{"id":"https://openalex.org/W7137959480","doi":"https://doi.org/10.1609/aaai.v40i12.37983","title":"Semore: VLM-guided Enhanced Semantic Motion Representations for Visual Reinforcement Learning","display_name":"Semore: VLM-guided Enhanced Semantic Motion Representations for Visual Reinforcement Learning","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137959480","doi":"https://doi.org/10.1609/aaai.v40i12.37983"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i12.37983","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37983","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i12.37983","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129714120","display_name":"Wentao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wentao Wang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129667839","display_name":"Chunyang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunyang Liu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016509766","display_name":"Kehua Sheng","orcid":"https://orcid.org/0009-0008-3370-7711"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kehua Sheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129678275","display_name":"Bo Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129654870","display_name":"Yan O. Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan Wang","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5129714120"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21700224,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"12","first_page":"10154","last_page":"10162"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9628999829292297,"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":0.9628999829292297,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.007199999876320362,"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":0.004000000189989805,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6687999963760376},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6557000279426575},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5961999893188477},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5103999972343445},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5047000050544739},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.45820000767707825},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4309000074863434},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.3968999981880188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.777400016784668},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6687999963760376},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6680999994277954},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6557000279426575},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5961999893188477},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5103999972343445},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5047000050544739},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.45820000767707825},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.3968999981880188},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.38269999623298645},{"id":"https://openalex.org/C82990744","wikidata":"https://www.wikidata.org/wiki/Q166194","display_name":"RGB color model","level":2,"score":0.37700000405311584},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3644999861717224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34950000047683716},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.32989999651908875},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28850001096725464},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.27959999442100525},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2793999910354614},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2752000093460083},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.267300009727478},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.26260000467300415}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i12.37983","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37983","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i12.37983","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i12.37983","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8171299695968628,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"growing":[1],"exploration":[2],"of":[3,19,33,40,43,132,149],"Large":[4],"Language":[5],"Models":[6,10],"(LLM)":[7],"and":[8,36,70,115,134,159],"Vision-Language":[9],"(VLM)":[11],"has":[12],"opened":[13],"avenues":[14],"for":[15,62,118],"enhancing":[16],"the":[17,31,38,44,78,95,100,105,109,130,147,152],"effectiveness":[18],"reinforcement":[20],"learning":[21],"(RL).":[22],"However,":[23],"existing":[24],"LLM-based":[25],"RL":[26],"methods":[27],"often":[28],"focus":[29],"on":[30],"guidance":[32,148],"control":[34],"policy":[35],"encounter":[37],"challenge":[39],"limited":[41],"representations":[42,72,107,117],"backbone":[45,76],"networks.":[46],"To":[47,111],"tackle":[48],"this":[49],"problem,":[50],"we":[51],"introduce":[52],"Enhanced":[53],"Semantic":[54],"Motion":[55],"Representations":[56],"(Semore),":[57],"a":[58,74,123],"new":[59],"VLM-based":[60],"framework":[61],"visual":[63],"RL,":[64],"which":[65],"can":[66],"simultaneously":[67,128],"extract":[68],"semantic":[69,114],"motion":[71,116],"through":[73],"dual-path":[75],"from":[77,91],"RGB":[79],"flows.":[80],"Semore":[81],"utilizes":[82],"VLM":[83,150],"with":[84],"common-sense":[85],"knowledge":[86],"to":[87,98,127,139,163],"retrieve":[88],"key":[89],"information":[90],"observations,":[92],"while":[93,136],"using":[94],"pre-trained":[96],"clip":[97],"achieve":[99],"text-image":[101],"alignment,":[102],"thereby":[103],"embedding":[104],"ground-truth":[106],"into":[108],"backbone.":[110],"efficiently":[112],"fuse":[113],"decision-making,":[119],"our":[120,155],"method":[121,156],"adopts":[122],"separately":[124],"supervised":[125],"approach":[126],"guide":[129],"extraction":[131],"semantics":[133],"motion,":[135],"allowing":[137],"them":[138],"interact":[140],"spontaneously.":[141],"Extensive":[142],"experiments":[143],"demonstrate":[144],"that,":[145],"under":[146],"at":[151],"feature":[153],"level,":[154],"exhibits":[157],"efficient":[158],"adaptive":[160],"ability":[161],"compared":[162],"state-of-the-art":[164],"methods.":[165],"All":[166],"codes":[167],"are":[168],"released.":[169]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}