{"id":"https://openalex.org/W7166838659","doi":"https://doi.org/10.18653/v1/2026.acl-long.1165","title":"Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts","display_name":"Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166838659","doi":"https://doi.org/10.18653/v1/2026.acl-long.1165"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1165","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1165","pdf_url":"https://aclanthology.org/2026.acl-long.1165.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1165.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139779131","display_name":"Di Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139753285","display_name":"Xun Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xun Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139722283","display_name":"Shaohan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaohan Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122951088","display_name":"Lingjie Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lingjie Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139807949","display_name":"Yaru Hao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaru Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139790469","display_name":"Li Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077329331","display_name":"Zewen Chi","orcid":"https://orcid.org/0000-0003-1615-1885"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zewen Chi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139757728","display_name":"Zhifang Sui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhifang Sui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139803669","display_name":"Furu Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Furu Wei","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.82814661,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"25446","last_page":"25457"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.7774999737739563,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.7774999737739563,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.03060000017285347,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.013000000268220901,"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":0.4569000005722046},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.35100001096725464},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.32589998841285706},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.32249999046325684},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.31040000915527344}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49320000410079956},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4569000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4496999979019165},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2849999964237213},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26420000195503235}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1165","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1165","pdf_url":"https://aclanthology.org/2026.acl-long.1165.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1165","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1165","pdf_url":"https://aclanthology.org/2026.acl-long.1165.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.756484866142273,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166838659.pdf","grobid_xml":"https://content.openalex.org/works/W7166838659.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Di":[0],"Zhang,":[1],"Xun":[2],"Wu,":[3],"Shaohan":[4],"Huang,":[5],"Lingjie":[6],"Jiang,":[7],"Yaru":[8],"Hao,":[9],"Li":[10],"Dong,":[11],"Zewen":[12],"Chi,":[13],"Zhifang":[14],"Sui,":[15],"Furu":[16],"Wei.":[17],"Proceedings":[18],"of":[19,24],"the":[20,25],"64th":[21],"Annual":[22],"Meeting":[23],"Association":[26],"for":[27],"Computational":[28],"Linguistics":[29],"(Volume":[30],"1:":[31],"Long":[32],"Papers).":[33],"2026.":[34]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}