@inproceedings{liu-etal-2026-vista,
title = "{VISTA}: A Controllable Platform for Generating and Auditing Egocentric Assistance Scenarios",
author = "Liu, Yu-Hsiang and
Tang, Yu-Chien and
Yen, An-Zi",
editor = "Agrawal, Sweta and
Abad, Alberto",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-demos.81/",
pages = "859--867",
ISBN = "979-8-89176-461-3",
abstract = "First-person assistance situations are difficult to collect with controlled timing and evidence: rare hazards should not be staged, while ordinary needs often depend on subtle visual and conversational context. We present VISTA, an interactive platform that treats scenario creation as an inspectable authoring workflow rather than a one-shot video prompt. A six-stage compiler turns a seed into typed intent, scene, event, interaction, rendering, and media artifacts; human reviewers can inspect revisions and provider requests before approving execution. We evaluate the rendered outputs, not the authoring interface. In a blinded study of 60 scenarios, 11 evaluators supplied 165 judgments. They selected the human-reviewed VISTA output as the best match to the seed in 52.1{\%} of judgments, versus 22.4{\%} for a one-pass seed-plus-assets baseline and 25.5{\%} for seed-only generation. Case-balanced seed-match scores were 3.65, 3.27, and 3.22, respectively. These results support the complete workflow under the tested renderers; they do not establish interface usability, authoring efficiency, or a novel planning algorithm. The public artifact is a credential-free prepared replay with a narrated screencast."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-vista">
<titleInfo>
<title>VISTA: A Controllable Platform for Generating and Auditing Egocentric Assistance Scenarios</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yu-Hsiang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Chien</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">An-Zi</namePart>
<namePart type="family">Yen</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 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sweta</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Abad</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">979-8-89176-461-3</identifier>
</relatedItem>
<abstract>First-person assistance situations are difficult to collect with controlled timing and evidence: rare hazards should not be staged, while ordinary needs often depend on subtle visual and conversational context. We present VISTA, an interactive platform that treats scenario creation as an inspectable authoring workflow rather than a one-shot video prompt. A six-stage compiler turns a seed into typed intent, scene, event, interaction, rendering, and media artifacts; human reviewers can inspect revisions and provider requests before approving execution. We evaluate the rendered outputs, not the authoring interface. In a blinded study of 60 scenarios, 11 evaluators supplied 165 judgments. They selected the human-reviewed VISTA output as the best match to the seed in 52.1% of judgments, versus 22.4% for a one-pass seed-plus-assets baseline and 25.5% for seed-only generation. Case-balanced seed-match scores were 3.65, 3.27, and 3.22, respectively. These results support the complete workflow under the tested renderers; they do not establish interface usability, authoring efficiency, or a novel planning algorithm. The public artifact is a credential-free prepared replay with a narrated screencast.</abstract>
<identifier type="citekey">liu-etal-2026-vista</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-demos.81/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>859</start>
<end>867</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VISTA: A Controllable Platform for Generating and Auditing Egocentric Assistance Scenarios
%A Liu, Yu-Hsiang
%A Tang, Yu-Chien
%A Yen, An-Zi
%Y Agrawal, Sweta
%Y Abad, Alberto
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-461-3
%F liu-etal-2026-vista
%X First-person assistance situations are difficult to collect with controlled timing and evidence: rare hazards should not be staged, while ordinary needs often depend on subtle visual and conversational context. We present VISTA, an interactive platform that treats scenario creation as an inspectable authoring workflow rather than a one-shot video prompt. A six-stage compiler turns a seed into typed intent, scene, event, interaction, rendering, and media artifacts; human reviewers can inspect revisions and provider requests before approving execution. We evaluate the rendered outputs, not the authoring interface. In a blinded study of 60 scenarios, 11 evaluators supplied 165 judgments. They selected the human-reviewed VISTA output as the best match to the seed in 52.1% of judgments, versus 22.4% for a one-pass seed-plus-assets baseline and 25.5% for seed-only generation. Case-balanced seed-match scores were 3.65, 3.27, and 3.22, respectively. These results support the complete workflow under the tested renderers; they do not establish interface usability, authoring efficiency, or a novel planning algorithm. The public artifact is a credential-free prepared replay with a narrated screencast.
%U https://aclanthology.org/2026.emnlp-demos.81/
%P 859-867
Markdown (Informal)
[VISTA: A Controllable Platform for Generating and Auditing Egocentric Assistance Scenarios](https://aclanthology.org/2026.emnlp-demos.81/) (Liu et al., EMNLP 2026)
ACL