{"id":"https://openalex.org/W7162523419","doi":"https://doi.org/10.48550/arxiv.2605.26470","title":"Triadic Dynamics Aware Diffusion Posterior Sampling for Inverse Problems: Optimizing Guidance and Stochasticity Schedules","display_name":"Triadic Dynamics Aware Diffusion Posterior Sampling for Inverse Problems: Optimizing Guidance and Stochasticity Schedules","publication_year":2026,"publication_date":"2026-05-26","ids":{"openalex":"https://openalex.org/W7162523419","doi":"https://doi.org/10.48550/arxiv.2605.26470"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.26470","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26470","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.26470","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037265505","display_name":"Junseo Bang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bang, Junseo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5116309154","display_name":"Dong Ju Mun","orcid":"https://orcid.org/0009-0005-7636-0920"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mun, Dong Ju","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084951243","display_name":"Hoigi Seo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seo, Hoigi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137159398","display_name":"Seongmin Hong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hong, Seongmin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137173567","display_name":"Se Young Chun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chun, Se Young","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":0.1525000035762787,"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":0.1525000035762787,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.14489999413490295,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.13019999861717224,"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/sampling","display_name":"Sampling (signal processing)","score":0.5688999891281128},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5442000031471252},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.49559998512268066},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.48350000381469727},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4814999997615814},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4542999863624573},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.44130000472068787},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4361000061035156},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4253999888896942}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6549000144004822},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5688999891281128},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5442000031471252},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.49559998512268066},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.48350000381469727},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46790000796318054},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4542999863624573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4519999921321869},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.44130000472068787},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4253999888896942},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.40549999475479126},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.3889999985694885},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.34209999442100525},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3407000005245209},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.329800009727478},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.32420000433921814},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.2799000144004822},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C157085824","wikidata":"https://www.wikidata.org/wiki/Q2384809","display_name":"TRIPS architecture","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25380000472068787},{"id":"https://openalex.org/C187523126","wikidata":"https://www.wikidata.org/wiki/Q17098330","display_name":"Inverse dynamics","level":3,"score":0.2533999979496002},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.26470","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26470","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.26470","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.26470","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":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4335877001285553}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generative":[0],"posterior":[1,129],"sampling":[2,101,130],"using":[3],"diffusion":[4],"models":[5],"has":[6,49],"emerged":[7],"as":[8,131],"a":[9,132,140],"dominant":[10],"paradigm":[11],"for":[12,83,164,176],"solving":[13,88],"inverse":[14,89],"problems":[15,90],"in":[16,77,87,91,100,187],"imaging,":[17],"which":[18,127],"usually":[19],"consists":[20],"of":[21,79,143],"three":[22,75],"main":[23],"components:":[24],"data":[25,188],"consistency":[26],"(DC)":[27],"guidance,":[28,105],"classifier-free":[29],"guidance":[30],"(CFG)":[31],"and":[32,136,146,168,190],"stochasticity.":[33],"While":[34],"prior":[35],"arts":[36],"have":[37],"focused":[38],"on":[39,116],"how":[40,52],"to":[41,51,53,57,112],"develop":[42],"each":[43],"or":[44,60],"all":[45,74],"components,":[46],"less":[47],"attention":[48],"given":[50],"schedule":[54],"them,":[55],"leading":[56],"heuristically":[58],"fixed":[59],"partially":[61],"adjusted":[62],"suboptimal":[63],"schedules.":[64],"In":[65],"this":[66,155],"work,":[67],"we":[68,119],"argue":[69],"that":[70,96],"the":[71,109],"interactions":[72],"among":[73],"components":[76],"terms":[78],"scheduling":[80],"are":[81],"crucial":[82],"significantly":[84],"improved":[85],"performance":[86],"imaging.":[92],"Our":[93],"analysis":[94],"shows":[95],"aggressive":[97],"CFG":[98,151],"early":[99],"conflict":[102],"with":[103],"DC":[104,145],"while":[106],"stochasticity":[107,147],"brings":[108],"trajectory":[110],"back":[111],"higher-probability":[113],"regions.":[114],"Based":[115],"these":[117],"findings,":[118],"propose":[120],"Triadic":[121],"Dynamics":[122],"Aware":[123],"Posterior":[124],"Sampling":[125],"(TriPS),":[126],"reformulates":[128],"time-varying":[133],"control":[134],"problem":[135],"optimizes":[137],"schedules":[138],"following":[139],"triadic":[141],"trend":[142],"decreasing":[144],"scales":[148],"alongside":[149],"increasing":[150],"scale.":[152],"TriPS":[153,183],"achieves":[154],"through":[156],"two":[157],"strategies:":[158],"template-based":[159],"search":[160],"over":[161],"functional":[162],"priors":[163],"reliable":[165],"baseline":[166],"schedules,":[167],"Group":[169],"Relative":[170],"Policy":[171],"Optimization":[172],"(GRPO)-based":[173],"reinforcement":[174],"learning":[175],"more":[177],"flexible":[178],"temporal":[179],"curves.":[180],"Experiments":[181],"demonstrate":[182],"outperforms":[184],"state-of-the-art":[185],"baselines":[186],"fidelity":[189],"perceptual":[191],"realism.":[192]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-28T00:00:00"}