{"id":"https://openalex.org/W4396718192","doi":"https://doi.org/10.48550/arxiv.2405.02794","title":"Octopi: Object Property Reasoning with Large Tactile-Language Models","display_name":"Octopi: Object Property Reasoning with Large Tactile-Language Models","publication_year":2024,"publication_date":"2024-05-05","ids":{"openalex":"https://openalex.org/W4396718192","doi":"https://doi.org/10.48550/arxiv.2405.02794"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2405.02794","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.02794","pdf_url":"https://arxiv.org/pdf/2405.02794","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2405.02794","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064211749","display_name":"Samson Yu","orcid":"https://orcid.org/0000-0003-4647-8539"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Samson","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072170012","display_name":"Kelvin Lin","orcid":"https://orcid.org/0000-0002-1494-1464"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Kelvin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008106624","display_name":"Anxing Xiao","orcid":"https://orcid.org/0000-0001-7184-8365"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Anxing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027184297","display_name":"Jiafei Duan","orcid":"https://orcid.org/0000-0003-4551-2424"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duan, Jiafei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5066073375","display_name":"Harold Soh","orcid":"https://orcid.org/0000-0002-3278-0035"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soh, Harold","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.36730000376701355,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.36730000376701355,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.3402999937534332,"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/T11006","display_name":"BIM and Construction Integration","score":0.3109999895095825,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.7115967273712158},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6574872732162476},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5097412467002869},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37199825048446655},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.34293869137763977},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32911309599876404},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3014456033706665},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.0707639753818512},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.06679144501686096}],"concepts":[{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.7115967273712158},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6574872732162476},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5097412467002869},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37199825048446655},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.34293869137763977},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32911309599876404},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3014456033706665},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0707639753818512},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.06679144501686096}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2405.02794","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.02794","pdf_url":"https://arxiv.org/pdf/2405.02794","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2405.02794","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2405.02794","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2405.02794","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2405.02794","pdf_url":"https://arxiv.org/pdf/2405.02794","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4396718192.pdf","grobid_xml":"https://content.openalex.org/works/W4396718192.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2737719445","https://openalex.org/W2582753012","https://openalex.org/W4239098401","https://openalex.org/W4300101497","https://openalex.org/W2898210368","https://openalex.org/W2382480268","https://openalex.org/W2058182359","https://openalex.org/W4319995445","https://openalex.org/W3204019825","https://openalex.org/W2256775812"],"abstract_inverted_index":{"Physical":[0],"reasoning":[1,52,103],"is":[2,149],"important":[3],"for":[4,17,38],"effective":[5],"robot":[6],"manipulation.":[7],"Recent":[8],"work":[9],"has":[10],"investigated":[11],"both":[12,101,123],"vision":[13,20],"and":[14,29,35,89,105,127,133,167],"language":[15,30,67,140],"modalities":[16],"physical":[18,51,58,85,155],"reasoning;":[19],"can":[21,61],"reveal":[22],"information":[23],"about":[24,135],"objects":[25],"in":[26],"the":[27],"environment":[28],"serves":[31],"as":[32],"an":[33],"abstraction":[34],"communication":[36],"medium":[37],"additional":[39],"context.":[40],"Although":[41],"these":[42],"works":[43],"have":[44],"demonstrated":[45],"success":[46],"on":[47,144,162],"a":[48,95,111,119],"variety":[49],"of":[50],"tasks,":[53],"they":[54],"are":[55,169],"limited":[56],"to":[57,83,131,151,158],"properties":[59,86],"that":[60,121,147],"be":[62],"inferred":[63],"from":[64],"visual":[65],"or":[66],"inputs.":[68],"In":[69],"this":[70],"work,":[71],"we":[72],"investigate":[73],"combining":[74],"tactile":[75,107,113,124,136],"perception":[76],"with":[77,138],"language,":[78],"which":[79,99],"enables":[80],"embodied":[81],"systems":[82],"obtain":[84],"through":[87],"interaction":[88],"apply":[90],"commonsense":[91],"reasoning.":[92],"We":[93,115],"contribute":[94],"new":[96],"dataset":[97],"PhysiCLeAR,":[98],"comprises":[100],"physical/property":[102],"tasks":[104],"annotated":[106],"videos":[108],"obtained":[109],"using":[110],"GelSight":[112],"sensor.":[114],"then":[116],"introduce":[117],"Octopi,":[118],"system":[120],"leverages":[122],"representation":[125],"learning":[126],"large":[128],"vision-language":[129],"models":[130],"predict":[132],"reason":[134],"inputs":[137],"minimal":[139],"fine-tuning.":[141],"Our":[142],"evaluations":[143],"PhysiCLeAR":[145,166],"show":[146],"Octopi":[148,168],"able":[150],"effectively":[152],"use":[153],"intermediate":[154],"property":[156],"predictions":[157],"improve":[159],"its":[160],"performance":[161],"various":[163],"tactile-related":[164],"tasks.":[165],"available":[170],"at":[171],"https://github.com/clear-nus/octopi.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-08-27T14:10:00.468798","created_date":"2025-10-10T00:00:00"}