{"id":"https://openalex.org/W7164818926","doi":"https://doi.org/10.48550/arxiv.2606.13898","title":"HiLo-Token: Input-Adaptive High-Low Frequency Token Compression for Efficient Image Editing","display_name":"HiLo-Token: Input-Adaptive High-Low Frequency Token Compression for Efficient Image Editing","publication_year":2026,"publication_date":"2026-06-11","ids":{"openalex":"https://openalex.org/W7164818926","doi":"https://doi.org/10.48550/arxiv.2606.13898"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.13898","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.13898","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.2606.13898","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080793133","display_name":"Haoran You","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"You, Haoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044727306","display_name":"Yotam Nitzan","orcid":"https://orcid.org/0000-0001-8851-6279"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nitzan, Yotam","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138689769","display_name":"Lingzhi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Lingzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138651969","display_name":"Yifan Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gong, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138654582","display_name":"Mang-Tik Chiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chiu, Mang-Tik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083898813","display_name":"Connelly Barnes","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barnes, Connelly","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102007923","display_name":"Yan Kang","orcid":"https://orcid.org/0000-0003-2476-4921"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138655084","display_name":"Yuqian Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yuqian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024777042","display_name":"Eli Shechtman","orcid":"https://orcid.org/0000-0002-6783-1795"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shechtman, Eli","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5042253371","display_name":"Sohrab Amirghodsi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amirghodsi, Sohrab","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":0.3635999858379364,"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":0.3635999858379364,"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":0.13369999825954437,"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":0.09520000219345093,"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/security-token","display_name":"Security token","score":0.8517000079154968},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.7494000196456909},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.445499986410141},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4424999952316284},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.36329999566078186},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.35030001401901245},{"id":"https://openalex.org/keywords/image-compression","display_name":"Image compression","score":0.3400999903678894},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.3301999866962433}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8517000079154968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8159000277519226},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.7494000196456909},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.445499986410141},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4424999952316284},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.43790000677108765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4027000069618225},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.35030001401901245},{"id":"https://openalex.org/C13481523","wikidata":"https://www.wikidata.org/wiki/Q412438","display_name":"Image compression","level":4,"score":0.3400999903678894},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3301999866962433},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3125},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.31150001287460327},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.31040000915527344},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.3012999892234802},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.296999990940094},{"id":"https://openalex.org/C119657128","wikidata":"https://www.wikidata.org/wiki/Q11633","display_name":"Photography","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C87829876","wikidata":"https://www.wikidata.org/wiki/Q648877","display_name":"Post-production","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.13898","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.13898","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.2606.13898","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.13898","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Creative":[0],"image":[1,60,179,214],"editing":[2,61,127,151,215],"tools,":[3],"such":[4],"as":[5],"Photoshop's":[6],"Remove":[7],"or":[8],"Generative":[9],"Fill":[10],"buttons,":[11],"are":[12],"central":[13],"to":[14,49,93,113,121,142,167,180],"everyday":[15],"customer":[16],"use":[17],"and":[18,28,146,184,207,220,231],"account":[19],"for":[20,75,125,213],"a":[21,64,139,155,176],"major":[22],"share":[23],"of":[24,58,67,78,80,200,228],"traffic":[25],"in":[26,237],"Photoshop":[27],"Lightroom.":[29],"However,":[30],"current":[31],"generative":[32],"AI":[33],"models":[34],"face":[35],"significant":[36],"latency":[37],"challenges,":[38],"which":[39],"become":[40],"even":[41,85],"more":[42,110],"pronounced":[43],"when":[44],"transitioning":[45],"from":[46,89,175],"convolution-based":[47],"U-Nets":[48],"Diffusion":[50],"Transformers":[51],"(DiTs).":[52],"In":[53],"our":[54],"evaluation":[55,195],"on":[56,164,193,211],"hundreds":[57],"representative":[59],"samples":[62],"spanning":[63],"wide":[65],"range":[66],"mask":[68,141,222],"ratios,":[69],"the":[70,81,126,131,150,186,198,201],"DiT":[71,209],"module":[72],"alone":[73],"accounts":[74],"an":[76,103],"average":[77,226],"73%":[79],"total":[82],"model":[83],"latency,":[84],"after":[86],"being":[87],"distilled":[88],"50":[90],"timesteps":[91],"down":[92],"8":[94],"timesteps.":[95],"To":[96],"tackle":[97],"this":[98],"challenge,":[99],"we":[100,134,153],"propose":[101],"$\\textbf{HiLo-Token}$,":[102],"input-adaptive":[104],"token":[105,111,160],"compression":[106],"framework":[107],"that":[108],"allocates":[109],"budget":[112],"high-frequency,":[114],"rich-context":[115],"regions":[116],"while":[117,172],"assigning":[118],"fewer":[119],"tokens":[120,137,174],"low-frequency":[122,182],"areas.":[123],"Specifically,":[124],"region":[128],"specified":[129],"by":[130],"user":[132],"mask,":[133],"retain":[135],"all":[136],"within":[138],"dilated":[140],"preserve":[143,185],"strong":[144],"locality":[145],"contextual":[147],"relevance.":[148],"Outside":[149],"region,":[152],"introduce":[154],"simple":[156],"yet":[157],"effective":[158],"high-frequency":[159],"selection":[161],"strategy":[162],"based":[163],"spatial":[165],"frequency":[166],"capture":[168],"important":[169],"local":[170],"details,":[171],"using":[173],"16x":[177],"downsampled":[178],"represent":[181],"components":[183],"blurry":[187],"but":[188],"global":[189],"structure.":[190],"Extensive":[191],"experiments":[192],"production-level":[194],"data":[196],"validate":[197],"effectiveness":[199],"proposed":[202],"method,":[203],"achieving":[204],"3.13x,":[205],"2.59x,":[206],"1.67x":[208],"speedups":[210],"A100-80GB":[212],"tasks":[216],"across":[217],"small,":[218],"medium,":[219],"large":[221],"ratio":[223],"categories":[224],"with":[225],"ratios":[227],"6.38%,":[229],"15.92%,":[230],"35.36%,":[232],"respectively,":[233],"without":[234],"any":[235],"regression":[236],"generation":[238],"quality.":[239]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-16T00:00:00"}