{"id":"https://openalex.org/W7137137800","doi":"https://doi.org/10.48550/arxiv.2603.12575","title":"AccelAes: Accelerating Diffusion Transformers for Training-Free Aesthetic-Enhanced Image Generation","display_name":"AccelAes: Accelerating Diffusion Transformers for Training-Free Aesthetic-Enhanced Image Generation","publication_year":2026,"publication_date":"2026-03-13","ids":{"openalex":"https://openalex.org/W7137137800","doi":"https://doi.org/10.48550/arxiv.2603.12575"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.12575","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.12575","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2603.12575","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125194282","display_name":"Xuanhua Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Xuanhua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082895857","display_name":"Chuanzhi Xu","orcid":"https://orcid.org/0009-0009-0613-3705"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Chuanzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129483983","display_name":"Haoxian Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Haoxian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129565664","display_name":"Boyu Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Boyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129424011","display_name":"Weidong Cai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cai, Weidong","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":0.8974999785423279,"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":0.8974999785423279,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.03269999846816063,"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":0.020099999383091927,"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/computation","display_name":"Computation","score":0.7437999844551086},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6622999906539917},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5931000113487244},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5206000208854675},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.47859999537467957},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4650999903678894},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.42809998989105225},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.40149998664855957}],"concepts":[{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7437999844551086},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6622999906539917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6258000135421753},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5931000113487244},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5206000208854675},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4796999990940094},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.47859999537467957},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4650999903678894},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.40149998664855957},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39910000562667847},{"id":"https://openalex.org/C3017489831","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Running time","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.34619998931884766},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.33559998869895935},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.32429999113082886},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C81845259","wikidata":"https://www.wikidata.org/wiki/Q290117","display_name":"Quadratic programming","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C2983327147","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Image denoising","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2736000120639801},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.25999999046325684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.12575","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.12575","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.12575","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.12575","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5454034209251404,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion":[0],"Transformers":[1],"(DiTs)":[2],"are":[3],"a":[4,78,95,126,153],"dominant":[5],"backbone":[6],"for":[7],"high-fidelity":[8],"text-to-image":[9],"generation":[10],"due":[11],"to":[12,28,44,117],"strong":[13],"scalability":[14],"and":[15,32,58,104,115,145,156],"alignment":[16],"at":[17,168],"high":[18,29],"resolutions.":[19],"However,":[20],"quadratic":[21],"self-attention":[22],"over":[23,161],"dense":[24,163],"spatial":[25],"tokens":[26,54],"leads":[27],"inference":[30],"latency":[31],"limits":[33],"deployment.":[34],"We":[35,120],"observe":[36],"that":[37,81,131],"denoising":[38],"is":[39,110,166],"spatially":[40],"non-uniform":[41],"with":[42,52,68],"respect":[43],"aesthetic":[45,53,97],"descriptors":[46],"in":[47],"the":[48,162],"prompt.":[49],"Regions":[50],"associated":[51],"receive":[55],"concentrated":[56],"cross-attention":[57,105],"show":[59,142],"larger":[60],"temporal":[61,123],"variation,":[62],"while":[63,88],"low-affinity":[64],"regions":[65],"evolve":[66],"smoothly":[67],"redundant":[69],"computation.":[70],"Based":[71],"on":[72,138],"this":[73],"insight,":[74],"we":[75],"propose":[76],"AccelAes,":[77],"training-free":[79],"framework":[80],"accelerates":[82],"DiTs":[83],"through":[84],"aesthetics-aware":[85],"spatio-temporal":[86],"reduction":[87],"improving":[89],"perceptual":[90],"aesthetics.":[91],"AccelAes":[92,151],"builds":[93],"AesMask,":[94],"one-shot":[96],"focus":[98],"mask":[99],"derived":[100],"from":[101],"prompt":[102],"semantics":[103],"signals.":[106],"When":[107],"localized":[108],"computation":[109,114],"feasible,":[111],"SkipSparse":[112],"reallocates":[113],"guidance":[116],"masked":[118],"regions.":[119],"further":[121],"reduce":[122],"redundancy":[124],"using":[125],"lightweight":[127],"step-level":[128],"prediction":[129],"cache":[130],"periodically":[132],"replaces":[133],"full":[134],"Transformer":[135],"evaluations.":[136],"Experiments":[137],"representative":[139],"DiT":[140],"families":[141],"consistent":[143],"acceleration":[144],"improved":[146],"aesthetics-oriented":[147],"quality.":[148],"On":[149],"Lumina-Next,":[150],"achieves":[152],"2.11$\\times$":[154],"speedup":[155],"improves":[157],"ImageReward":[158],"by":[159],"+11.9%":[160],"baseline.":[164],"Code":[165],"available":[167],"https://github.com/xuanhuayin/AccelAes.":[169]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-17T00:00:00"}