@inproceedings{han-etal-2026-mpresenter,
title = "m{P}resenter: An Agentic Framework for Generating Multilingual Presentation Videos from Scientific Papers",
author = "Han, Wenhan and
Xiao, Xiao and
Pechenizkiy, Mykola and
Fang, Meng",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.805/",
doi = "10.18653/v1/2026.findings-acl.805",
pages = "16358--16371",
ISBN = "979-8-89176-395-1",
abstract = "Generating presentation videos from scientific papers is challenging due to the need for long-document discourse planning and cross-lingual grounding. Existing Paper2Video systems are largely monolingual and often rely on single-pass pipelines, which can limit the coherence and informativeness of the resulting presentations.We present mPresenter, a multilingual agentic Paper2Video system that decomposes the task into planning, audience-oriented critique, layout-aware slide generation, and multilingual figure interpretation, enabling iterative refinement at the discourse level. To facilitate reproducible evaluation, we also introduce mPreBench, a multilingual benchmark that evaluates presentation videos via question answering as a proxy for effective information transfer. Experimental results indicate that mPresenter improves question-answering accuracy relative to prior systems, while maintaining affordable cost and latency."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-etal-2026-mpresenter">
<titleInfo>
<title>mPresenter: An Agentic Framework for Generating Multilingual Presentation Videos from Scientific Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenhan</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mykola</namePart>
<namePart type="family">Pechenizkiy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Fang</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>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</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, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Generating presentation videos from scientific papers is challenging due to the need for long-document discourse planning and cross-lingual grounding. Existing Paper2Video systems are largely monolingual and often rely on single-pass pipelines, which can limit the coherence and informativeness of the resulting presentations.We present mPresenter, a multilingual agentic Paper2Video system that decomposes the task into planning, audience-oriented critique, layout-aware slide generation, and multilingual figure interpretation, enabling iterative refinement at the discourse level. To facilitate reproducible evaluation, we also introduce mPreBench, a multilingual benchmark that evaluates presentation videos via question answering as a proxy for effective information transfer. Experimental results indicate that mPresenter improves question-answering accuracy relative to prior systems, while maintaining affordable cost and latency.</abstract>
<identifier type="citekey">han-etal-2026-mpresenter</identifier>
<identifier type="doi">10.18653/v1/2026.findings-acl.805</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.805/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>16358</start>
<end>16371</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T mPresenter: An Agentic Framework for Generating Multilingual Presentation Videos from Scientific Papers
%A Han, Wenhan
%A Xiao, Xiao
%A Pechenizkiy, Mykola
%A Fang, Meng
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F han-etal-2026-mpresenter
%X Generating presentation videos from scientific papers is challenging due to the need for long-document discourse planning and cross-lingual grounding. Existing Paper2Video systems are largely monolingual and often rely on single-pass pipelines, which can limit the coherence and informativeness of the resulting presentations.We present mPresenter, a multilingual agentic Paper2Video system that decomposes the task into planning, audience-oriented critique, layout-aware slide generation, and multilingual figure interpretation, enabling iterative refinement at the discourse level. To facilitate reproducible evaluation, we also introduce mPreBench, a multilingual benchmark that evaluates presentation videos via question answering as a proxy for effective information transfer. Experimental results indicate that mPresenter improves question-answering accuracy relative to prior systems, while maintaining affordable cost and latency.
%R 10.18653/v1/2026.findings-acl.805
%U https://aclanthology.org/2026.findings-acl.805/
%U https://doi.org/10.18653/v1/2026.findings-acl.805
%P 16358-16371
Markdown (Informal)
[mPresenter: An Agentic Framework for Generating Multilingual Presentation Videos from Scientific Papers](https://aclanthology.org/2026.findings-acl.805/) (Han et al., Findings 2026)
ACL