{"id":"https://openalex.org/W7163194097","doi":"https://doi.org/10.48550/arxiv.2606.00837","title":"Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning","display_name":"Coarse-to-Fine Compositional Diffusion for Long-Horizon Planning","publication_year":2026,"publication_date":"2026-05-30","ids":{"openalex":"https://openalex.org/W7163194097","doi":"https://doi.org/10.48550/arxiv.2606.00837"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.00837","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00837","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.2606.00837","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076456141","display_name":"Byoungwoo Park","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Park, Byoungwoo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083595150","display_name":"Utkarsh A. Mishra","orcid":"https://orcid.org/0000-0002-4977-5187"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mishra, Utkarsh A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137709256","display_name":"Jaemoo Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Choi, Jaemoo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137636053","display_name":"Juho Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Juho","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137708250","display_name":"Yongxin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yongxin","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.21699999272823334,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.21699999272823334,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10970000177621841,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.08540000021457672,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.6947000026702881},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5888000130653381},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4878999888896942},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.476500004529953},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.47029998898506165},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.4262000024318695},{"id":"https://openalex.org/keywords/local-structure","display_name":"Local structure","score":0.4083999991416931}],"concepts":[{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.6947000026702881},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6388000249862671},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5888000130653381},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4878999888896942},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.476500004529953},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.47029998898506165},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.4262000024318695},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4235999882221222},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4198000133037567},{"id":"https://openalex.org/C2986090443","wikidata":"https://www.wikidata.org/wiki/Q77870413","display_name":"Local structure","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C137105694","wikidata":"https://www.wikidata.org/wiki/Q3407510","display_name":"Local consistency","level":4,"score":0.33239999413490295},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30469998717308044},{"id":"https://openalex.org/C2985909886","wikidata":"https://www.wikidata.org/wiki/Q193147","display_name":"Spatial coherence","level":3,"score":0.2655999958515167},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C36299963","wikidata":"https://www.wikidata.org/wiki/Q1369844","display_name":"Observability","level":2,"score":0.25920000672340393}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.00837","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00837","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.2606.00837","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00837","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":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.6966951489448547}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Diffusion":[0,116],"models":[1,20],"provide":[2],"strong":[3],"priors":[4],"for":[5],"generating":[6],"structured":[7],"data,":[8],"but":[9,98,206],"many":[10],"tasks":[11],"require":[12],"outputs":[13],"beyond":[14],"the":[15,58,62,104,147,165,176],"scale":[16],"on":[17],"which":[18],"these":[19,99],"are":[21],"typically":[22],"trained.":[23],"Compositional":[24,115],"generation":[25],"addresses":[26],"this":[27,154],"by":[28,87,94],"composing":[29],"overlapping":[30],"local":[31,50,53,90,109,127,133,168,171,199],"plans":[32,70,110],"from":[33,126],"a":[34,39,66,137,142],"pretrained":[35,167],"short-horizon":[36],"prior":[37,203],"into":[38],"long-horizon":[40,181],"output.":[41],"However,":[42],"standard":[43],"composition":[44],"primarily":[45],"enforces":[46],"agreement":[47],"between":[48],"neighboring":[49],"plans,":[51],"yielding":[52],"consistency":[54,91],"without":[55],"directly":[56],"specifying":[57],"global":[59,85,123,143,178,196],"structure":[60,124,173],"of":[61,108],"full":[63],"composition.":[64],"As":[65],"result,":[67],"locally":[68],"compatible":[69],"may":[71],"still":[72],"form":[73],"an":[74,118,157],"implausible":[75],"route,":[76],"task":[77],"sequence,":[78],"or":[79,93,106],"temporal":[80],"evolution.":[81],"Existing":[82],"methods":[83],"improve":[84],"coherence":[86,197],"repeatedly":[88],"propagating":[89],"signals":[92],"adding":[95],"inference-time":[96,119],"optimization,":[97],"procedures":[100],"become":[101],"expensive":[102],"as":[103],"number":[105],"dimensionality":[107],"increases.":[111],"We":[112],"propose":[113],"Coarse-to-Fine":[114],"(CoFi),":[117],"sampler":[120],"that":[121,145],"separates":[122],"formation":[125],"detail":[128],"refinement.":[129],"CoFi":[130,191],"first":[131],"aligns":[132],"denoised":[134],"estimates":[135],"around":[136],"shared":[138],"coarse":[139],"structure,":[140],"producing":[141],"scaffold":[144,155],"captures":[146],"long-range":[148],"task-level":[149],"arrangement.":[150],"It":[151],"then":[152],"diffuses":[153],"to":[156],"intermediate":[158],"noise":[159],"level":[160],"and":[161,187,198],"denoises":[162],"it":[163],"with":[164],"same":[166],"prior,":[169],"restoring":[170],"fine":[172],"while":[174],"preserving":[175],"scaffold-induced":[177],"coherence.":[179],"Across":[180],"robotic":[182],"planning,":[183],"panoramic":[184],"image":[185],"generation,":[186,190],"long":[188],"video":[189],"not":[192],"only":[193],"improves":[194],"both":[195],"sample":[200],"quality":[201],"over":[202],"compositional":[204],"baselines,":[205],"also":[207],"requires":[208],"2-8x":[209],"fewer":[210],"denoiser":[211],"evaluations.":[212]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-03T00:00:00"}