{"id":"https://openalex.org/W4416748797","doi":"https://doi.org/10.1109/iros60139.2025.11246374","title":"ManipGPT: Is Affordance Segmentation by Large Vision Models Enough for Articulated Object Manipulation?","display_name":"ManipGPT: Is Affordance Segmentation by Large Vision Models Enough for Articulated Object Manipulation?","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748797","doi":"https://doi.org/10.1109/iros60139.2025.11246374"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101736516","display_name":"Taewhan Kim","orcid":"https://orcid.org/0000-0003-2376-4970"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Taewhan Kim","raw_affiliation_strings":["Peking University,CFCS, School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Peking University,CFCS, School of Computer Science","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hojin Bae","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hojin Bae","raw_affiliation_strings":["Peking University,CFCS, School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Peking University,CFCS, School of Computer Science","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065271362","display_name":"Zeming Li","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeming Li","raw_affiliation_strings":["Peking University,CFCS, School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Peking University,CFCS, School of Computer Science","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100634697","display_name":"Xiaoqi Li","orcid":"https://orcid.org/0000-0001-7462-6303"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqi Li","raw_affiliation_strings":["Peking University,CFCS, School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Peking University,CFCS, School of Computer Science","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104261352","display_name":"Iaroslav Ponomarenko","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Iaroslav Ponomarenko","raw_affiliation_strings":["Peking University,CFCS, School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Peking University,CFCS, School of Computer Science","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050276953","display_name":"Ruihai Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruihai Wu","raw_affiliation_strings":["Peking University,CFCS, School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Peking University,CFCS, School of Computer Science","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100389347","display_name":"Hao Dong","orcid":"https://orcid.org/0000-0002-0132-0239"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Dong","raw_affiliation_strings":["Peking University,CFCS, School of Computer Science"],"affiliations":[{"raw_affiliation_string":"Peking University,CFCS, School of Computer Science","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5101736516"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.441317,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20974","last_page":"20981"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8586999773979187,"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"}},"topics":[{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.8586999773979187,"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"}},{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.024800000712275505,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10531","display_name":"Advanced Vision and Imaging","score":0.018200000748038292,"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/affordance","display_name":"Affordance","score":0.9193999767303467},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5626000165939331},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4984999895095825},{"id":"https://openalex.org/keywords/transformative-learning","display_name":"Transformative learning","score":0.498199999332428},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.461899995803833},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.45260000228881836},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.373199999332428},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.33799999952316284}],"concepts":[{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.9193999767303467},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7069000005722046},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6798999905586243},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.590499997138977},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5626000165939331},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4984999895095825},{"id":"https://openalex.org/C70587473","wikidata":"https://www.wikidata.org/wiki/Q7834111","display_name":"Transformative learning","level":2,"score":0.498199999332428},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.461899995803833},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.45260000228881836},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3301999866962433},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C54174078","wikidata":"https://www.wikidata.org/wiki/Q3197188","display_name":"Kinome","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2800999879837036},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.26330000162124634},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2542000114917755}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2773765248","https://openalex.org/W2961368225","https://openalex.org/W3035131925","https://openalex.org/W3035198432","https://openalex.org/W3035624836","https://openalex.org/W3083488491","https://openalex.org/W3120441392","https://openalex.org/W3199614037","https://openalex.org/W3207081724","https://openalex.org/W4206386832","https://openalex.org/W4221153063","https://openalex.org/W4283785166","https://openalex.org/W4288083516","https://openalex.org/W4313033364","https://openalex.org/W4313160783","https://openalex.org/W4383097515","https://openalex.org/W4389666682","https://openalex.org/W4390872920","https://openalex.org/W4390873795","https://openalex.org/W4390874575","https://openalex.org/W4401415189","https://openalex.org/W4402727730","https://openalex.org/W4402754134","https://openalex.org/W4405786114"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"actionable":[1],"affordance":[2,34,106,130],"has":[3],"emerged":[4],"as":[5],"a":[6,55,67,75],"transformative":[7],"approach":[8],"in":[9],"robotics,":[10],"focusing":[11],"on":[12,22,98],"perceiving":[13],"interaction":[14,28,61],"areas":[15,62],"prior":[16],"to":[17,25,44,46,58,83,114],"manipulation.":[18],"Traditional":[19],"methods":[20],"rely":[21],"pixel":[23],"sampling":[24],"identify":[26],"successful":[27],"samples":[29],"or":[30,145],"processing":[31],"pointclouds":[32],"for":[33,63,142],"mapping.":[35],"However,":[36],"these":[37],"approaches":[38],"are":[39],"computationally":[40],"intensive":[41],"and":[42,48,80,89,124],"struggle":[43],"adapt":[45],"diverse":[47],"dynamic":[49],"environments.":[50],"This":[51,118],"paper":[52],"introduces":[53],"ManipGPT,":[54],"framework":[56],"designed":[57],"predict":[59],"optimal":[60],"articulated":[64],"objects":[65],"using":[66],"large":[68],"pretrained":[69],"vision":[70,96],"transformer":[71,97],"(ViT).":[72],"We":[73],"create":[74],"dataset":[76],"of":[77],"9.9k":[78],"simulated":[79,123],"real":[81],"images":[82],"bridge":[84],"the":[85,95,109,140],"visual":[86],"simto-real":[87],"gap":[88],"enhance":[90],"real-world":[91,125],"applicability.":[92],"By":[93],"finetuning":[94],"this":[99],"small":[100],"dataset,":[101],"we":[102],"significantly":[103],"improve":[104],"part-level":[105,129],"segmentation,":[107],"adapting":[108],"model\u2019s":[110],"in-context":[111],"segmentation":[112],"capabilities":[113],"robot":[115],"manipulation":[116,121],"scenarios.":[117],"enables":[119],"effective":[120],"across":[122],"environments":[126],"by":[127],"generating":[128],"masks,":[131],"paired":[132],"with":[133],"an":[134],"impedance":[135],"adaptation":[136],"policy,":[137],"sufficiently":[138],"eliminating":[139],"need":[141],"complex":[143],"datasets":[144],"perception":[146],"systems.":[147],"Our":[148],"project":[149],"page":[150],"is":[151],"available":[152],"at:":[153],"https://lxkim814.github.io/ManipGPT_website/":[154]},"counts_by_year":[],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-11-28T00:00:00"}