{"id":"https://openalex.org/W7168255799","doi":"https://doi.org/10.48550/arxiv.2607.10535","title":"Improving Sample Diversity in Autoregressive Text-to-Image Generation via Cluster Truncation","display_name":"Improving Sample Diversity in Autoregressive Text-to-Image Generation via Cluster Truncation","publication_year":2026,"publication_date":"2026-07-12","ids":{"openalex":"https://openalex.org/W7168255799","doi":"https://doi.org/10.48550/arxiv.2607.10535"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.10535","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.10535","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.10535","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140743742","display_name":"Trang Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nguyen, Trang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140615382","display_name":"Shuang Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Shuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140664791","display_name":"Runyan Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Runyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5140643082","display_name":"Phillip Howard","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Howard, Phillip","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8235999941825867,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8235999941825867,"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/T11019","display_name":"Image Enhancement Techniques","score":0.02449999935925007,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.018400000408291817,"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/autoregressive-model","display_name":"Autoregressive model","score":0.7508000135421753},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5656999945640564},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.46959999203681946},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.46650001406669617},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4230000078678131},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4219000041484833},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4023999869823456},{"id":"https://openalex.org/keywords/truncation","display_name":"Truncation (statistics)","score":0.3400000035762787}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7508000135421753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5899999737739563},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5656999945640564},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.46959999203681946},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.46650001406669617},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.426800012588501},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4230000078678131},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4219000041484833},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4023999869823456},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3628000020980835},{"id":"https://openalex.org/C106195933","wikidata":"https://www.wikidata.org/wiki/Q7847935","display_name":"Truncation (statistics)","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3305000066757202},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.32749998569488525},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3228999972343445},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.3190999925136566},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2782999873161316},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2542000114917755},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.10535","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.10535","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.10535","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.10535","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,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"diffusion":[1],"models":[2,32,52,189,221],"achieve":[3],"state-of-the-art":[4],"image":[5,30,39,61,120,131,200,226],"quality":[6,40,48,227],"for":[7,152],"text-to-image":[8],"(T2I)":[9],"generation,":[10,72,132],"recent":[11,45],"work":[12],"has":[13],"demonstrated":[14],"that":[15,125,164,209],"they":[16],"suffer":[17],"from":[18],"sample":[19,42,116],"diversity":[20,92,117,153,215],"collapse.":[21],"In":[22],"this":[23],"work,":[24],"we":[25,109],"investigate":[26],"whether":[27],"autoregressive":[28,187,219],"(AR)":[29],"generation":[31,75,121],"can":[33],"push":[34],"the":[35,98,106,111,145,213],"Pareto":[36],"frontier":[37],"between":[38],"and":[41,49,137,181,190,204,222,228],"diversity.":[43,205],"With":[44],"advances":[46],"in":[47,93,105,118,140],"efficiency,":[50],"AR":[51,107,119,130],"have":[53],"emerged":[54],"as":[55,69],"a":[56,81,101,160,194],"viable":[57],"alternative":[58],"to":[59,90],"diffusion-based":[60],"generation.":[62,95],"Beyond":[63],"enabling":[64],"new":[65,161],"use":[66],"cases":[67],"such":[68],"interleaved":[70],"image-text":[71],"their":[73],"sequential":[74],"process":[76],"makes":[77],"them":[78],"compatible":[79],"with":[80],"wide":[82],"range":[83],"of":[84,100,115,129,147,197],"token-based":[85],"decoding":[86,150,162,183],"strategies":[87],"originally":[88],"developed":[89],"improve":[91],"text":[94],"Motivated":[96],"by":[97],"potential":[99],"better":[102],"diversity-quality":[103],"tradeoff":[104],"paradigm,":[108],"present":[110],"first":[112],"systematic":[113],"study":[114],"models.":[122],"We":[123,155,177],"show":[124,208],"two":[126,191],"key":[127],"properties":[128],"persistently":[133],"high":[134],"token-level":[135,149],"entropy":[136],"substantial":[138],"redundancy":[139],"visual":[141],"token":[142,175],"spaces,":[143],"limit":[144],"effectiveness":[146],"existing":[148],"methods":[151,184],"enhancement.":[154],"therefore":[156],"propose":[157],"$p$-less":[158,210],"cluster,":[159],"strategy":[163],"performs":[165],"entropy-based":[166],"truncation":[167],"sampling":[168],"at":[169,174],"cluster":[170,211],"level":[171],"rather":[172],"than":[173],"level.":[176],"evaluate":[178],"our":[179],"approach":[180],"baseline":[182],"across":[185,216],"four":[186],"T2I":[188,220],"datasets":[192,223],"using":[193],"comprehensive":[195],"suite":[196],"metrics":[198],"spanning":[199],"quality,":[201],"prompt":[202,229],"alignment,":[203],"Our":[206],"results":[207],"unlocks":[212],"greatest":[214],"most":[217],"evaluated":[218],"while":[224],"maintaining":[225],"alignment.":[230]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-15T00:00:00"}