{"id":"https://openalex.org/W4323066451","doi":"https://doi.org/10.48550/arxiv.2303.00855","title":"Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents","display_name":"Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents","publication_year":2023,"publication_date":"2023-03-01","ids":{"openalex":"https://openalex.org/W4323066451","doi":"https://doi.org/10.48550/arxiv.2303.00855"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2303.00855","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.00855","pdf_url":"https://arxiv.org/pdf/2303.00855","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":null},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2303.00855","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104521370","display_name":"Wenlong Huang","orcid":"https://orcid.org/0000-0003-3611-5654"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Huang, Wenlong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676786","display_name":"Fei Xia","orcid":"https://orcid.org/0009-0002-4609-9950"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Fei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044385533","display_name":"Dhruv Shah","orcid":"https://orcid.org/0000-0001-6180-5951"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shah, Dhruv","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080239685","display_name":"Danny Driess","orcid":"https://orcid.org/0000-0002-8258-1659"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Driess, Danny","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005577303","display_name":"Andy Zeng","orcid":"https://orcid.org/0000-0002-4319-2159"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Andy","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100334841","display_name":"Yao Lu","orcid":"https://orcid.org/0000-0002-2803-534X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Yao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021289514","display_name":"Pete Florence","orcid":"https://orcid.org/0000-0002-7148-5645"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Florence, Pete","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014193325","display_name":"Igor Mordatch","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mordatch, Igor","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Levine, Sergey","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088777896","display_name":"Karol Hausman","orcid":"https://orcid.org/0000-0002-1504-6197"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hausman, Karol","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018507768","display_name":"Brian Ichter","orcid":"https://orcid.org/0000-0002-6955-6432"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ichter, Brian","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5104521370"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":13,"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/T10028","display_name":"Topic Modeling","score":0.9947999715805054,"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/T10028","display_name":"Topic Modeling","score":0.9947999715805054,"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":0.9945999979972839,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9789000153541565,"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":0.7342054843902588},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6396863460540771},{"id":"https://openalex.org/keywords/grounded-theory","display_name":"Grounded theory","score":0.6274247765541077},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5771015882492065},{"id":"https://openalex.org/keywords/situated","display_name":"Situated","score":0.5411036014556885},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5387903451919556},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5045582056045532},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4719342887401581},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.46900200843811035},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4283641576766968},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3674684762954712},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33592504262924194},{"id":"https://openalex.org/keywords/qualitative-research","display_name":"Qualitative research","score":0.12036558985710144}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7342054843902588},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6396863460540771},{"id":"https://openalex.org/C156325361","wikidata":"https://www.wikidata.org/wiki/Q1152864","display_name":"Grounded theory","level":3,"score":0.6274247765541077},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5771015882492065},{"id":"https://openalex.org/C132829578","wikidata":"https://www.wikidata.org/wiki/Q581151","display_name":"Situated","level":2,"score":0.5411036014556885},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5387903451919556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5045582056045532},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4719342887401581},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.46900200843811035},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4283641576766968},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3674684762954712},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33592504262924194},{"id":"https://openalex.org/C190248442","wikidata":"https://www.wikidata.org/wiki/Q839486","display_name":"Qualitative research","level":2,"score":0.12036558985710144},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2303.00855","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.00855","pdf_url":"https://arxiv.org/pdf/2303.00855","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":null},{"id":"doi:10.48550/arxiv.2303.00855","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2303.00855","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:2303.00855","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2303.00855","pdf_url":"https://arxiv.org/pdf/2303.00855","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":null},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1600697036","https://openalex.org/W1601337804","https://openalex.org/W4392983437","https://openalex.org/W2035858348","https://openalex.org/W2155106162","https://openalex.org/W2010047220","https://openalex.org/W1964989911","https://openalex.org/W4387507518","https://openalex.org/W2015118488","https://openalex.org/W4230093006"],"abstract_inverted_index":{"Recent":[0],"progress":[1],"in":[2,87,127,135,225],"large":[3],"language":[4,129,152,184],"models":[5,25,160,201],"(LLMs)":[6],"has":[7,179],"demonstrated":[8],"the":[9,43,63,76,81,88,97,105,109,124,151,162,183,213,231],"ability":[10],"to":[11,26,37,47,83,104,120,150,158,171,219],"learn":[12,70],"and":[13,51,154,186,208,211],"leverage":[14],"Internet-scale":[15],"knowledge":[16,126,232],"through":[17],"pre-training":[18],"with":[19,28,42],"autoregressive":[20],"models.":[21,235],"Unfortunately,":[22],"applying":[23],"such":[24,31,92,199],"settings":[27],"embodied":[29,137],"agents,":[30],"as":[32,167],"robots,":[33],"is":[34,146,217],"challenging":[35],"due":[36,103],"their":[38],"lack":[39,98],"of":[40,53,99,108,123,161,192,233],"experience":[41],"physical":[44],"world,":[45,90],"inability":[46],"parse":[48],"non-language":[49],"observations,":[50],"ignorance":[52],"rewards":[54],"or":[55],"safety":[56],"constraints":[57],"that":[58,69,79,145,177,212],"robots":[59],"may":[60],"require.":[61],"On":[62],"other":[64],"hand,":[65],"language-conditioned":[66],"robotic":[67,227],"policies":[68,93],"from":[71],"interaction":[72,110],"data":[73,111],"can":[74,202,239],"provide":[75],"necessary":[77],"grounding":[78],"allows":[80],"agent":[82],"be":[84,203,240],"correctly":[85],"situated":[86],"real":[89],"but":[91],"are":[94],"limited":[95,106],"by":[96,229],"high-level":[100],"semantic":[101,125],"understanding":[102],"breadth":[107],"available":[112],"for":[113],"training":[114],"them.":[115],"Thus,":[116],"if":[117],"we":[118,139],"want":[119],"make":[121],"use":[122],"a":[128,168,175,190,226],"model":[130,153,185,194],"while":[131],"still":[132],"situating":[133],"it":[134],"an":[136,142],"setting,":[138],"must":[140],"construct":[141],"action":[143],"sequence":[144,176],"both":[147,178,234],"likely":[148],"according":[149,157],"also":[155],"realizable":[156],"grounded":[159,193,200],"environment.":[163],"We":[164,196],"frame":[165],"this":[166],"problem":[169],"similar":[170],"probabilistic":[172],"filtering:":[173],"decode":[174],"high":[180,187],"probability":[181,188],"under":[182,189],"set":[191],"objectives.":[195],"demonstrate":[197],"how":[198],"obtained":[204],"across":[205],"three":[206],"simulation":[207],"real-world":[209],"domains,":[210],"proposed":[214],"decoding":[215],"strategy":[216],"able":[218],"solve":[220],"complex,":[221],"long-horizon":[222],"embodiment":[223],"tasks":[224],"setting":[228],"leveraging":[230],"The":[236],"project's":[237],"website":[238],"found":[241],"at":[242],"grounded-decoding.github.io.":[243]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}