{"id":"https://openalex.org/W4417070059","doi":"https://doi.org/10.1109/iccv51701.2025.01823","title":"Edit: Efficient Diffusion Transformers with Linear Compressed Attention","display_name":"Edit: Efficient Diffusion Transformers with Linear Compressed Attention","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417070059","doi":"https://doi.org/10.1109/iccv51701.2025.01823"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.16726","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060732954","display_name":"Philipp Becker","orcid":"https://orcid.org/0009-0004-6253-0944"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philipp Becker","raw_affiliation_strings":["Samsung, AI Center Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung, AI Center Cambridge","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103129498","display_name":"Abhinav Mehrotra","orcid":"https://orcid.org/0000-0001-6751-0302"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Abhinav Mehrotra","raw_affiliation_strings":["Samsung, AI Center Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung, AI Center Cambridge","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079337487","display_name":"Ruchika Chavhan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ruchika Chavhan","raw_affiliation_strings":["Samsung, AI Center Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung, AI Center Cambridge","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078019808","display_name":"Malcolm Chadwick","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Malcolm Chadwick","raw_affiliation_strings":["Samsung, AI Center Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung, AI Center Cambridge","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120715763","display_name":"Luca Morreale","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Luca Morreale","raw_affiliation_strings":["Samsung, AI Center Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung, AI Center Cambridge","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mehdi Noroozi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mehdi Noroozi","raw_affiliation_strings":["Samsung, AI Center Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung, AI Center Cambridge","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Alberto Gil C. P. Ramos","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alberto Gil C. P. Ramos","raw_affiliation_strings":["Samsung, AI Center Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung, AI Center Cambridge","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087701164","display_name":"Sourav Bhattacharya","orcid":"https://orcid.org/0000-0001-9670-5264"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sourav Bhattacharya","raw_affiliation_strings":["Samsung, AI Center Cambridge"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung, AI Center Cambridge","institution_ids":["https://openalex.org/I4210117523"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34623701,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19608","last_page":"19616"},"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":0.257099986076355,"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":0.257099986076355,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.10159999877214432,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.07900000363588333,"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/quadratic-equation","display_name":"Quadratic equation","score":0.6172999739646912},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5866000056266785},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5525000095367432},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4300000071525574},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.29269999265670776},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.2732999920845032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7087000012397766},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.6172999739646912},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5866000056266785},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5525000095367432},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43639999628067017},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4300000071525574},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.37959998846054077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3538999855518341},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.30149999260902405},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C170122806","wikidata":"https://www.wikidata.org/wiki/Q1914828","display_name":"Linear scale","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2554999887943268}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.16726","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16726","pdf_url":"https://arxiv.org/pdf/2503.16726","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.2503.16726","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.16726","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:2503.16726","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.16726","pdf_url":"https://arxiv.org/pdf/2503.16726","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion":[0,124,146],"Transformers":[1],"(DiTs)":[2],"have":[3],"emerged":[4],"as":[5],"a":[6,62,70,90],"leading":[7],"architecture":[8],"for":[9,94,101,109],"text-to-image":[10],"synthesis,":[11],"producing":[12],"high-quality":[13],"and":[14,55,82,104,134,144],"photorealistic":[15],"images.":[16],"However,":[17],"the":[18,23,129,132],"quadratic":[19],"scaling":[20],"properties":[21],"of":[22,131],"attention":[24,66,92,100,108],"in":[25,52],"DiTs":[26,54,57],"hinder":[27],"image":[28,156],"generation":[29],"with":[30,36,77,154],"higher":[31],"resolution":[32],"or":[33],"on":[34],"devices":[35],"limited":[37],"resources.":[38],"This":[39],"work":[40],"introduces":[41],"an":[42,119],"efficient":[43],"diffusion":[44],"transformer":[45],"(EDiT)":[46],"to":[47,74,118,151],"alleviate":[48],"these":[49,114],"efficiency":[50],"bottlenecks":[51],"conventional":[53],"Multimodal":[56,122],"(MM-DiTs).":[58],"First,":[59],"we":[60,88],"present":[61],"novel":[63],"linear":[64,99],"compressed":[65],"method":[67],"that":[68,97],"uses":[69],"multi-layer":[71],"convolutional":[72],"network":[73],"modulate":[75],"queries":[76],"local":[78],"information":[79],"while":[80],"keys":[81],"values":[83],"are":[84],"aggregated":[85],"spatially.":[86],"Second,":[87],"formulate":[89],"hybrid":[91],"scheme":[93],"multimodal":[95],"inputs":[96],"combines":[98],"image-to-image":[102],"interactions":[103,110],"standard":[105],"scaled":[106],"dot-product":[107],"involving":[111],"prompts.":[112],"Merging":[113],"two":[115],"approaches":[116],"leads":[117],"expressive,":[120],"linear-time":[121],"Efficient":[123],"Transformer":[125],"(MM-EDiT).":[126],"We":[127],"demonstrate":[128],"effectiveness":[130],"EDiT":[133],"MM-EDiT":[135],"architectures":[136],"by":[137],"integrating":[138],"them":[139],"into":[140],"PixArt-Sigma":[141],"(conventional":[142],"DiT)":[143],"Stable":[145],"3.5-Medium":[147],"(MM-DiT),":[148],"achieving":[149],"up":[150],"2.2x":[152],"speedup":[153],"comparable":[155],"quality":[157],"after":[158],"distillation.":[159]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}