{"id":"https://openalex.org/W4388187930","doi":"https://doi.org/10.1145/3581783.3612012","title":"LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation","display_name":"LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388187930","doi":"https://doi.org/10.1145/3581783.3612012"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612012","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612012","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612012","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612012","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010816782","display_name":"Leigang Qu","orcid":"https://orcid.org/0009-0004-6555-3834"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Leigang Qu","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0004-6555-3834","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089517967","display_name":"Shengqiong Wu","orcid":"https://orcid.org/0000-0001-6192-1194"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shengqiong Wu","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6192-1194","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055815455","display_name":"Hao Fei","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hao Fei","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0003-3026-6347","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038612499","display_name":"Liqiang Nie","orcid":"https://orcid.org/0000-0003-1476-0273"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen), Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-1476-0273","affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen), Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089404640","display_name":"Tat\u2010Seng Chua","orcid":"https://orcid.org/0000-0001-6097-7807"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Tat-Seng Chua","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6097-7807","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":87,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"643","last_page":"654"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9933000206947327,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9933000206947327,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9921000003814697,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9908000230789185,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8330894708633423},{"id":"https://openalex.org/keywords/sketch","display_name":"Sketch","score":0.684083104133606},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5776491761207581},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5667312741279602},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5663820505142212},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5436420440673828},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5091814398765564},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47274836897850037},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4443526268005371},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.42806270718574524},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.42609769105911255},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.4248586595058441},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.358987033367157},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.18421119451522827},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14416354894638062}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8330894708633423},{"id":"https://openalex.org/C2779231336","wikidata":"https://www.wikidata.org/wiki/Q7534724","display_name":"Sketch","level":2,"score":0.684083104133606},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5776491761207581},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5667312741279602},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5663820505142212},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5436420440673828},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5091814398765564},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47274836897850037},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4443526268005371},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.42806270718574524},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.42609769105911255},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4248586595058441},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.358987033367157},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.18421119451522827},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14416354894638062},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612012","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612012","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612012","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581783.3612012","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581783.3612012","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581783.3612012","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388187930.pdf","grobid_xml":"https://content.openalex.org/works/W4388187930.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W2963184176","https://openalex.org/W2963426391","https://openalex.org/W2963966654","https://openalex.org/W2964024144","https://openalex.org/W2964216930","https://openalex.org/W2965833116","https://openalex.org/W2983248633","https://openalex.org/W3098584011","https://openalex.org/W3155230099","https://openalex.org/W3156470785","https://openalex.org/W3190835409","https://openalex.org/W3202536355","https://openalex.org/W3206831165","https://openalex.org/W4200630543","https://openalex.org/W4226079479","https://openalex.org/W4312388283","https://openalex.org/W4312911498","https://openalex.org/W4312933868","https://openalex.org/W4385567149","https://openalex.org/W4385573504","https://openalex.org/W6600234944","https://openalex.org/W6600237248","https://openalex.org/W6631455383","https://openalex.org/W6639102338"],"related_works":["https://openalex.org/W4362706942","https://openalex.org/W4313443006","https://openalex.org/W2945374968","https://openalex.org/W4385452045","https://openalex.org/W4293777179","https://openalex.org/W2164070813","https://openalex.org/W2135608140","https://openalex.org/W2319626700","https://openalex.org/W3099598016","https://openalex.org/W4319589573"],"abstract_inverted_index":{"In":[0,80],"the":[1,43,120,151,154,166],"text-to-image":[2,45],"generation":[3],"field,":[4],"recent":[5,48],"remarkable":[6],"progress":[7],"in":[8,37,169],"Stable":[9],"Diffusion":[10],"makes":[11],"it":[12],"possible":[13],"to":[14,53,74,85,109,145],"generate":[15,119],"rich":[16],"kinds":[17],"of":[18,171],"novel":[19],"photorealistic":[20],"images.":[21],"However,":[22],"current":[23],"models":[24,168],"still":[25],"face":[26],"misalignment":[27],"issues":[28],"(e.g.,":[29,60],"problematic":[30],"spatial":[31],"relation":[32],"understanding":[33],"and":[34,62,113,153,173,178],"numeration":[35],"failure)":[36],"complex":[38],"natural":[39],"scenes,":[40],"which":[41],"impedes":[42],"high-faithfulness":[44,147],"generation.":[46,115,175],"Although":[47],"efforts":[49],"have":[50,73],"been":[51,68],"made":[52],"improve":[54],"controllability":[55],"by":[56],"giving":[57],"fine-grained":[58,141],"guidance":[59,77],"sketch":[61],"scribbles),":[63],"this":[64,81,102],"issue":[65],"has":[66],"not":[67],"fundamentally":[69],"tackled":[70],"since":[71],"users":[72],"provide":[75],"such":[76],"information":[78],"manually.":[79],"work,":[82],"we":[83,104,117,138],"strive":[84],"synthesize":[86,146],"high-fidelity":[87],"images":[88,148],"that":[89,161],"are":[90,180],"semantically":[91],"aligned":[92],"with":[93],"a":[94,106,125,140],"given":[95,126],"textual":[96,127],"prompt":[97,128,152],"without":[98],"any":[99],"guidance.":[100],"Toward":[101],"end,":[103],"propose":[105,139],"coarse-to-fine":[107],"paradigm":[108],"achieve":[110],"layout":[111,122,172],"planning":[112],"image":[114,174],"Concretely,":[116],"first":[118],"coarse-grained":[121],"conditioned":[123,149],"on":[124,133,150],"via":[129],"in-context":[130],"learning":[131],"based":[132],"Large":[134],"Language":[135],"Models.":[136],"Afterward,":[137],"object-interaction":[142],"diffusion":[143],"method":[144,164],"automatically":[155],"generated":[156],"layout.":[157],"Extensive":[158],"experiments":[159],"demonstrate":[160],"our":[162],"proposed":[163],"outperforms":[165],"state-of-the-art":[167],"terms":[170],"Our":[176],"code":[177],"settings":[179],"available":[181],"at":[182],"https://layoutllm-t2i.github.io/.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":38},{"year":2024,"cited_by_count":42}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}