{"id":"https://openalex.org/W7163351069","doi":"https://doi.org/10.48550/arxiv.2606.03243","title":"MemoGen: Can Past Experience Improve Future Text-to-Image Generation?","display_name":"MemoGen: Can Past Experience Improve Future Text-to-Image Generation?","publication_year":2026,"publication_date":"2026-06-02","ids":{"openalex":"https://openalex.org/W7163351069","doi":"https://doi.org/10.48550/arxiv.2606.03243"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.03243","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03243","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.03243","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137754309","display_name":"Wenshuo Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Wenshuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136229044","display_name":"Kuimou Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Kuimou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137771278","display_name":"Bowen Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Bowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137781357","display_name":"Jianfei Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Jianfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137713997","display_name":"Shaofeng Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Shaofeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137776395","display_name":"Haozhe Jia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jia, Haozhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137769995","display_name":"Kan Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Kan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137774732","display_name":"Haosen Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Haosen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137728816","display_name":"Kaishen Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Kaishen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137755555","display_name":"Lei Wang (6656)","orcid":"https://orcid.org/0000-0002-8600-7099"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137736405","display_name":"Jiemin Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jiemin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137801945","display_name":"Songning Lai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lai, Songning","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137726239","display_name":"Yutao Yue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue, Yutao","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":0.5699999928474426,"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":0.5699999928474426,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.20909999310970306,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.01590000092983246,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6751999855041504},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.574400007724762},{"id":"https://openalex.org/keywords/unexpected-events","display_name":"Unexpected events","score":0.37290000915527344},{"id":"https://openalex.org/keywords/ask-price","display_name":"Ask price","score":0.3508000075817108},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3325999975204468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6775000095367432},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6751999855041504},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.574400007724762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47870001196861267},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3903000056743622},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3172999918460846},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.29589998722076416},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2782000005245209},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.27630001306533813}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.03243","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03243","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.03243","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03243","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":{"Modern":[0],"text-to-image":[1,72,229],"models":[2],"have":[3],"achieved":[4],"strong":[5,200],"visual":[6,15,109,134],"synthesis,":[7],"yet":[8,43],"remain":[9],"unreliable":[10],"when":[11,116],"prompts":[12,38],"require":[13],"implicit":[14],"constraints,":[16,123],"relational":[17],"reasoning,":[18],"or":[19,36,60],"external":[20,33,112],"knowledge.":[21],"Existing":[22],"retrieval-augmented":[23],"and":[24,53,114,128,138,178,208,212],"agentic":[25,100],"generation":[26,48,80,122],"methods":[27],"mitigate":[28],"this":[29,66,185],"issue":[30],"by":[31],"acquiring":[32],"knowledge,":[34],"references,":[35],"refined":[37],"for":[39,62,227],"the":[40,84,125,148,182,195],"current":[41],"request,":[42],"they":[44],"typically":[45],"treat":[46],"each":[47,104],"as":[49,141,204,221],"an":[50,99],"isolated":[51],"episode":[52],"do":[54],"not":[55],"systematically":[56],"preserve":[57],"past":[58],"successes":[59],"failures":[61],"future":[63,156],"use.":[64],"In":[65],"work,":[67],"we":[68],"ask":[69],"whether":[70],"a":[71,90,222],"system":[73],"can":[74,219],"continually":[75],"improve":[76,154],"from":[77],"its":[78],"own":[79],"experience":[81,143,152,217],"without":[82,171],"updating":[83],"underlying":[85],"generator.":[86],"We":[87],"propose":[88],"MemoGen,":[89],"training-free":[91],"framework":[92],"that":[93,215],"augments":[94],"existing":[95],"image":[96],"generators":[97],"with":[98],"evolution":[101,146,190],"layer.":[102],"For":[103],"task,":[105],"MemoGen":[106,192],"explicitly":[107],"infers":[108],"requirements,":[110],"retrieves":[111,150],"evidence":[113],"references":[115],"necessary,":[117],"translates":[118],"them":[119],"into":[120],"executable":[121],"evaluates":[124],"generated":[126],"result,":[127],"stores":[129],"task":[130],"understanding,":[131],"reference":[132],"choices,":[133],"feedback,":[135],"successful":[136,165],"strategies,":[137],"failure":[139],"lessons":[140],"reusable":[142],"memory.":[144],"Across":[145],"rounds,":[147,191],"agent":[149],"relevant":[151],"to":[153],"similar":[155],"generations,":[157],"selectively":[158],"repairing":[159],"previously":[160],"failed":[161],"cases":[162],"while":[163],"preserving":[164],"ones,":[166],"thereby":[167],"enabling":[168],"test-time":[169],"self-evolution":[170],"parameter":[172],"updates.":[173],"Extensive":[174],"experiments":[175],"on":[176,210],"knowledge-intensive":[177],"reasoning-oriented":[179],"benchmarks":[180],"demonstrate":[181],"effectiveness":[183],"of":[184],"paradigm:":[186],"after":[187],"only":[188],"two":[189],"built":[193],"upon":[194],"open-source":[196],"Qwen-Image":[197],"backbone":[198],"surpasses":[199],"proprietary":[201],"systems":[202],"such":[203],"Nano":[205],"Banana":[206],"Pro":[207],"GPT-Image-1":[209],"WISE":[211],"Mind-Bench,":[213],"showing":[214],"explicit":[216],"memory":[218],"serve":[220],"powerful":[223],"continual":[224],"learning":[225],"signal":[226],"reliable":[228],"generation.":[230]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-04T00:00:00"}