{"id":"https://openalex.org/W7128681275","doi":"https://doi.org/10.48550/arxiv.2602.10619","title":"Improving Medical Visual Reinforcement Fine-Tuning via Perception and Reasoning Augmentation","display_name":"Improving Medical Visual Reinforcement Fine-Tuning via Perception and Reasoning Augmentation","publication_year":2026,"publication_date":"2026-02-11","ids":{"openalex":"https://openalex.org/W7128681275","doi":"https://doi.org/10.48550/arxiv.2602.10619"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.10619","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5125716380","display_name":"Guangjing Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Guangjing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039325478","display_name":"Zi-Fa Yu","orcid":"https://orcid.org/0000-0001-5012-0148"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, ZhangYuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125684680","display_name":"Ziyuan Qin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Ziyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125724901","display_name":"Xinyuan Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Xinyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060429045","display_name":"Huahui Yi","orcid":"https://orcid.org/0009-0007-9361-5491"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi, Huahui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057396396","display_name":"Qingbo Kang","orcid":"https://orcid.org/0000-0002-4919-5246"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Qingbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125752351","display_name":"Jun Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Jun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019309609","display_name":"Yiyue Li","orcid":"https://orcid.org/0000-0001-5435-1699"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yiyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113562685","display_name":"Chenlin Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Chenlin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033156313","display_name":"Lao Qicheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lao, Qicheng","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":0.9136000275611877,"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":0.9136000275611877,"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":0.0333000011742115,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.007899999618530273,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.6883999705314636},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.652999997138977},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6306999921798706},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.40389999747276306},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.32989999651908875},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.31150001287460327}],"concepts":[{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.6883999705314636},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.652999997138977},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6306999921798706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.580299973487854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47870001196861267},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.40389999747276306},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35429999232292175},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.33079999685287476},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3305000066757202},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2581999897956848}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.10619","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.10619","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.10619","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":"pmh:doi:10.48550/arxiv.2602.10619","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"recent":[1],"advances":[2],"in":[3,35],"Reinforcement":[4],"Fine-Tuning":[5],"(RFT)":[6],"have":[7],"shown":[8],"that":[9,119,141],"rule-based":[10],"reward":[11,94],"schemes":[12],"can":[13,142],"enable":[14],"effective":[15,41],"post-training":[16],"for":[17,67,160,169],"large":[18],"language":[19],"models,":[20],"their":[21],"extension":[22],"to":[23,79,103,145,164],"cross-modal,":[24],"vision-centric":[25],"domains":[26],"remains":[27],"largely":[28],"underexplored.":[29],"This":[30],"limitation":[31],"is":[32],"especially":[33],"pronounced":[34],"the":[36,68,107,161],"medical":[37,69,115,147,171],"imaging":[38],"domain,":[39],"where":[40],"performance":[42],"requires":[43],"both":[44,81,124],"robust":[45],"visual":[46,62],"perception":[47,82],"and":[48,83,96,105,128,137,157],"structured":[49],"reasoning.":[50],"In":[51],"this":[52,56,152],"work,":[53],"we":[54,117,132],"address":[55],"gap":[57],"by":[58],"proposing":[59],"VRFT-Aug,":[60],"a":[61,73],"reinforcement":[63],"fine-tuning":[64,127],"framework":[65],"tailored":[66],"domain.":[70],"VRFT-Aug":[71],"introduces":[72],"series":[74],"of":[75],"training":[76,139],"strategies":[77],"designed":[78],"augment":[80],"reasoning,":[84],"including":[85],"prior":[86],"knowledge":[87],"injection,":[88],"perception-driven":[89],"policy":[90],"refinement,":[91],"medically":[92],"informed":[93],"shaping,":[95],"behavioral":[97],"imitation.":[98],"Together,":[99],"these":[100],"methods":[101],"aim":[102],"stabilize":[104],"improve":[106],"RFT":[108,129],"process.":[109],"Through":[110],"extensive":[111],"experiments":[112],"across":[113],"multiple":[114],"datasets,":[116],"show":[118],"our":[120],"approaches":[121],"consistently":[122],"outperform":[123],"standard":[125],"supervised":[126],"baselines.":[130],"Moreover,":[131],"provide":[133],"empirically":[134],"grounded":[135],"insights":[136],"practical":[138],"heuristics":[140],"be":[143],"generalized":[144],"other":[146],"image":[148],"tasks.":[149],"We":[150],"hope":[151],"work":[153],"contributes":[154],"actionable":[155],"guidance":[156],"fresh":[158],"inspiration":[159],"ongoing":[162],"effort":[163],"develop":[165],"reliable,":[166],"reasoning-capable":[167],"models":[168],"high-stakes":[170],"applications.":[172]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-02-13T00:00:00"}