{"id":"https://openalex.org/W4413158050","doi":"https://doi.org/10.1109/cvpr52734.2025.00276","title":"AutoPresent: Designing Structured Visuals from Scratch","display_name":"AutoPresent: Designing Structured Visuals from Scratch","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4413158050","doi":"https://doi.org/10.1109/cvpr52734.2025.00276"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52734.2025.00276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034530447","display_name":"Jiaxin Ge","orcid":"https://orcid.org/0000-0001-9152-6267"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiaxin Ge","raw_affiliation_strings":["University of California,Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041297063","display_name":"Zora Zhiruo Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zora Zhiruo Wang","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101418027","display_name":"Xuhui Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xuhui Zhou","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071254672","display_name":"Yi-Hao Peng","orcid":"https://orcid.org/0000-0002-6335-5904"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yi-Hao Peng","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020117260","display_name":"Sanjay Subramanian","orcid":"https://orcid.org/0009-0001-1399-9920"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjay Subramanian","raw_affiliation_strings":["University of California,Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115757107","display_name":"Qinyue Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qinyue Tan","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015128745","display_name":"Maarten Sap","orcid":"https://orcid.org/0000-0002-0701-4654"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maarten Sap","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009625151","display_name":"Alane Suhr","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alane Suhr","raw_affiliation_strings":["University of California,Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102739620","display_name":"Daniel Fried","orcid":"https://orcid.org/0000-0002-0454-9792"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Fried","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068811427","display_name":"Graham Neubig","orcid":"https://orcid.org/0000-0002-2072-3789"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Darrell","raw_affiliation_strings":["University of California,Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8273,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.91469536,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2902","last_page":"2911"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10888","display_name":"Augmented Reality Applications","score":0.5135999917984009,"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/T10888","display_name":"Augmented Reality Applications","score":0.5135999917984009,"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":0.5004000067710876,"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/T13518","display_name":"Architecture and Computational Design","score":0.43130001425743103,"subfield":{"id":"https://openalex.org/subfields/2216","display_name":"Architecture"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scratch","display_name":"Scratch","score":0.9231008887290955},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6923129558563232},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.4104537069797516},{"id":"https://openalex.org/keywords/engineering-drawing","display_name":"Engineering drawing","score":0.3542281985282898},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1747700572013855},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12743708491325378}],"concepts":[{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.9231008887290955},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6923129558563232},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.4104537069797516},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.3542281985282898},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1747700572013855},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12743708491325378}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52734.2025.00276","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52734.2025.00276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1987531039","https://openalex.org/W2001642682","https://openalex.org/W2150969685","https://openalex.org/W2152397572","https://openalex.org/W2540278800","https://openalex.org/W2924752388","https://openalex.org/W2970641574","https://openalex.org/W3126063179","https://openalex.org/W3153469116","https://openalex.org/W3169613483","https://openalex.org/W4213106665","https://openalex.org/W4312933868","https://openalex.org/W4385570707","https://openalex.org/W4386065691","https://openalex.org/W4390872747","https://openalex.org/W4402660091","https://openalex.org/W4402667024","https://openalex.org/W4402683861","https://openalex.org/W4402754147","https://openalex.org/W4402952465","https://openalex.org/W4403998348","https://openalex.org/W4404781099","https://openalex.org/W4409360777"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2475116013","https://openalex.org/W2770018148","https://openalex.org/W2358308169","https://openalex.org/W2385135707","https://openalex.org/W2140315382","https://openalex.org/W2059109728","https://openalex.org/W322691623"],"abstract_inverted_index":{"Designing":[0],"structured":[1,194],"visuals":[2],"such":[3],"as":[4],"presentation":[5],"slides":[6,92,115],"is":[7,163],"essential":[8],"for":[9,50,142,189],"communicative":[10],"needs,":[11],"necessitating":[12],"both":[13],"content":[14],"creation":[15],"and":[16,56,82,99,108,145,170,200],"visual":[17],"planning":[18],"skills.":[19],"In":[20],"this":[21,174],"work,":[22],"we":[23,126,171],"tackle":[24],"the":[25,44,47,87,121,150,161,177],"challenge":[26],"of":[27,90,106,123,137],"automated":[28],"slide":[29,34,51,63,143],"generation,":[30,125,144],"where":[31,160],"models":[32],"produce":[33,113],"presentations":[35],"from":[36,61],"natural":[37],"language":[38],"(NL)":[39],"instructions.":[40],"We":[41,94,154,180],"first":[42,48],"introduce":[43],"SlidesBench":[45,68],"benchmark,":[46],"benchmark":[49,95],"generation":[52,98,101],"with":[53,103,140],"7k":[54,135],"training":[55],"585":[57],"testing":[58],"examples":[59],"derived":[60],"310":[62],"decks":[64],"across":[65],"10":[66],"domains.":[67],"supports":[69],"evaluations":[70],"that":[71,110,173,182],"are":[72,203],"(i)":[73],"reference-based":[74],"to":[75,78,85,149,165],"measure":[76,86],"similarity":[77],"a":[79,104,187],"target":[80],"slide,":[81],"(ii)":[83],"reference-free":[84],"design":[88,158],"quality":[89],"generated":[91],"alone.":[93],"end-to-end":[96],"image":[97],"program":[100,124],"methods":[102,112],"variety":[105],"models,":[107],"find":[109],"programmatic":[111],"higher-quality":[114],"in":[116],"user-interactable":[117],"formats.":[118],"Built":[119],"on":[120,134,192],"success":[122],"create":[127],"AutoPresent,":[128],"an":[129],"8B":[130],"LlaMa-based":[131],"model":[132,152,162],"trained":[133],"pairs":[136],"instructions":[138],"paired":[139],"code":[141],"achieve":[146],"results":[147],"comparable":[148],"closed-source":[151],"GPT-4O.":[153],"further":[155],"explore":[156],"iterative":[157],"refinement":[159],"tasked":[164],"self-refine":[166],"its":[167],"own":[168],"output,":[169],"found":[172],"process":[175],"improves":[176],"slide\u2019s":[178],"quality.":[179],"hope":[181],"our":[183],"work":[184,191],"will":[185],"provide":[186],"basis":[188],"future":[190],"generating":[193],"visuals.":[195],"Our":[196],"code,":[197],"data,":[198],"demo,":[199],"video":[201],"demonstrations":[202],"publicly":[204],"available":[205],"at":[206],"https:":[207],"//github.com/para-lost/AutoPresent":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
