{"id":"https://openalex.org/W7224119413","doi":"https://doi.org/10.5281/zenodo.23720760","title":"Lookahead Semantic Commitment Intervention Optimization for Diffusion Models: Predicting the Downstream Effects of Semantic Disambiguation","display_name":"Lookahead Semantic Commitment Intervention Optimization for Diffusion Models: Predicting the Downstream Effects of Semantic Disambiguation","publication_year":2026,"publication_date":"2026-10-28","ids":{"openalex":"https://openalex.org/W7224119413","doi":"https://doi.org/10.5281/zenodo.23720760"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23720760","doi":"https://doi.org/10.5281/zenodo.23720760","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23720760","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23720760","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100638045","display_name":"Jincheng Zhang","orcid":"https://orcid.org/0000-0001-7332-6704","observed_orcids":["https://orcid.org/0000-0001-7332-6704","https://orcid.org/0009-0005-1860-0009"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Jincheng","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0005-1860-0009","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5100638045"],"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":1.0,"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":1.0,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0,"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":0.0,"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/diffusion-models","display_name":"diffusion models","score":0.871999979019165},{"id":"https://openalex.org/keywords/semantic-disambiguation","display_name":"semantic disambiguation","score":0.7870000004768372},{"id":"https://openalex.org/keywords/decision-making-under-uncertainty","display_name":"decision making under uncertainty","score":0.7519999742507935},{"id":"https://openalex.org/keywords/model-predictive-control","display_name":"model predictive control","score":0.9369999766349792},{"id":"https://openalex.org/keywords/compositional-image-generation","display_name":"compositional image generation","score":0.6589999794960022}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7046999931335449},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6550999879837036},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.626800000667572},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.5655999779701233},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.46219998598098755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46129998564720154},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.448199987411499},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41190001368522644},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33809998631477356},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.30660000443458557},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2978000044822693},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.28619998693466187},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C2780665704","wikidata":"https://www.wikidata.org/wiki/Q959298","display_name":"Intervention (counseling)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2630000114440918},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.262800008058548}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23720760","doi":"https://doi.org/10.5281/zenodo.23720760","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23720760","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"},{"id":"doi:10.5281/zenodo.23720761","doi":"https://doi.org/10.5281/zenodo.23720761","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23720761","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23720760","doi":"https://doi.org/10.5281/zenodo.23720760","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23720760","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7224090458","https://openalex.org/W7224130750","https://openalex.org/W7224137454","https://openalex.org/W7224130202","https://openalex.org/W7224122826","https://openalex.org/W7224107942","https://openalex.org/W7224095425","https://openalex.org/W7224128603","https://openalex.org/W7158424734","https://openalex.org/W7224091087"],"abstract_inverted_index":{"Diffusion":[0],"models":[1],"generate":[2],"images":[3],"through":[4,250],"iterative":[5],"denoising":[6],"processes":[7],"conditioned":[8],"on":[9,102,110],"text":[10],"prompts,":[11,193],"visual":[12],"observations,":[13],"or":[14,77,114,126],"other":[15],"forms":[16],"of":[17,75,219,223,244],"guidance.":[18],"During":[19],"generation,":[20,63,165,259],"an":[21],"ambiguous":[22,192],"prompt":[23,254],"may":[24,60,68],"support":[25],"multiple":[26],"plausible":[27],"semantic":[28,53,66,129,132,194,224,234],"interpretations,":[29],"including":[30],"alternative":[31,120,157],"object":[32],"identities,":[33],"colors,":[34],"shapes,":[35],"spatial":[36],"relationships,":[37],"and":[38,44,173,183,200,236,242,260],"scene":[39],"configurations.":[40],"Existing":[41],"conditioning":[42],"mechanisms":[43],"guidance":[45,112],"schedules":[46,113],"influence":[47],"how":[48],"strongly":[49],"a":[50,89,141,148],"model":[51],"follows":[52],"information,":[54],"but":[55],"prematurely":[56],"reinforcing":[57],"one":[58],"interpretation":[59,143],"restrict":[61],"subsequent":[62],"while":[64,147],"delaying":[65],"commitment":[67,133,158,225],"preserve":[69],"useful":[70],"alternatives":[71],"at":[72],"the":[73,136,152,220,228],"expense":[74],"ambiguity":[76],"computational":[78,201],"efficiency.":[79],"This":[80],"paper":[81],"proposes":[82],"Lookahead":[83],"Semantic":[84],"Commitment":[85],"Intervention":[86],"Optimization":[87],"(LSCIO),":[88],"conceptual":[90],"framework":[91,161],"for":[92],"selecting":[93],"semantic-conditioning":[94],"interventions":[95],"according":[96],"to":[97,139],"their":[98],"predicted":[99],"downstream":[100,168,221],"effects":[101],"final":[103,153],"generation":[104],"quality.":[105],"Rather":[106],"than":[107],"relying":[108],"exclusively":[109],"fixed":[111,233],"instantaneous":[115,237],"confidence":[116],"estimates,":[117],"LSCIO":[118],"evaluates":[119],"actions":[121],"that":[122,216],"strengthen,":[123],"weaken,":[124],"preserve,":[125],"temporarily":[127],"defer":[128],"constraints.":[130],"A":[131,176],"state":[134],"represents":[135],"current":[137],"degree":[138],"which":[140],"particular":[142],"has":[144],"been":[145],"favored,":[146],"lookahead":[149],"evaluator":[150],"estimates":[151],"utility":[154,169],"associated":[155],"with":[156,232,252],"decisions.":[159],"The":[160,188,211,240],"combines":[162],"candidate":[163],"intervention":[164],"semantic-state":[166],"representation,":[167],"prediction,":[170],"uncertainty-aware":[171],"decision-making,":[172],"receding-horizon":[174],"control.":[175,239],"mathematical":[177],"formulation,":[178],"training":[179],"objectives,":[180],"inference":[181],"algorithm,":[182],"experimental":[184,204],"protocol":[185],"are":[186,206],"presented.":[187],"proposed":[189],"evaluation":[190],"emphasizes":[191],"diversity,":[195],"compositional":[196,258],"correctness,":[197],"final-image":[198],"quality,":[199],"cost.":[202],"No":[203],"results":[205],"claimed":[207],"in":[208],"this":[209,245],"paper.":[210],"principal":[212],"research":[213],"hypothesis":[214],"is":[215],"explicit":[217],"prediction":[218],"consequences":[222],"can":[226],"improve":[227],"quality\u2013diversity\u2013efficiency":[229],"trade-off":[230],"compared":[231],"strengthening":[235],"confidence-based":[238],"novelty":[241],"effectiveness":[243],"formulation":[246],"must":[247],"be":[248],"established":[249],"comparisons":[251],"existing":[253],"scheduling,":[255],"adaptive":[256],"guidance,":[257],"test-time":[261],"search":[262],"methods.":[263]},"counts_by_year":[],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2026-10-29T00:00:00"}