{"id":"https://openalex.org/W4415037686","doi":"https://doi.org/10.52202/085713-0530","title":"Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers","display_name":"Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4415037686","doi":"https://doi.org/10.52202/085713-0530"},"language":"en","primary_location":{"id":"doi:10.52202/085713-0530","doi":"https://doi.org/10.52202/085713-0530","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-0530","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.21497","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080597597","display_name":"Wei Pang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Wei Pang","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083481253","display_name":"Kevin Qinghong Lin","orcid":"https://orcid.org/0000-0003-2568-2346","observed_orcids":["https://orcid.org/0000-0003-2568-2346"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kevin Qinghong Lin","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050075702","display_name":"Xiangru Jian","orcid":"https://orcid.org/0009-0004-7138-7078","observed_orcids":["https://orcid.org/0009-0004-7138-7078"]},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xiangru Jian","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016879805","display_name":"Xi He","orcid":"https://orcid.org/0000-0002-6046-7855","observed_orcids":["https://orcid.org/0000-0002-6046-7855"]},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Xi He","raw_affiliation_strings":["University of Waterloo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001534492","display_name":"Philip H. S. Torr","orcid":"https://orcid.org/0009-0006-0259-5732","observed_orcids":["https://orcid.org/0009-0006-0259-5732"]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip Torr","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":176.3004,"has_fulltext":true,"cited_by_count":59,"citation_normalized_percentile":{"value":1.0,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"17652","last_page":"17708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12648","display_name":"Academic Writing and Publishing","score":0.6538000106811523,"subfield":{"id":"https://openalex.org/subfields/3309","display_name":"Library and Information Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12648","display_name":"Academic Writing and Publishing","score":0.6538000106811523,"subfield":{"id":"https://openalex.org/subfields/3309","display_name":"Library and Information Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1597999930381775,"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/T10799","display_name":"Data Visualization and Analytics","score":0.027300000190734863,"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/vision-language-models","display_name":"vision-language models","score":0.6790000200271606},{"id":"https://openalex.org/keywords/multi-agent-systems","display_name":"multi-agent systems","score":0.7179999947547913},{"id":"https://openalex.org/keywords/layout-planning","display_name":"layout planning","score":0.7160000205039978},{"id":"https://openalex.org/keywords/visual-quality-assessment","display_name":"visual quality assessment","score":0.4390000104904175},{"id":"https://openalex.org/keywords/reader-engagement","display_name":"reader engagement","score":0.49000000953674316},{"id":"https://openalex.org/keywords/gpt-4o","display_name":"GPT-4o","score":0.6980000138282776},{"id":"https://openalex.org/keywords/qwen2-5","display_name":"Qwen2.5","score":0.7680000066757202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7792999744415283},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.7174000144004822},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5878000259399414},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.4675000011920929},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.390500009059906},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3833000063896179},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3686999976634979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36059999465942383},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3305000066757202},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3294000029563904},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3208000063896179},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.31850001215934753},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.31459999084472656},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.31139999628067017},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C190812933","wikidata":"https://www.wikidata.org/wiki/Q28923","display_name":"Chart","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.2599000036716461},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2572999894618988},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.52202/085713-0530","doi":"https://doi.org/10.52202/085713-0530","is_oa":false,"landing_page_url":"https://doi.org/10.52202/085713-0530","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Neural Information Processing Systems 38","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2505.21497","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.21497","pdf_url":"https://arxiv.org/pdf/2505.21497","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.21497","doi":"https://doi.org/10.48550/arxiv.2505.21497","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.21497","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.21497","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.21497","pdf_url":"https://arxiv.org/pdf/2505.21497","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1982762021","display_name":null,"funder_award_id":"62176098","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321883","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415037686.pdf","grobid_xml":"https://content.openalex.org/works/W4415037686.