{"id":"https://openalex.org/W4417183093","doi":"https://doi.org/10.48550/arxiv.2507.01652","title":"Autoregressive Image Generation with Linear Complexity: A Spatial-Aware Decay Perspective","display_name":"Autoregressive Image Generation with Linear Complexity: A Spatial-Aware Decay Perspective","publication_year":2025,"publication_date":"2025-07-02","ids":{"openalex":"https://openalex.org/W4417183093","doi":"https://doi.org/10.48550/arxiv.2507.01652"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2507.01652","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.01652","pdf_url":"https://arxiv.org/pdf/2507.01652","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.01652","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102015118","display_name":"Yuxin Mao","orcid":"https://orcid.org/0000-0002-2837-2290"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Mao, Yuxin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053193181","display_name":"Zhentao Qin","orcid":"https://orcid.org/0009-0009-7458-978X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Zhen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047303316","display_name":"Jinxing Zhou","orcid":"https://orcid.org/0000-0001-6402-7593"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Jinxing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111614248","display_name":"Hui Deng","orcid":"https://orcid.org/0000-0002-8002-236X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deng, Hui","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063135412","display_name":"Xuyang Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Xuyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101863814","display_name":"Bin Fan","orcid":"https://orcid.org/0000-0001-9191-8455"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Bin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100345515","display_name":"Jing Zhang","orcid":"https://orcid.org/0009-0002-4129-7237"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066621365","display_name":"Yiran Zhong","orcid":"https://orcid.org/0000-0003-1404-3610"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Yiran","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036202579","display_name":"Yuchao Dai","orcid":"https://orcid.org/0000-0002-4432-7406"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Yuchao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5102015118"],"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":0.7494000196456909,"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":0.7494000196456909,"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":0.05550000071525574,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.03139999881386757,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8409000039100647},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5192999839782715},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.5060999989509583},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4729999899864197},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.4697999954223633},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4537000060081482},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.41130000352859497},{"id":"https://openalex.org/keywords/image-quality","display_name":"Image quality","score":0.3905999958515167}],"concepts":[{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.8409000039100647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5479999780654907},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5192999839782715},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5030999779701233},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4729999899864197},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.4697999954223633},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4690999984741211},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4537000060081482},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.41130000352859497},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.3905999958515167},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.38179999589920044},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3808000087738037},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35190001130104065},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3449999988079071},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.31520000100135803},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.31310001015663147},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3127000033855438},{"id":"https://openalex.org/C194657046","wikidata":"https://www.wikidata.org/wiki/Q7394685","display_name":"STAR model","level":4,"score":0.31189998984336853},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.30820000171661377},{"id":"https://openalex.org/C141379421","wikidata":"https://www.wikidata.org/wiki/Q6094427","display_name":"Iterative reconstruction","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C106430172","wikidata":"https://www.wikidata.org/wiki/Q6002272","display_name":"Image restoration","level":4,"score":0.29649999737739563},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2621000111103058}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2507.01652","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.01652","pdf_url":"https://arxiv.org/pdf/2507.01652","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.01652","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.01652","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.01652","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.01652","pdf_url":"https://arxiv.org/pdf/2507.01652","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Autoregressive":[0],"(AR)":[1],"models":[2,27],"have":[3,61],"garnered":[4],"significant":[5],"attention":[6,59,102,146],"in":[7,66,89],"image":[8,77,114,141,161],"generation":[9,78,162],"for":[10,178],"their":[11,82],"ability":[12],"to":[13,50,84,147],"effectively":[14],"capture":[15,85],"both":[16],"local":[17],"and":[18,45,164,174],"global":[19],"structures":[20],"within":[21,111],"visual":[22,90],"data.":[23,91],"However,":[24],"prevalent":[25],"AR":[26],"predominantly":[28],"rely":[29],"on":[30,122,133,155],"the":[31,51,112,168],"transformer":[32],"architectures,":[33],"which":[34],"are":[35],"beset":[36],"by":[37,116],"quadratic":[38],"computational":[39,165],"complexity":[40],"concerning":[41],"input":[42],"sequence":[43,130],"length":[44],"substantial":[46],"memory":[47],"overhead":[48],"due":[49],"necessity":[52],"of":[53,81],"maintaining":[54],"key-value":[55],"caches.":[56],"Although":[57],"linear":[58,152,171],"mechanisms":[60],"successfully":[62],"reduced":[63],"this":[64,134],"burden":[65],"language":[67],"models,":[68],"our":[69],"initial":[70],"experiments":[71],"reveal":[72],"that":[73,104,143],"they":[74],"significantly":[75],"degrade":[76],"quality":[79],"because":[80],"inability":[83],"critical":[86],"long-range":[87],"dependencies":[88],"We":[92],"propose":[93],"Linear":[94],"Attention":[95],"with":[96,151],"Spatial-Aware":[97],"Decay":[98],"(LASAD),":[99],"a":[100],"novel":[101],"mechanism":[103],"explicitly":[105],"preserves":[106],"genuine":[107],"2D":[108,124],"spatial":[109,125,149,175],"relationships":[110],"flattened":[113],"sequences":[115],"computing":[117],"position-dependent":[118],"decay":[119],"factors":[120],"based":[121],"true":[123],"location":[126],"rather":[127],"than":[128],"1D":[129],"positions.":[131],"Based":[132],"mechanism,":[135],"we":[136],"present":[137],"LASADGen,":[138],"an":[139],"autoregressive":[140],"generator":[142],"enables":[144],"selective":[145],"relevant":[148],"contexts":[150],"complexity.":[153],"Experiments":[154],"ImageNet":[156],"show":[157],"LASADGen":[158],"achieves":[159],"state-of-the-art":[160],"performance":[163],"efficiency,":[166],"bridging":[167],"gap":[169],"between":[170],"attention's":[172],"efficiency":[173],"understanding":[176],"needed":[177],"high-quality":[179],"generation.":[180]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}