{"id":"https://openalex.org/W4386555488","doi":"https://doi.org/10.48550/arxiv.2309.03895","title":"InstructDiffusion: A Generalist Modeling Interface for Vision Tasks","display_name":"InstructDiffusion: A Generalist Modeling Interface for Vision Tasks","publication_year":2023,"publication_date":"2023-09-07","ids":{"openalex":"https://openalex.org/W4386555488","doi":"https://doi.org/10.48550/arxiv.2309.03895"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2309.03895","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.03895","pdf_url":"https://arxiv.org/pdf/2309.03895","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.03895","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079916339","display_name":"Zigang Geng","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Geng, Zigang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013134358","display_name":"Binxin Yang","orcid":"https://orcid.org/0000-0003-4110-1986"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Binxin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049097915","display_name":"Tiankai Hang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hang, Tiankai","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369797","display_name":"Chen Li","orcid":"https://orcid.org/0000-0002-0260-2182"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034954588","display_name":"Shuyang Gu","orcid":"https://orcid.org/0000-0003-4535-2280"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Shuyang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100458354","display_name":"Ting Zhang","orcid":"https://orcid.org/0009-0008-8621-3598"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ting","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101369681","display_name":"Jianmin Bao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bao, Jianmin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081039383","display_name":"Zheng Zhang","orcid":"https://orcid.org/0000-0002-7040-2326"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091049278","display_name":"Hu Han","orcid":"https://orcid.org/0000-0001-6010-1792"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Han","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013116360","display_name":"Dong Chen","orcid":"https://orcid.org/0000-0001-8118-3889"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Dong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101666011","display_name":"Baining Guo","orcid":"https://orcid.org/0000-0001-8349-8868"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Baining","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5079916339"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"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":0.9966999888420105,"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":0.9966999888420105,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.994700014591217,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9941999912261963,"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/computer-science","display_name":"Computer science","score":0.7935420274734497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6458141207695007},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6383081078529358},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.6324734687805176},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6209781169891357},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5246375203132629},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.5207319259643555},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5129079818725586},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5087843537330627},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.50034499168396},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4666326940059662},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.4511869549751282},{"id":"https://openalex.org/keywords/machine-vision","display_name":"Machine vision","score":0.4151727557182312}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7935420274734497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6458141207695007},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6383081078529358},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.6324734687805176},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6209781169891357},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5246375203132629},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5207319259643555},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5129079818725586},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5087843537330627},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.50034499168396},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4666326940059662},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4511869549751282},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.4151727557182312},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2309.03895","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.03895","pdf_url":"https://arxiv.org/pdf/2309.03895","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"doi:10.48550/arxiv.2309.03895","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.03895","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.03895","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.03895","pdf_url":"https://arxiv.org/pdf/2309.03895","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386555488.pdf","grobid_xml":"https://content.openalex.org/works/W4386555488.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2032233321","https://openalex.org/W3121970507","https://openalex.org/W2110028391","https://openalex.org/W54497855","https://openalex.org/W217960748","https://openalex.org/W3125814499","https://openalex.org/W2090827041","https://openalex.org/W2094012830","https://openalex.org/W187246281","https://openalex.org/W2079194830"],"abstract_inverted_index":{"We":[0],"present":[1],"InstructDiffusion,":[2],"a":[3,42,50,86,96,136,140],"unifying":[4],"and":[5,23,30,52,65,107,110,116,127],"generic":[6],"framework":[7],"for":[8,32,144],"aligning":[9],"computer":[10,155],"vision":[11,34,39,99,145],"tasks":[12,40,103,112,126],"with":[13],"human":[14],"instructions.":[15],"Unlike":[16],"existing":[17],"approaches":[18],"that":[19],"integrate":[20],"prior":[21,129],"knowledge":[22],"pre-define":[24],"the":[25,57,62,78,90,121,152],"output":[26,47],"space":[27,48],"(e.g.,":[28],"categories":[29],"coordinates)":[31],"each":[33],"task,":[35],"we":[36],"cast":[37],"diverse":[38],"into":[41],"human-intuitive":[43],"image-manipulating":[44],"process":[45,64],"whose":[46],"is":[49,59,66],"flexible":[51],"interactive":[53],"pixel":[54],"space.":[55],"Concretely,":[56],"model":[58],"built":[60],"upon":[61],"diffusion":[63],"trained":[67],"to":[68,72,89,123],"predict":[69],"pixels":[70],"according":[71],"user":[73],"instructions,":[74],"such":[75],"as":[76,105,114],"encircling":[77],"man's":[79],"left":[80,91],"shoulder":[81],"in":[82,151],"red":[83],"or":[84],"applying":[85],"blue":[87],"mask":[88],"car.":[92],"InstructDiffusion":[93],"could":[94],"handle":[95,124],"variety":[97],"of":[98,154],"tasks,":[100,146],"including":[101],"understanding":[102],"(such":[104,113],"segmentation":[106],"keypoint":[108],"detection)":[109],"generative":[111],"editing":[115],"enhancement).":[117],"It":[118],"even":[119],"exhibits":[120],"ability":[122],"unseen":[125],"outperforms":[128],"methods":[130],"on":[131],"novel":[132],"datasets.":[133],"This":[134],"represents":[135],"significant":[137],"step":[138],"towards":[139],"generalist":[141],"modeling":[142],"interface":[143],"advancing":[147],"artificial":[148],"general":[149],"intelligence":[150],"field":[153],"vision.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}