{"id":"https://openalex.org/W4380353811","doi":"https://doi.org/10.48550/arxiv.2306.05696","title":"Embodied Executable Policy Learning with Language-based Scene Summarization","display_name":"Embodied Executable Policy Learning with Language-based Scene Summarization","publication_year":2023,"publication_date":"2023-06-09","ids":{"openalex":"https://openalex.org/W4380353811","doi":"https://doi.org/10.48550/arxiv.2306.05696"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2306.05696","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.05696","pdf_url":"https://arxiv.org/pdf/2306.05696","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/2306.05696","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058194829","display_name":"Jielin Qiu","orcid":"https://orcid.org/0000-0002-7384-1324"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Qiu, Jielin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102020639","display_name":"Mengdi Xu","orcid":"https://orcid.org/0000-0001-6087-7558"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Mengdi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066352315","display_name":"William Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, William","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091107431","display_name":"Seungwhan Moon","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moon, Seungwhan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037644321","display_name":"Ding Zhao","orcid":"https://orcid.org/0000-0002-9400-8446"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Ding","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5058194829"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.9976999759674072,"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":0.9976999759674072,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9793000221252441,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9343000054359436,"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/automatic-summarization","display_name":"Automatic summarization","score":0.7979985475540161},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7687026262283325},{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.7273188829421997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5898688435554504},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.557873547077179},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.5498011112213135},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4798164367675781},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.4691578149795532},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4499064087867737},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4269421398639679},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4239058494567871},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.23974457383155823}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.7979985475540161},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7687026262283325},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.7273188829421997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5898688435554504},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.557873547077179},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.5498011112213135},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4798164367675781},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.4691578149795532},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4499064087867737},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4269421398639679},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4239058494567871},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.23974457383155823}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2306.05696","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.05696","pdf_url":"https://arxiv.org/pdf/2306.05696","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.2306.05696","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2306.05696","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:2306.05696","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2306.05696","pdf_url":"https://arxiv.org/pdf/2306.05696","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/W4380353811.pdf","grobid_xml":"https://content.openalex.org/works/W4380353811.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W4306886878","https://openalex.org/W1517524280","https://openalex.org/W2740009304"],"abstract_inverted_index":{"Large":[0],"Language":[1],"models":[2],"(LLMs)":[3],"have":[4],"shown":[5],"remarkable":[6],"success":[7],"in":[8,34,72,136,237],"assisting":[9],"robot":[10,36,147],"learning":[11,37,65,138,148,208,211,257],"tasks,":[12],"i.e.,":[13],"complex":[14],"household":[15],"planning.":[16],"However,":[17],"the":[18,49,73,89,128,131,137,157,162,173,176,186,192,216,238,252],"performance":[19],"of":[20,75,85,111,127,154,172,254],"pretrained":[21],"LLMs":[22,44],"heavily":[23],"relies":[24],"on":[25,185],"domain-specific":[26],"templated":[27],"text":[28,46,125,170],"data,":[29],"which":[30,103,140,160,179],"may":[31],"be":[32],"infeasible":[33],"real-world":[35,146],"tasks":[38,219,232],"with":[39,45,53,56],"image-based":[40],"observations.":[41],"Moreover,":[42,118],"existing":[43,249],"inputs":[47],"lack":[48],"capability":[50],"to":[51,213,215],"evolve":[52],"non-expert":[54],"interactions":[55],"environments.":[57],"In":[58],"this":[59,255],"work,":[60],"we":[61],"introduce":[62],"a":[63,109,169],"novel":[64,256],"paradigm":[66,97,152],"that":[67,197,245],"generates":[68,180],"robots'":[69],"executable":[70,181],"actions":[71],"form":[74],"text,":[76],"derived":[77],"solely":[78],"from":[79,100],"visual":[80,114,165],"observations,":[81],"using":[82,164],"language-based":[83],"summarization":[84,126],"these":[86],"observations":[87,166],"as":[88,116],"connecting":[90],"bridge":[91],"between":[92],"both":[93],"domains.":[94],"Our":[95,150,241],"proposed":[96,151,199],"stands":[98],"apart":[99],"previous":[101],"works,":[102],"utilized":[104],"either":[105],"language":[106,112,188],"instructions":[107],"or":[108],"combination":[110],"and":[113,167,175,209,231],"data":[115],"inputs.":[117],"our":[119,198,246],"method":[120,200,247],"does":[121],"not":[122],"require":[123],"oracle":[124],"scene,":[129,174],"eliminating":[130],"need":[132],"for":[133,145],"human":[134],"involvement":[135],"loop,":[139],"makes":[141],"it":[142],"more":[143],"practical":[144],"tasks.":[149],"consists":[153],"two":[155,203],"modules:":[156],"SUM":[158,193],"module,":[159,178],"interprets":[161],"environment":[163],"produces":[168],"summary":[171],"APM":[177],"action":[182],"policies":[183],"based":[184],"natural":[187],"descriptions":[189],"provided":[190],"by":[191],"module.":[194],"We":[195,221],"demonstrate":[196,244],"can":[201],"employ":[202],"fine-tuning":[204],"strategies,":[205],"including":[206],"imitation":[207],"reinforcement":[210],"approaches,":[212],"adapt":[214],"target":[217],"test":[218],"effectively.":[220],"conduct":[222],"extensive":[223],"experiments":[224],"involving":[225],"various":[226],"SUM/APM":[227],"model":[228],"selections,":[229],"environments,":[230],"across":[233],"7":[234],"house":[235],"layouts":[236],"VirtualHome":[239],"environment.":[240],"experimental":[242],"results":[243],"surpasses":[248],"baselines,":[250],"confirming":[251],"effectiveness":[253],"paradigm.":[258]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2023-06-13T00:00:00"}