@inproceedings{mondal-etal-2026-helping,
title = "Helping Figures Tell their Story! Paper-Grounded Video Generation Explaining Complex Scientific Figures",
author = "Mondal, Ishani and
Baghirov, Javad and
Boyd-Graber, Jordan",
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.131/",
pages = "3017--3051",
ISBN = "979-8-89176-459-0",
abstract = "Scientific figures compress complex pipelines into a single canvas, but understanding them requires paper-grounded, step-by-step narration aligned with visual highlights{---}a capability missing from current video generation systems and benchmarks. To address this, we introduce paper-grounded figure-to-video generation: generating narrated, region-grounded walkthrough videos from a figure and its paper. Second, we develop a multi-agent pipeline MINARD, which first generates paper-grounded narration and then ground the figure regions through staged extraction and clustering. Third, we release FigTalk, a benchmark derived from Paper2Video with new sequential and component-level grounding metrics that correlate strongly with human judgments. On FigTalk, MINARD produces human-like narrations grounded in paper evidence, and MINARD-Grounding substantially outperforms existing VLM grounding, animation-based, and diffusion-style video generation methods in both automatic and human evaluation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mondal-etal-2026-helping">
<titleInfo>
<title>Helping Figures Tell their Story! Paper-Grounded Video Generation Explaining Complex Scientific Figures</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ishani</namePart>
<namePart type="family">Mondal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javad</namePart>
<namePart type="family">Baghirov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</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>Scientific figures compress complex pipelines into a single canvas, but understanding them requires paper-grounded, step-by-step narration aligned with visual highlights—a capability missing from current video generation systems and benchmarks. To address this, we introduce paper-grounded figure-to-video generation: generating narrated, region-grounded walkthrough videos from a figure and its paper. Second, we develop a multi-agent pipeline MINARD, which first generates paper-grounded narration and then ground the figure regions through staged extraction and clustering. Third, we release FigTalk, a benchmark derived from Paper2Video with new sequential and component-level grounding metrics that correlate strongly with human judgments. On FigTalk, MINARD produces human-like narrations grounded in paper evidence, and MINARD-Grounding substantially outperforms existing VLM grounding, animation-based, and diffusion-style video generation methods in both automatic and human evaluation.</abstract>
<identifier type="citekey">mondal-etal-2026-helping</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.131/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>3017</start>
<end>3051</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Helping Figures Tell their Story! Paper-Grounded Video Generation Explaining Complex Scientific Figures
%A Mondal, Ishani
%A Baghirov, Javad
%A Boyd-Graber, Jordan
%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 mondal-etal-2026-helping
%X Scientific figures compress complex pipelines into a single canvas, but understanding them requires paper-grounded, step-by-step narration aligned with visual highlights—a capability missing from current video generation systems and benchmarks. To address this, we introduce paper-grounded figure-to-video generation: generating narrated, region-grounded walkthrough videos from a figure and its paper. Second, we develop a multi-agent pipeline MINARD, which first generates paper-grounded narration and then ground the figure regions through staged extraction and clustering. Third, we release FigTalk, a benchmark derived from Paper2Video with new sequential and component-level grounding metrics that correlate strongly with human judgments. On FigTalk, MINARD produces human-like narrations grounded in paper evidence, and MINARD-Grounding substantially outperforms existing VLM grounding, animation-based, and diffusion-style video generation methods in both automatic and human evaluation.
%U https://aclanthology.org/2026.emnlp-main.131/
%P 3017-3051
Markdown (Informal)
[Helping Figures Tell their Story! Paper-Grounded Video Generation Explaining Complex Scientific Figures](https://aclanthology.org/2026.emnlp-main.131/) (Mondal et al., EMNLP 2026)
ACL