{"id":"https://openalex.org/W4415288396","doi":"https://doi.org/10.1109/iccv51701.2025.00944","title":"GraspCoT: Integrating Physical Property Reasoning for 6-DoF Grasping Under Flexible Language Instructions","display_name":"GraspCoT: Integrating Physical Property Reasoning for 6-DoF Grasping Under Flexible Language Instructions","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4415288396","doi":"https://doi.org/10.1109/iccv51701.2025.00944"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00944","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00944","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":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2503.16013","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049103765","display_name":"Xiaomeng Chu","orcid":"https://orcid.org/0000-0003-3040-1289"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaomeng Chu","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089561793","display_name":"Jiajun Deng","orcid":"https://orcid.org/0000-0001-9624-7451"},"institutions":[{"id":"https://openalex.org/I5681781","display_name":"The University of Adelaide","ror":"https://ror.org/00892tw58","country_code":"AU","type":"education","lineage":["https://openalex.org/I5681781"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jiajun Deng","raw_affiliation_strings":["The University of Adelaide"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Adelaide","institution_ids":["https://openalex.org/I5681781"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034921190","display_name":"Guoliang You","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoliang You","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023154495","display_name":"Wei Liu","orcid":"https://orcid.org/0000-0002-3315-5370"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Liu","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100749620","display_name":"Xingchen Li","orcid":"https://orcid.org/0000-0001-7843-7446"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingchen Li","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061104105","display_name":"Jianmin Ji","orcid":"https://orcid.org/0000-0002-1515-0402"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianmin Ji","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053344541","display_name":"Yanyong Zhang","orcid":"https://orcid.org/0000-0001-6520-255X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanyong Zhang","raw_affiliation_strings":["University of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":"10130","last_page":"10140"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9866999983787537,"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/T13629","display_name":"Text Readability and Simplification","score":0.9866999983787537,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9603000283241272,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.9271000027656555,"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/grasp","display_name":"GRASP","score":0.8562999963760376},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6032999753952026},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.5753999948501587},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5569000244140625},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.5511999726295471},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5504999756813049},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5317000150680542},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5271999835968018}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.8562999963760376},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7720000147819519},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6032999753952026},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5863999724388123},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.5753999948501587},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5569000244140625},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.5511999726295471},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5504999756813049},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5317000150680542},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5271999835968018},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5073000192642212},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4706999957561493},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.447299987077713},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3774000108242035},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.37049999833106995},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29989999532699585},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2921999990940094},{"id":"https://openalex.org/C145460709","wikidata":"https://www.wikidata.org/wiki/Q859951","display_name":"Human\u2013robot interaction","level":3,"score":0.289000004529953},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25690001249313354}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iccv51701.2025.00944","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00944","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":"doi:10.48550/arxiv.2503.16013","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.16013","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2503.16013","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.16013","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4430582919","display_name":null,"funder_award_id":"62332016","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2033223309","https://openalex.org/W2805051407","https://openalex.org/W2890646997","https://openalex.org/W2962875890","https://openalex.org/W2963033241","https://openalex.org/W2963351448","https://openalex.org/W2986303149","https://openalex.org/W3004103739","https://openalex.org/W3022674252","https://openalex.org/W3035198432","https://openalex.org/W3204876017","https://openalex.org/W3206683563","https://openalex.org/W3207888596","https://openalex.org/W4380450805","https://openalex.org/W4382366145","https://openalex.org/W4383109488","https://openalex.org/W4386066015","https://openalex.org/W4387092545","https://openalex.org/W4389667691","https://openalex.org/W4390874575","https://openalex.org/W4401414292","https://openalex.org/W4402716423","https://openalex.org/W4402727761","https://openalex.org/W4402916210","https://openalex.org/W4403562331","https://openalex.org/W4405078890","https://openalex.org/W4405079066","https://openalex.org/W4405785307","https://openalex.org/W4405785344","https://openalex.org/W4405786716","https://openalex.org/W4405786915","https://openalex.org/W4413145659","https://openalex.org/W4414051092","https://openalex.org/W4415797783","https://openalex.org/W7133224126","https://openalex.org/W7133246057"],"related_works":[],"abstract_inverted_index":{"Flexible":[0],"instruction-guided":[1],"6-DoF":[2,66],"grasping":[3],"is":[4,195],"a":[5,65,72,90,115,153],"significant":[6],"yet":[7],"challenging":[8],"task":[9],"for":[10,163],"real-world":[11,187],"robotic":[12,188],"systems.":[13],"Existing":[14],"methods":[15],"utilize":[16],"the":[17,22,41,44,158,178],"contextual":[18],"understanding":[19],"capabilities":[20],"of":[21,92,124,180],"large":[23],"language":[24],"models":[25],"(LLMs)":[26],"to":[27,36,57,78,95,144],"establish":[28],"mappings":[29],"between":[30],"expressions":[31],"and":[32,108,131,169],"targets,":[33],"allowing":[34],"robots":[35],"comprehend":[37],"users'":[38],"intentions":[39],"in":[40,160,186],"instructions.":[42],"However,":[43],"LLM's":[45],"knowledge":[46],"about":[47],"objects'":[48],"physical":[49,79,105],"properties":[50],"remains":[51],"underexplored":[52],"despite":[53],"its":[54,191],"tight":[55],"relevance":[56],"grasping.":[58],"In":[59],"this":[60],"work,":[61],"we":[62,88,150],"propose":[63],"GraspCoT,":[64],"grasp":[67,109,146,165],"detection":[68,166],"framework":[69],"that":[70,99,156],"integrates":[71],"Chain-of-Thought":[73],"(CoT)":[74],"reasoning":[75,98],"mechanism":[76],"oriented":[77],"properties,":[80],"guided":[81],"by":[82],"auxiliary":[83],"question-answering":[84],"(QA)":[85],"tasks.":[86],"Particularly,":[87],"design":[89],"set":[91],"QA":[93],"templates":[94],"enable":[96],"hierarchical":[97],"includes":[100],"three":[101],"stages:":[102],"target":[103],"parsing,":[104],"property":[106],"analysis,":[107],"action":[110],"selection.":[111],"Moreover,":[112],"GraspCoT":[113],"presents":[114],"unified":[116],"multimodal":[117],"LLM":[118],"architecture,":[119],"which":[120],"encodes":[121],"multi-view":[122],"observations":[123],"3D":[125],"scenes":[126],"into":[127],"3D-aware":[128],"visual":[129,136],"tokens,":[130],"then":[132],"jointly":[133],"embeds":[134],"these":[135],"tokens":[137,141],"with":[138,183],"CoT-derived":[139],"textual":[140],"within":[142],"LLMs":[143],"generate":[145],"pose":[147],"predictions.":[148],"Furthermore,":[149],"present":[151],"IntentGrasp,":[152],"large-scale":[154],"benchmark":[155],"fills":[157],"gap":[159],"public":[161],"datasets":[162],"multi-object":[164],"under":[167],"diverse":[168],"indirect":[170],"verbal":[171],"commands.":[172],"Extensive":[173],"experiments":[174],"on":[175],"IntentGrasp":[176],"demonstrate":[177],"superiority":[179],"our":[181],"method,":[182],"additional":[184],"validation":[185],"applications":[189],"confirming":[190],"practicality.":[192],"The":[193],"code":[194],"available":[196],"at":[197],"https://github.com/cxmomo/GraspCoT.":[198]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-17T00:00:00"}