{"id":"https://openalex.org/W7164938486","doi":"https://doi.org/10.48550/arxiv.2606.15920","title":"OmniOPSD: Rationale-Privileged On-Policy Self-Distillation for Affective Computing","display_name":"OmniOPSD: Rationale-Privileged On-Policy Self-Distillation for Affective Computing","publication_year":2026,"publication_date":"2026-06-14","ids":{"openalex":"https://openalex.org/W7164938486","doi":"https://doi.org/10.48550/arxiv.2606.15920"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.15920","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15920","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.15920","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138732188","display_name":"Zebang Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Zebang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138715205","display_name":"Shuimu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Shuimu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124108288","display_name":"Boxue Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Boxue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072679873","display_name":"Yuanshen Guan","orcid":"https://orcid.org/0000-0003-3468-1417"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan, Yuanshen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122991705","display_name":"Jingyi Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jingyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138729908","display_name":"Zheng Lian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lian, Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138703393","display_name":"Xiaojiang Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Xiaojiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138753542","display_name":"Fei Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138698442","display_name":"LaiZhong Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, LaiZhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138754381","display_name":"Qi Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Qi","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":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5813999772071838,"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":0.5813999772071838,"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/T10028","display_name":"Topic Modeling","score":0.16539999842643738,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.05400000140070915,"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/inference","display_name":"Inference","score":0.5964000225067139},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.5733000040054321},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5220999717712402},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5181999802589417},{"id":"https://openalex.org/keywords/imitation","display_name":"Imitation","score":0.48249998688697815},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.48249998688697815}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7197999954223633},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5964000225067139},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5819000005722046},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.5733000040054321},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5181999802589417},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.48249998688697815},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.48249998688697815},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.4309000074863434},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.40639999508857727},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.39719998836517334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39469999074935913},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3409000039100647},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2567000091075897},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.15920","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15920","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.15920","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.15920","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6292420029640198}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,69],"for":[2,63,77,117],"multimodal":[3,35,53,71,130],"large":[4],"language":[5],"models":[6],"(MLLMs)":[7],"is":[8,21],"often":[9],"hindered":[10],"by":[11],"severe":[12],"reward":[13],"sparsity":[14],"in":[15,24,70],"complex":[16],"reasoning":[17],"tasks.":[18],"This":[19],"challenge":[20],"particularly":[22],"pronounced":[23],"human-centered":[25],"scenarios":[26],"involving":[27],"states,":[28],"emotions,":[29],"intentions,":[30],"and":[31,37,47,73,140,159,186],"behaviors,":[32],"where":[33],"heterogeneous":[34],"signals":[36],"subjective":[38],"human":[39],"factors":[40],"make":[41],"high-quality":[42],"chain-of-thought":[43],"(CoT)":[44],"annotations":[45],"expensive":[46],"difficult":[48],"to":[49],"obtain.":[50],"Although":[51],"many":[52],"datasets":[54],"provide":[55],"expert-annotated":[56],"ground-truth":[57],"labels,":[58,163],"directly":[59,155],"using":[60],"these":[61,83],"labels":[62],"supervised":[64],"fine-tuning":[65],"may":[66],"encourage":[67],"shortcut":[68],"perception":[72],"provides":[74,141],"limited":[75],"transparency":[76],"safety-critical":[78],"human--AI":[79],"interaction.":[80],"To":[81],"address":[82],"limitations,":[84],"we":[85],"propose":[86],"OmniOPSD,":[87],"a":[88,118],"Rationale-Privileged":[89],"On-Policy":[90],"Self-Distillation":[91],"framework":[92],"that":[93,175],"uses":[94,107],"frontier-generated":[95,108],"rationales":[96,110],"as":[97,112],"teacher-side":[98],"privileged":[99,114],"evidence":[100,115],"rather":[101],"than":[102],"student":[103,122,147],"imitation":[104],"targets.":[105],"OmniOPSD":[106,176],"evidence-aware":[109],"only":[111],"training-time":[113],"context":[116],"local":[119],"teacher.":[120],"The":[121],"samples":[123],"its":[124,150],"own":[125,151],"rollout":[126],"from":[127],"the":[128,133,137,146,190],"original":[129],"input,":[131],"while":[132],"rationale-privileged":[134,193],"teacher":[135,194],"scores":[136],"same":[138],"tokens":[139],"dense":[142],"token-level":[143],"supervision.":[144],"Thus,":[145],"learns":[148],"on":[149,172],"trajectory":[152],"distribution":[153],"without":[154],"imitating":[156],"frontier-model":[157],"completions,":[158],"inference":[160],"requires":[161],"no":[162],"rationales,":[164],"CoT":[165],"annotations,":[166],"or":[167],"closed-source":[168],"model":[169],"access.":[170],"Experiments":[171],"MER-UniBench":[173],"show":[174],"achieves":[177],"state-of-the-art":[178],"performance":[179],"with":[180],"an":[181],"average":[182],"score":[183],"of":[184,192],"$84.19$,":[185],"ablations":[187],"further":[188],"support":[189],"value":[191],"guidance.":[195]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-17T00:00:00"}