{"id":"https://openalex.org/W7160267000","doi":"https://doi.org/10.1109/wacv61042.2026.00101","title":"No MoCap Needed: Post-Training Motion Diffusion Models with Reinforcement Learning using Only Textual Prompts","display_name":"No MoCap Needed: Post-Training Motion Diffusion Models with Reinforcement Learning using Only Textual Prompts","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160267000","doi":"https://doi.org/10.1109/wacv61042.2026.00101"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5135352734","display_name":"Macaluso Girolamo","orcid":null},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Macaluso Girolamo","raw_affiliation_strings":["University of Florence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florence","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135331761","display_name":"Mandelli Lorenzo","orcid":null},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mandelli Lorenzo","raw_affiliation_strings":["University of Florence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florence","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119964110","display_name":"Mirko Bicchierai","orcid":null},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mirko Bicchierai","raw_affiliation_strings":["University of Florence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florence","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135368541","display_name":"Stefano Berretti","orcid":null},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stefano Berretti","raw_affiliation_strings":["University of Florence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florence","institution_ids":["https://openalex.org/I45084792"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135380493","display_name":"Andrew D. Bagdanov","orcid":null},"institutions":[{"id":"https://openalex.org/I45084792","display_name":"University of Florence","ror":"https://ror.org/04jr1s763","country_code":"IT","type":"education","lineage":["https://openalex.org/I45084792"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrew D. Bagdanov","raw_affiliation_strings":["University of Florence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Florence","institution_ids":["https://openalex.org/I45084792"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45084792"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"967","last_page":"976"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.14499999582767487,"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":0.14499999582767487,"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/T12290","display_name":"Human Motion and Animation","score":0.13819999992847443,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.07410000264644623,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.5777000188827515},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.44510000944137573},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.3043000102043152},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.29179999232292175},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.28769999742507935}],"concepts":[{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.5777000188827515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5702999830245972},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.551800012588501},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4041999876499176},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2827000021934509},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.26969999074935913}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wacv61042.2026.00101","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00101","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:flore.unifi.it:2158/1479712","is_oa":false,"landing_page_url":"https://hdl.handle.net/2158/1479712","pdf_url":null,"source":{"id":"https://openalex.org/S4306402033","display_name":"Florence Research (University of Florence)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45084792","host_organization_name":"University of Florence","host_organization_lineage":["https://openalex.org/I45084792"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1735317348","https://openalex.org/W1967554269","https://openalex.org/W1986014385","https://openalex.org/W2469134594","https://openalex.org/W2474702929","https://openalex.org/W2796290181","https://openalex.org/W2902149428","https://openalex.org/W3153832461","https://openalex.org/W3161463741","https://openalex.org/W3204221554","https://openalex.org/W4231947169","https://openalex.org/W4297981470","https://openalex.org/W4312635677","https://openalex.org/W4382457661","https://openalex.org/W4386065848","https://openalex.org/W4386076288","https://openalex.org/W4387963302","https://openalex.org/W4390872247","https://openalex.org/W4402754111","https://openalex.org/W4402777371","https://openalex.org/W4402916263","https://openalex.org/W4403791248","https://openalex.org/W4404545718","https://openalex.org/W4409262798","https://openalex.org/W4409263041","https://openalex.org/W4411528087","https://openalex.org/W7133203876","https://openalex.org/W7160142824"],"related_works":[],"abstract_inverted_index":{"Diffusion":[0,85],"models":[1,19,55],"have":[2],"recently":[3],"advanced":[4],"human":[5],"motion":[6,28,53,63,102,113,165],"generation,":[7],"producing":[8],"realistic":[9],"and":[10,31,37,78,111,118,124,132,143,161],"diverse":[11],"animations":[12],"from":[13,129],"textual":[14,58],"prompts.":[15],"However,":[16],"adapting":[17],"these":[18],"to":[20,39],"unseen":[21],"actions":[22],"or":[23],"styles":[24],"typically":[25],"requires":[26],"additional":[27],"capture":[29],"data":[30],"full":[32],"retraining,":[33],"which":[34],"is":[35,157,168],"costly":[36],"difficult":[38],"scale.":[40],"We":[41,104],"propose":[42],"a":[43,69,75,158],"post-training":[44],"framework":[45],"based":[46],"on":[47,100,108,151,170],"Reinforcement":[48],"Learning":[49],"that":[50,136],"fine-tunes":[51],"pretrained":[52,70],"diffusion":[54,81,126],"using":[56,115],"only":[57],"prompts,":[59],"without":[60,98],"requiring":[61],"any":[62],"ground":[64],"truth.":[65],"Our":[66,155],"approach":[67,138,156],"employs":[68],"text\u2013motion":[71],"retrieval":[72],"network":[73],"as":[74],"reward":[76],"signal":[77],"optimizes":[79],"the":[80,90,95,116,141,152],"policy":[82],"with":[83],"Denoising":[84],"Policy":[86],"Optimization,":[87],"effectively":[88],"shifting":[89],"model\u2019s":[91],"generative":[92],"distribution":[93],"toward":[94],"target":[96],"domain":[97],"relying":[99],"paired":[101],"data.":[103],"evaluate":[105],"our":[106,137],"method":[107],"cross-dataset":[109],"adaptation":[110],"leave-one-out":[112],"experiments":[114],"HumanML3D":[117],"KIT-ML":[119],"datasets":[120],"across":[121],"both":[122],"latent-":[123],"joint-space":[125],"architectures.":[127],"Results":[128],"quantitative":[130],"metrics":[131],"user":[133],"studies":[134],"show":[135],"consistently":[139],"improves":[140],"quality":[142],"diversity":[144],"of":[145],"generated":[146],"motions,":[147],"while":[148],"preserving":[149],"performance":[150],"original":[153],"distribution.":[154],"flexible,":[159],"data-efficient,":[160],"privacy-preserving":[162],"solution":[163],"for":[164],"adaptation.":[166],"Code":[167],"available":[169],"GitHub":[171],"at":[172],"https://github.com/miccunifi/NoMoCapNeeded.":[173]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-06T00:00:00"}