{"id":"https://openalex.org/W7161948793","doi":"https://doi.org/10.48550/arxiv.2605.20914","title":"RISE: Reliable Improvement in Self-Evolving Vision-Language Models","display_name":"RISE: Reliable Improvement in Self-Evolving Vision-Language Models","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7161948793","doi":"https://doi.org/10.48550/arxiv.2605.20914"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.20914","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20914","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.2605.20914","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124957590","display_name":"Chaoran Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Chaoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101231610","display_name":"Yingmao Miao","orcid":"https://orcid.org/0000-0003-3483-2385"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miao, Yingmao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136616749","display_name":"Pengfei Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Pengfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112233442","display_name":"Hao Dou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dou, Hao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136630854","display_name":"Lei Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136684156","display_name":"Xiangxiang Chu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chu, Xiangxiang","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":0.9617000222206116,"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":0.9617000222206116,"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":0.010900000110268593,"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/T10028","display_name":"Topic Modeling","score":0.00989999994635582,"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/solver","display_name":"Solver","score":0.7505999803543091},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.6187999844551086},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.506600022315979},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4767000079154968},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4620000123977661},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.37689998745918274},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.3628999888896942}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.754800021648407},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.7505999803543091},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6187999844551086},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.506600022315979},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4620000123977661},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41449999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.414000004529953},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37689998745918274},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C164155591","wikidata":"https://www.wikidata.org/wiki/Q2067766","display_name":"Satisfiability modulo theories","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.3239000141620636},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C186886427","wikidata":"https://www.wikidata.org/wiki/Q5441213","display_name":"Feedback loop","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.26420000195503235},{"id":"https://openalex.org/C3019612716","wikidata":"https://www.wikidata.org/wiki/Q730920","display_name":"Problem solver","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.20914","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20914","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.2605.20914","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20914","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.64906907081604}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"(VLMs)":[2],"have":[3],"achieved":[4],"strong":[5],"multimodal":[6,31],"reasoning":[7],"capabilities,":[8],"but":[9],"further":[10],"improving":[11],"them":[12],"still":[13,77],"relies":[14],"heavily":[15],"on":[16,133,192],"large-scale":[17],"human-constructed":[18],"supervision":[19,23],"for":[20,29,127],"post-training.":[21],"Such":[22],"is":[24,131,214],"costly":[25],"to":[26,66,151],"obtain,":[27],"especially":[28],"reasoning-intensive":[30],"tasks":[32],"where":[33,47],"questions,":[34],"answers,":[35],"and":[36,62,91,101,115,148,161,164,172,185,209],"feedback":[37,143],"signals":[38],"must":[39],"be":[40],"carefully":[41],"designed.":[42],"This":[43],"motivates":[44],"self-evolving":[45,75,125],"learning,":[46],"a":[48,53,57,63,107,123,154],"model":[49],"improves":[50,158,203],"itself":[51],"through":[52],"dual-role":[54],"closed":[55],"loop:":[56],"questioner":[58,147],"autonomously":[59],"poses":[60],"questions":[61,95],"solver":[64,92,150],"learns":[65],"solve":[67],"them.":[68],"However,":[69],"we":[70,120],"observe":[71],"that":[72,200],"current":[73],"VLM":[74,194],"methods":[76],"face":[78],"three":[79,134],"major":[80],"challenges:":[81],"coarse-grained":[82],"role":[83,138],"alternation":[84],"delays":[85],"the":[86,113,142,146,149,204],"interaction":[87],"between":[88,145],"question":[89,102,159],"generation":[90],"adaptation;":[93],"generated":[94],"can":[96],"progressively":[97],"degrade":[98],"in":[99],"quality;":[100],"types":[103],"may":[104],"collapse":[105,171],"toward":[106],"narrow":[108],"distribution.":[109],"These":[110],"issues":[111],"limit":[112],"efficiency":[114],"reliability":[116],"of":[117],"self-evolution.":[118],"Thus,":[119],"propose":[121],"\\textbf{RISE},":[122],"reliable":[124,184],"framework":[126],"vision-language":[128],"models.":[129],"RISE":[130,201],"built":[132],"complementary":[135],"designs:":[136],"fine-grained":[137],"alternation,":[139],"which":[140,157,168],"shortens":[141],"loop":[144],"improve":[152],"efficiency;":[153],"quality":[155],"supervisor,":[156],"validity":[160],"pseudo-label":[162],"reliability;":[163],"skill-aware":[165],"dynamic":[166],"balancing,":[167],"mitigates":[169],"mode":[170],"maintains":[173],"broad":[174,208],"skill":[175],"coverage":[176],"during":[177],"evolution.":[178],"Together,":[179],"these":[180],"components":[181],"enable":[182],"more":[183],"effective":[186],"self-evolution":[187],"from":[188],"unlabeled":[189],"images.":[190],"Experiments":[191],"two":[193],"backbones":[195],"across":[196],"seven":[197],"benchmarks":[198],"show":[199],"consistently":[202],"base":[205],"models,":[206],"yielding":[207],"sustained":[210],"gains.":[211],"Our":[212],"code":[213],"publicly":[215],"available":[216],"at":[217],"https://github.com/AMAP-ML/RISE.":[218]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-22T00:00:00"}