{"id":"https://openalex.org/W7138237900","doi":"https://doi.org/10.1609/aaai.v40i14.38138","title":"Start Small, Think Big: Curriculum-based Relative Policy Optimization for Visual Grounding","display_name":"Start Small, Think Big: Curriculum-based Relative Policy Optimization for Visual Grounding","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138237900","doi":"https://doi.org/10.1609/aaai.v40i14.38138"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i14.38138","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38138","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38138/42100","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38138/42100","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129719934","display_name":"Qingyang Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Yan","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129691005","display_name":"Guangyao Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangyao Chen","raw_affiliation_strings":["Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129681083","display_name":"Yixiong Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yixiong Zou","raw_affiliation_strings":["Huazhong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huazhong University of Science and Technology","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"14","first_page":"11550","last_page":"11558"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9271000027656555,"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":0.9271000027656555,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.01899999938905239,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.00570000009611249,"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/intersection","display_name":"Intersection (aeronautics)","score":0.7491999864578247},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5730999708175659},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.48919999599456787},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42570000886917114},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3682999908924103},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.35910001397132874},{"id":"https://openalex.org/keywords/ground","display_name":"Ground","score":0.3546000123023987}],"concepts":[{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.7491999864578247},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6733999848365784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6456000208854675},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5730999708175659},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5034999847412109},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.48919999599456787},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3682999908924103},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2671999931335449}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i14.38138","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38138","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38138/42100","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"},{"id":"pmh:oai:ojs.aaai.org:article/38138","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/38138","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i14.38138","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i14.38138","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/38138/42100","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":[{"score":0.7014602422714233,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G1520791058","display_name":null,"funder_award_id":"62376103","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2878085913","display_name":null,"funder_award_id":"62206102","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4435229518","display_name":null,"funder_award_id":"62302184","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7449767353","display_name":null,"funder_award_id":"2024M750100","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"},{"id":"https://openalex.org/G8683302537","display_name":null,"funder_award_id":"2024BAA008","funder_id":"https://openalex.org/F4320336744","funder_display_name":"Science and Technology Program of Hubei Province"}],"funders":[{"id":"https://openalex.org/F4320318398","display_name":"Ant Group","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"},{"id":"https://openalex.org/F4320321883","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320336744","display_name":"Science and Technology Program of Hubei Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138237900.pdf","grobid_xml":"https://content.openalex.org/works/W7138237900.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Chain-of-Thought":[0],"(CoT)":[1],"prompting":[2],"has":[3],"recently":[4],"shown":[5],"significant":[6],"promise":[7],"across":[8],"various":[9],"NLP":[10],"and":[11,84,111,143,160],"computer":[12],"vision":[13],"tasks":[14,156],"by":[15,66,158],"explicitly":[16],"generating":[17],"intermediate":[18],"reasoning":[19,30],"steps.":[20],"However,":[21],"we":[22,69],"find":[23],"that":[24,51,80],"reinforcement":[25],"learning":[26,152],"(RL)-based":[27],"fine-tuned":[28],"CoT":[29,41,82],"can":[31],"paradoxically":[32],"degrade":[33],"performance":[34,59,148],"in":[35,150],"Visual":[36],"Grounding":[37],"tasks,":[38],"particularly":[39,154],"as":[40,91],"outputs":[42],"become":[43],"lengthy":[44],"or":[45],"complex.":[46],"Additionally,":[47],"our":[48,118],"analysis":[49],"reveals":[50],"increased":[52],"dataset":[53],"size":[54],"does":[55],"not":[56],"always":[57],"enhance":[58],"due":[60],"to":[61,94,101,133],"varying":[62],"data":[63,98],"complexities.":[64],"Motivated":[65],"these":[67],"findings,":[68],"propose":[70],"Curriculum-based":[71],"Relative":[72],"Policy":[73],"Optimization":[74],"(CuRPO),":[75],"a":[76,128],"novel":[77],"training":[78,97],"strategy":[79],"leverages":[81],"length":[83],"generalized":[85],"Intersection":[86],"over":[87],"Union":[88],"(gIoU)":[89],"rewards":[90],"complexity":[92],"indicators":[93],"progressively":[95],"structure":[96],"from":[99],"simpler":[100],"more":[102],"challenging":[103],"examples.":[104],"Extensive":[105],"experiments":[106],"on":[107,136],"RefCOCO,":[108],"RefCOCO+,":[109],"RefCOCOg,":[110],"LISA":[112],"datasets":[113],"demonstrate":[114],"the":[115],"effectiveness":[116],"of":[117,131],"approach.":[119],"CuRPO":[120,139],"consistently":[121],"outperforms":[122],"existing":[123],"methods,":[124],"including":[125],"Visual-RFT,":[126],"reaching":[127],"peak":[129],"improvement":[130],"up":[132],"15.49":[134],"mAP":[135],"RefCOCO.":[137],"Moreover,":[138],"exhibits":[140],"exceptional":[141],"efficiency":[142],"robustness,":[144],"delivering":[145],"strong":[146],"localization":[147],"even":[149],"few-shot":[151],"scenarios,":[153],"benefiting":[155],"characterized":[157],"ambiguous":[159],"intricate":[161],"textual":[162],"descriptions.":[163]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}