-5.6 Sol joint prediction. JAVR freezes the answer, aligns the queried actor or condition across all six views, revisits disputed cameras with target-specific crops, and changes only the view when a restricted comparator certifies an exact, direct, and complete evidence source. On the 55-item development set, JAVR produced a descriptive one item increase over its Sol anchor, from 46 to 47 jointly correct predictions, without changing any answer. Our official 59-item test submission reached 79.66% joint accuracy, 81.36% view accuracy, and 94.92% answer accuracy
%U https://aclanthology.org/2026.groundlm-1.85/
%P 1174-1178
Markdown (Informal)
[Maddies at GroundLM 2026 Shared Tasks: Answer-Preserving Visual Re-grounding for Multi-View Driving VQA](https://aclanthology.org/2026.groundlm-1.85/) (Channa et al., GroundLM 2026)
ACL