{"id":"https://openalex.org/W4416035154","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.165","title":"PreGenie: An Agentic Framework for High-quality Visual Presentation Generation","display_name":"PreGenie: An Agentic Framework for High-quality Visual Presentation Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035154","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.165"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.165","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.165","pdf_url":"https://aclanthology.org/2025.findings-emnlp.165.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.165.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101776462","display_name":"Xiaojie Xu","orcid":"https://orcid.org/0000-0002-6607-3339"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaojie Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101482591","display_name":"Xinli Xu","orcid":"https://orcid.org/0000-0002-6392-9437"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinli Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073327702","display_name":"Sirui Chen","orcid":"https://orcid.org/0000-0001-7740-508X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sirui Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100763973","display_name":"Haoyu Chen","orcid":"https://orcid.org/0000-0003-0676-4610"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoyu Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114778151","display_name":"Fan Zhang","orcid":"https://orcid.org/0009-0006-2374-5146"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5052475415","display_name":"Ying-Cong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ying-Cong Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3045","last_page":"3063"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.41839998960494995,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.41839998960494995,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.06549999862909317,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.05400000140070915,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/presentation","display_name":"Presentation (obstetrics)","score":0.5112000107765198},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.29269999265670776},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.2827000021934509},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.25360000133514404},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.25209999084472656}],"concepts":[{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.5112000107765198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4959999918937683},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.445499986410141},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.34850001335144043},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3100000023841858},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.28040000796318054},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.27230000495910645},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2517000138759613},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.165","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.165","pdf_url":"https://aclanthology.org/2025.findings-emnlp.165.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.165","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.165","pdf_url":"https://aclanthology.org/2025.findings-emnlp.165.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035154.pdf","grobid_xml":"https://content.openalex.org/works/W4416035154.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Visual":[0],"presentations":[1],"are":[2,82],"vital":[3],"for":[4,68],"effective":[5],"communication.Early":[6],"attempts":[7],"to":[8,33,117],"automate":[9],"their":[10,40],"creation":[11],"using":[12],"deep":[13],"learning":[14],"often":[15],"faced":[16],"issues":[17],"such":[18],"as":[19],"poorly":[20],"organized":[21],"layouts,":[22],"inaccurate":[23],"text":[24],"summarization,":[25],"and":[26,36,47,58,93,100,104,107,114,128,145],"a":[27],"lack":[28],"of":[29],"image":[30],"understanding,":[31,138],"leading":[32],"mismatched":[34],"visuals":[35],"text.These":[37],"limitations":[38],"restrict":[39],"application":[41],"in":[42,88,136,142],"formal":[43],"contexts":[44],"like":[45],"business":[46],"scientific":[48],"research.To":[49],"address":[50],"these":[51],"challenges,":[52],"we":[53],"propose":[54],"PreGenie,":[55],"an":[56],"agentic":[57],"modular":[59],"framework":[60],"powered":[61],"by":[62],"multimodal":[63,98,137],"large":[64],"language":[65],"models":[66,141],"(MLLMs)":[67],"generating":[69],"high-quality":[70,120],"visual":[71],"presentations.PreGenie":[72],"is":[73],"built":[74],"on":[75],"the":[76],"Slidev":[77],"presentation":[78],"framework,":[79],"where":[80],"slides":[81,116],"rendered":[83,115],"from":[84],"Markdown":[85],"code.It":[86],"operates":[87],"two":[89],"stages:":[90],"(1)":[91],"Analysis":[92],"Initial":[94],"Generation,":[95],"which":[96,109],"summarizes":[97],"input":[99],"generates":[101],"initial":[102],"code,":[103],"(2)":[105],"Review":[106],"Re-generation,":[108],"iteratively":[110],"reviews":[111],"intermediate":[112],"code":[113],"produce":[118],"final,":[119],"presentations.Each":[121],"stage":[122],"leverages":[123],"multiple":[124],"MLLMs":[125],"that":[126,133],"collaborate":[127],"share":[129],"information.Comprehensive":[130],"experiments":[131],"demonstrate":[132],"PreGenie":[134],"excels":[135],"outperforming":[139],"existing":[140],"both":[143],"aesthetics":[144],"content":[146],"consistency,":[147],"while":[148],"aligning":[149],"more":[150],"closely":[151],"with":[152],"human":[153],"design":[154],"preferences.":[155]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}