{"id":"https://openalex.org/W7137819731","doi":"https://doi.org/10.48550/arxiv.2603.13960","title":"IMS3: Breaking Distributional Aggregation in Diffusion-Based Dataset Distillation","display_name":"IMS3: Breaking Distributional Aggregation in Diffusion-Based Dataset Distillation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137819731","doi":"https://doi.org/10.48550/arxiv.2603.13960"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.13960","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13960","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.2603.13960","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125932880","display_name":"Chenru Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Chenru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129680556","display_name":"Yunyi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yunyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129648625","display_name":"Zijun Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129660061","display_name":"Joey Tianyi Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Joey Tianyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129677875","display_name":"Chi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chi","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":0.28850001096725464,"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":0.28850001096725464,"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/T11304","display_name":"Advanced Neuroimaging Techniques and Applications","score":0.1340000033378601,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.11699999868869781,"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/discriminative-model","display_name":"Discriminative model","score":0.8169999718666077},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.6154999732971191},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.551800012588501},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5332000255584717},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4447999894618988},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4097999930381775},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.35679998993873596},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.33730000257492065}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8169999718666077},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6154999732971191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6044999957084656},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.551800012588501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5415999889373779},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5332000255584717},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5056999921798706},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4097999930381775},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.35679998993873596},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33809998631477356},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.31450000405311584},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.31450000405311584},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.31279999017715454},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3034999966621399},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.25999999046325684}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.13960","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13960","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.2603.13960","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.13960","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":[{"score":0.7845870852470398,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dataset":[0],"Distillation":[1],"aims":[2],"to":[3,21,48],"synthesize":[4],"compact":[5],"datasets":[6],"that":[7,103,125,133,142],"can":[8],"approximate":[9],"the":[10,22,41,147],"training":[11],"efficacy":[12],"of":[13,26,45,81,152],"large-scale":[14],"real":[15],"datasets,":[16,154],"offering":[17],"an":[18,99],"efficient":[19],"solution":[20],"increasing":[23],"computational":[24],"demands":[25],"modern":[27],"deep":[28],"learning.":[29],"Recently,":[30],"diffusion-based":[31,159],"dataset":[32],"distillation":[33],"methods":[34],"have":[35],"shown":[36],"great":[37],"promise":[38],"by":[39,129],"leveraging":[40],"strong":[42],"generative":[43,66],"capacity":[44],"diffusion":[46,61],"models":[47,62],"produce":[49],"diverse":[50],"and":[51,78,114,137,150],"structurally":[52],"consistent":[53],"samples.":[54],"However,":[55],"a":[56,121],"fundamental":[57],"goal":[58],"misalignment":[59],"persists:":[60],"are":[63,134],"optimized":[64],"for":[65,85],"likelihood":[67],"rather":[68],"than":[69],"discriminative":[70,148],"utility,":[71],"resulting":[72],"in":[73,75],"over-concentration":[74],"high-density":[76],"regions":[77],"inadequate":[79],"coverage":[80,113],"boundary":[82],"samples":[83],"crucial":[84],"classification.":[86],"To":[87],"address":[88],"this":[89],"issue,":[90],"we":[91],"propose":[92],"two":[93],"complementary":[94],"strategies.":[95],"Inversion-Matching":[96],"(IM)":[97],"introduces":[98],"inversion-guided":[100],"fine-tuning":[101],"process":[102],"aligns":[104],"denoising":[105],"trajectories":[106],"with":[107],"their":[108],"inversion":[109],"counterparts,":[110],"broadening":[111],"distributional":[112],"enhancing":[115],"diversity.":[116],"Selective":[117],"Subgroup":[118],"Sampling(S^3)":[119],"is":[120],"training-free":[122],"sampling":[123],"mechanism":[124],"improves":[126],"inter-class":[127],"separability":[128],"selecting":[130],"synthetic":[131],"subsets":[132],"both":[135],"representative":[136],"distinctive.":[138],"Extensive":[139],"experiments":[140],"demonstrate":[141],"our":[143],"approach":[144],"significantly":[145],"enhances":[146],"quality":[149],"generalization":[151],"distilled":[153],"achieving":[155],"state-of-the-art":[156],"performance":[157],"among":[158],"methods.":[160]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-18T00:00:00"}