{"id":"https://openalex.org/W4414899008","doi":"https://doi.org/10.1109/iccv51701.2025.01670","title":"Dual-Process Image Generation","display_name":"Dual-Process Image Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414899008","doi":"https://doi.org/10.1109/iccv51701.2025.01670"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.01955","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089731016","display_name":"Grace Luo","orcid":null},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grace Luo","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041201260","display_name":"Jonathan Granskog","orcid":"https://orcid.org/0000-0002-7068-7085"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan Granskog","raw_affiliation_strings":["Runway"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Runway","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081027763","display_name":"Aleksander Holynski","orcid":"https://orcid.org/0009-0008-6915-0126"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aleksander Holynski","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5029105520","display_name":"Trevor Darrell","orcid":"https://orcid.org/0000-0001-5453-8533"},"institutions":[{"id":"https://openalex.org/I134446601","display_name":"Berkeley College","ror":"https://ror.org/02xewxa75","country_code":"US","type":"education","lineage":["https://openalex.org/I134446601"]},{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trevor Darrell","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I134446601","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17972","last_page":"17983"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.7836999893188477,"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/T10052","display_name":"Medical Image Segmentation Techniques","score":0.7836999893188477,"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/image","display_name":"Image (mathematics)","score":0.5983999967575073},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5903000235557556},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5091999769210815},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.40059998631477356},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.39910000562667847},{"id":"https://openalex.org/keywords/line","display_name":"Line (geometry)","score":0.3910999894142151},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.32510000467300415}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7210999727249146},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6840999722480774},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6786999702453613},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5983999967575073},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5903000235557556},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5091999769210815},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C198352243","wikidata":"https://www.wikidata.org/wiki/Q37105","display_name":"Line (geometry)","level":2,"score":0.3910999894142151},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.32510000467300415},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.31299999356269836},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.3075000047683716},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3052000105381012},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2646999955177307}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01670","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01670","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.01955","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.01955","pdf_url":"https://arxiv.org/pdf/2506.01955","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2506.01955","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.01955","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.01955","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.01955","pdf_url":"https://arxiv.org/pdf/2506.01955","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414899008.pdf","grobid_xml":"https://content.openalex.org/works/W4414899008.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Prior":[0],"methods":[1],"for":[2,31,101,122],"controlling":[3],"image":[4,44,73],"generation":[5],"are":[6],"limited":[7],"in":[8],"their":[9],"ability":[10],"to":[11,46,58,67],"be":[12],"taught":[13],"new":[14,48,83],"tasks.":[15],"In":[16],"contrast,":[17],"vision-language":[18],"models,":[19],"or":[20],"VLMs,":[21],"can":[22,118],"learn":[23,47],"tasks":[24,49,85],"in-context":[25],"and":[26,63,111,132],"produce":[27],"the":[28,60,69,72,87],"correct":[29],"outputs":[30],"a":[32,37,56,79,94,136],"given":[33],"input.":[34],"We":[35,92],"propose":[36],"dual-process":[38],"distillation":[39],"scheme":[40,54],"that":[41],"allows":[42],"feed-forward":[43],"generators":[45],"from":[50],"deliberative":[51],"VLMs.":[52],"Our":[53,75],"uses":[55],"VLM":[57],"rate":[59],"generated":[61],"images":[62],"backpropagates":[64],"this":[65,99],"gradient":[66],"update":[68],"weights":[70],"of":[71,82,96,98,104,138],"generator.":[74],"general":[76],"framework":[77],"enables":[78],"wide":[80],"variety":[81],"control":[84,105],"through":[86],"same":[88],"text-and-image":[89],"based":[90],"interface.":[91],"showcase":[93],"handful":[95],"applications":[97],"technique":[100],"different":[102],"types":[103],"signals,":[106],"such":[107,124],"as":[108,125],"commonsense":[109],"inferences":[110],"visual":[112],"prompts.":[113],"With":[114],"our":[115],"method,":[116],"users":[117],"implement":[119],"multimodal":[120],"controls":[121],"properties":[123],"color":[126],"palette,":[127],"line":[128],"weight,":[129],"horizon":[130],"position,":[131],"relative":[133],"depth":[134],"within":[135],"matter":[137],"minutes.":[139],"Project":[140],"page:":[141],"https://dual-process.github.io.":[142]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}