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2594668508","https://openalex.org/W4307784983","https://openalex.org/W4353113046","https://openalex.org/W4385572405","https://openalex.org/W4387846478","https://openalex.org/W4387947248","https://openalex.org/W4389820615","https://openalex.org/W4403370767","https://openalex.org/W4403885061","https://openalex.org/W4404990090","https://openalex.org/W4406755521","https://openalex.org/W4407012792","https://openalex.org/W4407569519","https://openalex.org/W4409367325","https://openalex.org/W4413147863","https://openalex.org/W4413156664","https://openalex.org/W4413158050","https://openalex.org/W4415085804","https://openalex.org/W4415186412","https://openalex.org/W4415244731","https://openalex.org/W4415796940","https://openalex.org/W4416036310","https://openalex.org/W7133214447","https://openalex.org/W7166862435"],"related_works":["https://openalex.org/W6948179307","https://openalex.org/W7077913017","https://openalex.org/W7163428472","https://openalex.org/W7133334491","https://openalex.org/W4283783923","https://openalex.org/W7172433812","https://openalex.org/W7222940092","https://openalex.org/W4415993184","https://openalex.org/W4401202064","https://openalex.org/W2963838620"],"abstract_inverted_index":{"Academic":[0],"poster":[1,38,226],"generation":[2,240],"is":[3,175],"a":[4,20,70,96,107,117,217,221],"crucial":[5],"yet":[6,223],"challenging":[7],"task":[8],"in":[9],"scientific":[10],"communication,":[11],"requiring":[12],"the":[13,31,101,104,111,128,176,198,238],"compression":[14],"of":[15,241],"long-context":[16],"interleaved":[17],"documents":[18],"into":[19,106,116,220],"single,":[21],"visually":[22,157],"coherent":[23],"page.":[24],"To":[25],"address":[26],"this":[27,91],"challenge,":[28],"we":[29,93,152,170],"introduce":[30],"first":[32,160],"benchmark":[33],"and":[34,48,65,72,124,127,138,145,165,169,248],"metric":[35],"suite":[36],"for":[37,229,237],"generation,":[39],"which":[40],"pairs":[41,115],"recent":[42],"conference":[43],"papers":[44],"with":[45,55],"author-designed":[46],"posters":[47,182],"evaluates":[49],"outputs":[50],"on":[51,90,185,197],"(i)Visual":[52],"Quality-semantic":[53],"alignment":[54],"human":[56],"posters,":[57],"(ii)Textual":[58],"Coherence-language":[59],"fluency,":[60],"(iii)Holistic":[61],"Assessment-six":[62],"fine-grained":[63],"aesthetic":[64,178],"informational":[66],"criteria":[67],"scored":[68],"by":[69,84,134],"VLM-as-judge,":[71],"notably":[73],"(iv)PaperQuiz-the":[74],"poster's":[75],"ability":[76],"to":[77,142,188],"convey":[78,189],"core":[79],"paper":[80,105,219],"content":[81],"as":[82,180],"measured":[83],"VLMs":[85],"answering":[86],"generated":[87],"quizzes.":[88],"Building":[89],"benchmark,":[92],"propose":[94],"PosterAgent,":[95],"top-down,":[97],"visual-in-the-loop":[98],"multi-agent":[99,204],"pipeline:":[100],"(a)Parser":[102],"distills":[103],"structured":[108],"asset":[109],"library;":[110],"(b)Planner":[112],"aligns":[113],"text-visual":[114],"binary-tree":[118],"layout":[119],"that":[120,154,172],"preserves":[121],"reading":[122],"order":[123],"spatial":[125],"balance;":[126],"(c)Painter-Commenter":[129],"loop":[130],"refines":[131],"each":[132],"panel":[133],"executing":[135],"rendering":[136],"code":[137,247],"using":[139,211],"VLM":[140],"feedback":[141],"eliminate":[143],"overflow":[144],"ensure":[146],"alignment.":[147],"In":[148],"our":[149],"comprehensive":[150],"evaluation,":[151],"find":[153,171],"GPT-4o":[155],"outputs-though":[156],"appealing":[158],"at":[159,252],"glance-often":[161],"exhibit":[162],"noisy":[163],"text":[164],"poor":[166],"PaperQuiz":[167],"scores,":[168],"reader":[173],"engagement":[174],"primary":[177],"bottleneck,":[179],"human-designed":[181],"rely":[183],"largely":[184],"visual":[186],"semantics":[187],"meaning.":[190],"Our":[191],"fully":[192,242],"open-source":[193],"variants":[194],"(e.g.":[195],"based":[196],"Qwen-2.5":[199],"series)":[200],"outperform":[201],"existing":[202],"4o-driven":[203],"systems":[205],"across":[206],"nearly":[207],"all":[208,228],"metrics,":[209],"while":[210],"87%":[212],"fewer":[213],"tokens.":[214],"It":[215],"transforms":[216],"22-page":[218],"finalized":[222],"editable":[224],".pptx":[225],"-":[227],"just":[230],"$0.005.":[231],"These":[232],"findings":[233],"chart":[234],"clear":[235],"directions":[236],"next":[239],"automated":[243],"poster-generation":[244],"models.":[245],"The":[246],"datasets":[249],"are":[250],"available":[251],"https://github.com/Paper2Poster/Paper2Poster.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":52},{"year":2025,"cited_by_count":7}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2025-10-10T00:00:00"}