{"id":"https://openalex.org/W7165377346","doi":"https://doi.org/10.1016/j.knosys.2026.116496","title":"What you say is what you get: Text-aligned semantic reward modeling with vision-language representations for reinforcement learning","display_name":"What you say is what you get: Text-aligned semantic reward modeling with vision-language representations for reinforcement learning","publication_year":2026,"publication_date":"2026-06-19","ids":{"openalex":"https://openalex.org/W7165377346","doi":"https://doi.org/10.1016/j.knosys.2026.116496"},"language":"en","primary_location":{"id":"doi:10.1016/j.knosys.2026.116496","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.116496","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100351716","display_name":"Wei He","orcid":"https://orcid.org/0009-0004-3424-5783"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei He","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China","Xi\u2019an Key Laboratory of Human\u2013Machine Collaborative Cyber-Physical Systems, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]},{"raw_affiliation_string":"Xi\u2019an Key Laboratory of Human\u2013Machine Collaborative Cyber-Physical Systems, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023257092","display_name":"Yukun Xiao","orcid":"https://orcid.org/0000-0001-5089-3538"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yukun Xiao","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China","Xi\u2019an Key Laboratory of Human\u2013Machine Collaborative Cyber-Physical Systems, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]},{"raw_affiliation_string":"Xi\u2019an Key Laboratory of Human\u2013Machine Collaborative Cyber-Physical Systems, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027446640","display_name":"Liqian Ma","orcid":"https://orcid.org/0000-0002-0814-9876"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqian Ma","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China","Xi\u2019an Key Laboratory of Human\u2013Machine Collaborative Cyber-Physical Systems, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0009-0185-3279","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]},{"raw_affiliation_string":"Xi\u2019an Key Laboratory of Human\u2013Machine Collaborative Cyber-Physical Systems, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432536","display_name":"Yisheng An","orcid":"https://orcid.org/0000-0003-4632-4919"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yisheng An","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China","Xi\u2019an Key Laboratory of Human\u2013Machine Collaborative Cyber-Physical Systems, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0003-4632-4919","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]},{"raw_affiliation_string":"Xi\u2019an Key Laboratory of Human\u2013Machine Collaborative Cyber-Physical Systems, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031068301","display_name":"Bo Sun","orcid":"https://orcid.org/0000-0001-6664-8676"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Sun","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China","Xi\u2019an Key Laboratory of Human\u2013Machine Collaborative Cyber-Physical Systems, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0001-6664-8676","affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]},{"raw_affiliation_string":"Xi\u2019an Key Laboratory of Human\u2013Machine Collaborative Cyber-Physical Systems, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633632","display_name":"Yue Wang","orcid":"https://orcid.org/0000-0003-0098-5359"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaxian Wang","raw_affiliation_strings":["School of Information Engineering, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China","Xi\u2019an Key Laboratory of Human\u2013Machine Collaborative Cyber-Physical Systems, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]},{"raw_affiliation_string":"Xi\u2019an Key Laboratory of Human\u2013Machine Collaborative Cyber-Physical Systems, Chang\u2019an University, Xi\u2019an, 710064, Shaanxi, China","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100361891","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-6004-0675"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["Ministry of Education Key Laboratory of Intelligent Networks and Network Security, and School of Computer Science and Technology, Xi\u2019an Jiaotong University, Xi\u2019an, 710049, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-6004-0675","affiliations":[{"raw_affiliation_string":"Ministry of Education Key Laboratory of Intelligent Networks and Network Security, and School of Computer Science and Technology, Xi\u2019an Jiaotong University, Xi\u2019an, 710049, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100432536"],"corresponding_institution_ids":["https://openalex.org/I25355098"],"apc_list":{"value":3130,"currency":"USD","value_usd":3130},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79181039,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"349","issue":null,"first_page":"116496","last_page":"116496"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6140000224113464,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6140000224113464,"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/T11519","display_name":"Digital Mental Health Interventions","score":0.031199999153614044,"subfield":{"id":"https://openalex.org/subfields/3202","display_name":"Applied 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/T10667","display_name":"Emotion and Mood Recognition","score":0.02800000086426735,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8289999961853027},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5464000105857849},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.524399995803833},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.46549999713897705},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.43700000643730164},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4036000072956085},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.3587000072002411}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8289999961853027},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6525999903678894},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5464000105857849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.545799970626831},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.524399995803833},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.43700000643730164},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4036000072956085},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3601999878883362},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32280001044273376},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.32089999318122864},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.31130000948905945},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.29100000858306885},{"id":"https://openalex.org/C67277372","wikidata":"https://www.wikidata.org/wiki/Q7449085","display_name":"Semantic role labeling","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.26409998536109924},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.25099998712539673},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.knosys.2026.116496","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.knosys.2026.116496","pdf_url":null,"source":{"id":"https://openalex.org/S10169007","display_name":"Knowledge-Based Systems","issn_l":"0950-7051","issn":["0950-7051","1872-7409"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Knowledge-Based Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6241488456726074,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W2616247523","https://openalex.org/W2963341956","https://openalex.org/W4297964528","https://openalex.org/W4368232744","https://openalex.org/W4385858056","https://openalex.org/W4387415195","https://openalex.org/W4391654576","https://openalex.org/W4395116617","https://openalex.org/W4402592483","https://openalex.org/W4404627931","https://openalex.org/W4404738510","https://openalex.org/W4405614453","https://openalex.org/W4410043735","https://openalex.org/W4411120032","https://openalex.org/W4412489912","https://openalex.org/W4413156825","https://openalex.org/W4413362511","https://openalex.org/W4413444580","https://openalex.org/W4413655311","https://openalex.org/W4413858428","https://openalex.org/W4413926122","https://openalex.org/W4414198480","https://openalex.org/W4416748544","https://openalex.org/W4417239585","https://openalex.org/W7133201058","https://openalex.org/W7133208539","https://openalex.org/W7133224126","https://openalex.org/W7160208130"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-06-22T06:23:43.705686","created_date":"2026-06-20T00:00:00"}
