{"id":"https://openalex.org/W7161030710","doi":"https://doi.org/10.48550/arxiv.2605.11931","title":"Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training","display_name":"Learn to Think: Improving Multimodal Reasoning through Vision-Aware Self-Improvement Training","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7161030710","doi":"https://doi.org/10.48550/arxiv.2605.11931"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.11931","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11931","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2605.11931","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053183023","display_name":"Qihuang Zhong","orcid":"https://orcid.org/0009-0001-0118-5217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Qihuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136079491","display_name":"Liang Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103145956","display_name":"Wenjie Xuan","orcid":"https://orcid.org/0000-0003-1579-2218"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuan, Wenjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136025011","display_name":"Juhua Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Juhua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136063006","display_name":"Bo Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136085817","display_name":"Dacheng Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Dacheng","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":0.8978000283241272,"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":0.8978000283241272,"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":0.014399999752640724,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.008899999782443047,"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/visual-reasoning","display_name":"Visual reasoning","score":0.6330999732017517},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5221999883651733},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4593999981880188},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.4352000057697296},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.4293999969959259},{"id":"https://openalex.org/keywords/opportunistic-reasoning","display_name":"Opportunistic reasoning","score":0.4284999966621399},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.390500009059906},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.359499990940094},{"id":"https://openalex.org/keywords/multimodal-learning","display_name":"Multimodal learning","score":0.3472999930381775},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.34599998593330383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7361000180244446},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6330999732017517},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5871000289916992},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5221999883651733},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4593999981880188},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4465000033378601},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.4352000057697296},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.4293999969959259},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.4284999966621399},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.390500009059906},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.359499990940094},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.34459999203681946},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.328900009393692},{"id":"https://openalex.org/C36964233","wikidata":"https://www.wikidata.org/wiki/Q7920942","display_name":"Verbal reasoning","level":3,"score":0.3260999917984009},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29809999465942383},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2971000075340271},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.29440000653266907},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.2651999890804291},{"id":"https://openalex.org/C107848011","wikidata":"https://www.wikidata.org/wiki/Q4680756","display_name":"Adaptive reasoning","level":4,"score":0.26499998569488525},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.2637999951839447}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.11931","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11931","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.11931","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11931","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6642795205116272,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Post-training":[0],"with":[1],"explicit":[2],"reasoning":[3,10,21,38,105,121,165],"traces":[4,22,39,122],"is":[5,23],"common":[6],"to":[7,36,116,134,150,175],"improve":[8],"the":[9,29,53,67,87,103,118,136,163],"capabilities":[11],"of":[12,56,106],"Multimodal":[13],"Large":[14],"Language":[15],"Models":[16],"(MLLMs).":[17],"However,":[18],"acquiring":[19],"high-quality":[20],"often":[24],"costly":[25],"and":[26,127,157,160,170],"time-consuming.":[27],"Hence,":[28],"self-improvement":[30,54,98],"paradigm":[31],"has":[32],"emerged,":[33],"enabling":[34],"MLLMs":[35,79,169],"self-generate":[37],"for":[40,101,123,180],"training":[41,55,99],"without":[42],"external":[43],"supervision.":[44],"Despite":[45],"its":[46],"effectiveness,":[47],"we":[48,93],"reveal":[49],"two":[50],"shortcomings":[51],"in":[52],"MLLMs:":[57],"1)":[58],"data":[59,125],"imbalance,":[60],"where":[61,78],"simple":[62],"samples":[63,71],"are":[64,72],"over-trained,":[65],"but":[66],"challenging":[68],"yet":[69],"crucial":[70],"under-trained;":[73],"2)":[74],"language":[75],"prior":[76],"bias,":[77],"overly":[80],"rely":[81],"on":[82,139],"linguistic":[83],"priors":[84],"while":[85],"neglecting":[86],"visual":[88,140],"cues.":[89],"To":[90],"this":[91],"end,":[92],"propose":[94],"VISTA,":[95],"a":[96,112,130],"vision-aware":[97,131],"framework":[100],"enhancing":[102],"multimodal":[104,164],"MLLMs.":[107],"Specifically,":[108],"VISTA":[109,146],"first":[110],"introduces":[111],"prefix":[113],"resampling":[114],"strategy":[115],"reuse":[117],"partial":[119],"correct":[120],"efficient":[124],"collection,":[126],"then":[128],"designs":[129],"attention":[132],"score":[133],"quantify":[135],"model's":[137],"focus":[138],"information.":[141],"Extensive":[142],"experiments":[143],"show":[144],"that":[145],"can":[147],"be":[148],"applied":[149],"various":[151,168],"post-training":[152],"scenarios,":[153],"i.e.,":[154],"supervised":[155],"fine-tuning":[156],"preference":[158],"learning,":[159],"effectively":[161],"enhances":[162],"performance":[166,178],"across":[167],"tasks,":[171],"e.g.,":[172],"bringing":[173],"up":[174],"+13.66%":[176],"average":[177],"gains":[179],"Qwen2.5-VL-3B-Instruct.":[181]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-14T00:00:00"}