{"id":"https://openalex.org/W7129241646","doi":"https://doi.org/10.48550/arxiv.2602.13357","title":"AdaCorrection: Adaptive Offset Cache Correction for Accurate Diffusion Transformers","display_name":"AdaCorrection: Adaptive Offset Cache Correction for Accurate Diffusion Transformers","publication_year":2026,"publication_date":"2026-02-13","ids":{"openalex":"https://openalex.org/W7129241646","doi":"https://doi.org/10.48550/arxiv.2602.13357"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.13357","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.13357","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.13357","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126241617","display_name":"Dong Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Liu, Dong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126219936","display_name":"Yanxuan Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Yanxuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126258901","display_name":"Ben Lengerich","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lengerich, Ben","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126173768","display_name":"Ying Nian Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Ying Nian","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5126241617"],"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":0.42410001158714294,"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":0.42410001158714294,"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":0.1906999945640564,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.06270000338554382,"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/cache","display_name":"Cache","score":0.8180999755859375},{"id":"https://openalex.org/keywords/offset","display_name":"Offset (computer science)","score":0.5784000158309937},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5189999938011169},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.48179998993873596},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.45590001344680786},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.43059998750686646}],"concepts":[{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.8180999755859375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7376000285148621},{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.5784000158309937},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.48179998993873596},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.45590001344680786},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40849998593330383},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.39800000190734863},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.3668999969959259},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.328000009059906},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.31189998984336853},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.3043000102043152},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3034999966621399},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.27549999952316284},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.258899986743927}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.13357","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.13357","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":"doi:10.48550/arxiv.2602.13357","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.13357","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":false,"raw_source_name":null,"raw_type":"article"},"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],"Transformers":[1],"(DiTs)":[2],"achieve":[3],"state-of-the-art":[4],"performance":[5],"in":[6],"high-fidelity":[7],"image":[8,127],"and":[9,47,91,95,128],"video":[10,129],"generation":[11,53,67,112,137],"but":[12],"suffer":[13],"from":[14],"expensive":[15],"inference":[16],"due":[17],"to":[18,44],"their":[19],"iterative":[20],"denoising":[21],"structure.":[22],"While":[23],"prior":[24],"methods":[25],"accelerate":[26],"sampling":[27],"by":[28],"caching":[29],"intermediate":[30],"features,":[31],"they":[32],"rely":[33],"on":[34,126],"static":[35],"reuse":[36,73],"schedules":[37],"or":[38,106],"coarse-grained":[39],"heuristics,":[40],"which":[41],"often":[42],"lead":[43],"temporal":[45],"drift":[46],"cache":[48,61,72,85],"misalignment":[49],"that":[50,64,133],"significantly":[51],"degrade":[52],"quality.":[54],"We":[55],"introduce":[56],"\\textbf{AdaCorrection},":[57],"an":[58],"adaptive":[59],"offset":[60],"correction":[62,99],"framework":[63],"maintains":[65],"high":[66],"fidelity":[68],"while":[69,121],"enabling":[70],"efficient":[71],"across":[74],"Transformer":[75],"layers":[76],"during":[77],"diffusion":[78,130],"inference.":[79],"At":[80],"each":[81],"timestep,":[82],"AdaCorrection":[83,134],"estimates":[84],"validity":[86],"with":[87,114],"lightweight":[88],"spatio-temporal":[89],"signals":[90],"adaptively":[92],"blends":[93],"cached":[94],"fresh":[96],"activations.":[97],"This":[98],"is":[100],"computed":[101],"on-the-fly":[102],"without":[103],"additional":[104],"supervision":[105],"retraining.":[107],"Our":[108],"approach":[109],"achieves":[110],"strong":[111],"quality":[113],"minimal":[115],"computational":[116],"overhead,":[117],"maintaining":[118],"near-original":[119],"FID":[120],"providing":[122],"moderate":[123],"acceleration.":[124],"Experiments":[125],"benchmarks":[131],"show":[132],"consistently":[135],"improves":[136],"performance.":[138]},"counts_by_year":[],"updated_date":"2026-02-18T06:25:47.457606","created_date":"2026-02-18T00:00:00"}