@inproceedings{han-etal-2026-vista,
title = "{VISTA}: Structure-Aware Training-Free Editable Diagram Generation from Natural Language",
author = "Han, Dongqi and
Lin, Bojie and
Wang, Junhan and
Luo, Jiefu",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.2403/",
pages = "54612--54627",
ISBN = "979-8-89176-459-0",
abstract = "Editable diagram generation from natural language requires structural correctness and visual readability. Text-to-image models produce rasters with no editable objects. LLM code-generation approaches yield editable output but face three challenges: unreliable geometry from token-by-token coordinate emission, shallow verification that checks code rather than the rendered image, and dependence on task-specific fine-tuning. We present VISTA, a training-free pipeline that assigns each subproblem to the appropriate component: an LLM extracts semantic structure, a deterministic algorithm computes all geometry, and a VLM inspects the rendered diagram jointly with its source and issues localized repairs. We construct a 150-prompt benchmark from PNG-only references and evaluate against eight baselines including Codex, Claude Code, and a fine-tuned multi-agent system. VISTA achieves the highest readability across all pairwise comparisons. Code and data are available at https://github.com/nice-grp/Vista."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-etal-2026-vista">
<titleInfo>
<title>VISTA: Structure-Aware Training-Free Editable Diagram Generation from Natural Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dongqi</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bojie</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junhan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiefu</namePart>
<namePart type="family">Luo</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</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Editable diagram generation from natural language requires structural correctness and visual readability. Text-to-image models produce rasters with no editable objects. LLM code-generation approaches yield editable output but face three challenges: unreliable geometry from token-by-token coordinate emission, shallow verification that checks code rather than the rendered image, and dependence on task-specific fine-tuning. We present VISTA, a training-free pipeline that assigns each subproblem to the appropriate component: an LLM extracts semantic structure, a deterministic algorithm computes all geometry, and a VLM inspects the rendered diagram jointly with its source and issues localized repairs. We construct a 150-prompt benchmark from PNG-only references and evaluate against eight baselines including Codex, Claude Code, and a fine-tuned multi-agent system. VISTA achieves the highest readability across all pairwise comparisons. Code and data are available at https://github.com/nice-grp/Vista.</abstract>
<identifier type="citekey">han-etal-2026-vista</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2403/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>54612</start>
<end>54627</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T VISTA: Structure-Aware Training-Free Editable Diagram Generation from Natural Language
%A Han, Dongqi
%A Lin, Bojie
%A Wang, Junhan
%A Luo, Jiefu
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F han-etal-2026-vista
%X Editable diagram generation from natural language requires structural correctness and visual readability. Text-to-image models produce rasters with no editable objects. LLM code-generation approaches yield editable output but face three challenges: unreliable geometry from token-by-token coordinate emission, shallow verification that checks code rather than the rendered image, and dependence on task-specific fine-tuning. We present VISTA, a training-free pipeline that assigns each subproblem to the appropriate component: an LLM extracts semantic structure, a deterministic algorithm computes all geometry, and a VLM inspects the rendered diagram jointly with its source and issues localized repairs. We construct a 150-prompt benchmark from PNG-only references and evaluate against eight baselines including Codex, Claude Code, and a fine-tuned multi-agent system. VISTA achieves the highest readability across all pairwise comparisons. Code and data are available at https://github.com/nice-grp/Vista.
%U https://aclanthology.org/2026.emnlp-main.2403/
%P 54612-54627
Markdown (Informal)
[VISTA: Structure-Aware Training-Free Editable Diagram Generation from Natural Language](https://aclanthology.org/2026.emnlp-main.2403/) (Han et al., EMNLP 2026)
ACL