{"id":"https://openalex.org/W4416034157","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1042","title":"Knowing More, Acting Better: Hierarchical Representation for Embodied Decision-Making","display_name":"Knowing More, Acting Better: Hierarchical Representation for Embodied Decision-Making","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034157","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.1042"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1042","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1042","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1042.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.1042.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100390394","display_name":"Chunhui Zhang","orcid":"https://orcid.org/0000-0002-8589-0158"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunhui Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006449247","display_name":"Zhongyu Ouyang","orcid":"https://orcid.org/0000-0002-4830-6768"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhongyu Ouyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101892331","display_name":"Xingjian Diao","orcid":"https://orcid.org/0000-0001-9605-4991"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingjian Diao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038767043","display_name":"Zheyuan Liu","orcid":"https://orcid.org/0000-0001-7809-4586"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheyuan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5035399743","display_name":"Soroush Vosoughi","orcid":"https://orcid.org/0000-0002-2564-8909"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soroush Vosoughi","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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"19144","last_page":"19155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11883","display_name":"Embodied and Extended Cognition","score":0.33180001378059387,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11883","display_name":"Embodied and Extended Cognition","score":0.33180001378059387,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10656","display_name":"Child and Animal Learning Development","score":0.10610000044107437,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11431","display_name":"Action Observation and Synchronization","score":0.07159999758005142,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5358999967575073},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5034000277519226},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.27790001034736633},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2718000113964081},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.26930001378059387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5911999940872192},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5358999967575073},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5034000277519226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.460099995136261},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2718000113964081},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2515000104904175},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.24719999730587006}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.1042","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1042","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1042.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.1042","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.1042","pdf_url":"https://aclanthology.org/2025.findings-emnlp.1042.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8672557266","display_name":"Collaborative Research: EAGER: NAIRR Pilot: An AI infrastructure to advance research in reducing poverty and informing social policy","funder_award_id":"2452367","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034157.pdf","grobid_xml":"https://content.openalex.org/works/W4416034157.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"embodied":[1,124,147],"AI":[2],"uses":[3],"multimodal":[4],"large":[5],"language":[6],"models":[7,125],"(MLLMs)":[8],"as":[9,152],"policy":[10],"models,":[11],"predicting":[12],"actions":[13],"from":[14,65],"final-layer":[15],"hidden":[16],"states.This":[17],"widely":[18],"adopted":[19],"approach,":[20],"however,":[21],"assumes":[22],"that":[23,61,74],"monolithic":[24],"last-layer":[25],"representations":[26,64],"suffice":[27],"for":[28,47,106],"decision-making-a":[29],"structural":[30],"simplification":[31],"at":[32],"odds":[33],"with":[34],"decades":[35],"of":[36,43],"cognitive":[37,159],"science,":[38],"which":[39],"highlights":[40],"the":[41,69],"importance":[42],"distributed,":[44],"hierarchical":[45,57,116,150],"processing":[46],"perception":[48],"and":[49,85,109,134,161],"action.Addressing":[50],"this":[51],"foundational":[52],"asymmetry,":[53],"we":[54],"introduce":[55],"a":[56,103,130,135,153],"action":[58],"probing":[59,151],"method":[60],"explicitly":[62],"aggregates":[63],"all":[66],"layers,":[67],"mirroring":[68],"brain's":[70],"multi-level":[71],"organization.Experiments":[72],"reveal":[73],"early":[75],"layers":[76,81,87],"facilitate":[77],"spatial":[78,107,139],"grounding,":[79],"middle":[80],"support":[82],"contextual":[83,110],"integration,":[84],"later":[86],"enable":[88],"abstract":[89],"generalization-which":[90],"shows":[91,118],"MLLMs":[92],"inherently":[93],"encode":[94],"distributed":[95],"action-relevant":[96],"structures.These":[97],"layer-wise":[98],"features":[99],"are":[100],"integrated":[101],"by":[102],"lightweight":[104],"probe":[105],"reasoning":[108,140],"understanding,":[111],"without":[112],"costly":[113],"backbone":[114],"fine-tuning.This":[115],"solution":[117],"significant":[119],"improvements":[120],"over":[121],"standard":[122],"lastlayer":[123],"in":[126,138,146,157],"physical":[127],"simulators,":[128],"achieving":[129],"46.6%":[131],"success":[132],"rate":[133],"62.5%":[136],"gain":[137],"tasks.These":[141],"findings":[142],"challenge":[143],"conventional":[144],"assumptions":[145],"AI,":[148],"establishing":[149],"principled":[154],"alternative":[155],"grounded":[156],"both":[158],"theory":[160],"empirical":[162],"evidence.":[163]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-08T00:00:00"}