{"id":"https://openalex.org/W4416975494","doi":"https://doi.org/10.48550/arxiv.2511.22172","title":"Guiding the Inner Eye: A Framework for Hierarchical and Flexible Visual Grounded Reasoning","display_name":"Guiding the Inner Eye: A Framework for Hierarchical and Flexible Visual Grounded Reasoning","publication_year":2025,"publication_date":"2025-11-27","ids":{"openalex":"https://openalex.org/W4416975494","doi":"https://doi.org/10.48550/arxiv.2511.22172"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2511.22172","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.22172","pdf_url":"https://arxiv.org/pdf/2511.22172","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2511.22172","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wei, Zhaoyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Zhaoyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102769588","display_name":"Wenchao Ding","orcid":"https://orcid.org/0000-0003-4249-526X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Wenchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031281125","display_name":"Yanchao Hao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao, Yanchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5084907332","display_name":"Xi Chen","orcid":"https://orcid.org/0000-0002-8344-180X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Xi","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":0.9710000157356262,"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":0.9710000157356262,"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/T11605","display_name":"Visual Attention and Saliency Detection","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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0019000000320374966,"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":0.5719000101089478},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5694000124931335},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.519599974155426},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.51419997215271},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4950000047683716},{"id":"https://openalex.org/keywords/cognitive-architecture","display_name":"Cognitive architecture","score":0.4244000017642975},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.42410001158714294},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.36079999804496765},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.3447999954223633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7152000069618225},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5719000101089478},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5694000124931335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5612999796867371},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.519599974155426},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.51419997215271},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4950000047683716},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.4293999969959259},{"id":"https://openalex.org/C20854674","wikidata":"https://www.wikidata.org/wiki/Q4386060","display_name":"Cognitive architecture","level":3,"score":0.4244000017642975},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.42410001158714294},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39969998598098755},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.36079999804496765},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3197000026702881},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C2776035091","wikidata":"https://www.wikidata.org/wiki/Q7928819","display_name":"Viewpoints","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.2969000041484833},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.287200003862381},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2689000070095062},{"id":"https://openalex.org/C160343418","wikidata":"https://www.wikidata.org/wiki/Q185256","display_name":"Rigidity (electromagnetism)","level":2,"score":0.26809999346733093},{"id":"https://openalex.org/C161407221","wikidata":"https://www.wikidata.org/wiki/Q4382939","display_name":"Cognitive model","level":3,"score":0.26510000228881836},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2511.22172","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.22172","pdf_url":"https://arxiv.org/pdf/2511.22172","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.22172","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.22172","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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:oai:arXiv.org:2511.22172","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.22172","pdf_url":"https://arxiv.org/pdf/2511.22172","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Models":[0],"capable":[1],"of":[2,37,45,128,217],"\"thinking":[3],"with":[4,29,199],"images\"":[5],"by":[6,92,143],"dynamically":[7],"grounding":[8],"their":[9],"reasoning":[10,91,149],"in":[11,18,105,183],"visual":[12,89,185],"evidence":[13],"represent":[14],"a":[15,79,116,136],"major":[16],"leap":[17],"multimodal":[19,218],"AI.":[20],"However,":[21],"replicating":[22],"and":[23,42,77,87,99,134,177,195,206],"advancing":[24],"this":[25,70],"ability":[26],"is":[27,210],"non-trivial,":[28],"current":[30],"methods":[31],"often":[32],"trapped":[33],"between":[34],"the":[35,43,60,95,122,126,153,173,214],"instability":[36],"end-to-end":[38],"reinforcement":[39],"learning":[40],"(RL)":[41],"rigidity":[44],"supervised":[46],"fine-tuning":[47],"(SFT).":[48],"This":[49],"leads":[50],"to":[51,56,124,204,208],"models":[52,171,198],"that":[53,84,120,139,190],"either":[54],"struggle":[55],"learn":[57],"or":[58],"lack":[59],"cognitive":[61,141],"flexibility":[62,142],"required":[63],"for":[64,202,212],"complex,":[65],"real-world":[66],"scenes.":[67],"To":[68],"navigate":[69],"dilemma,":[71],"we":[72],"introduce":[73],"GRiP":[74,156],"(Guided":[75],"Reasoning":[76],"Perception),":[78],"novel":[80],"two-stage":[81],"training":[82],"framework":[83],"cultivates":[85],"robust":[86],"flexible":[88],"grounded":[90],"explicitly":[93],"guiding":[94,197],"model's":[96],"perceptual":[97],"focus":[98],"logical":[100],"pathways.":[101,150],"GRiP's":[102],"core":[103],"lies":[104],"its":[106,181],"cognitive-enhanced":[107],"RL":[108],"stage,":[109],"which":[110],"features":[111],"two":[112],"key":[113],"innovations:":[114],"(1)":[115],"Salience-Weighted":[117],"IoU":[118],"Reward":[119,138],"incentivizes":[121],"model":[123],"prioritize":[125],"localization":[127],"mission-critical":[129],"objects":[130],"over":[131],"trivial":[132],"distractors,":[133],"(2)":[135],"Multi-Heuristic":[137],"encourages":[140],"rewarding":[144],"diverse":[145],"yet":[146],"logically":[147],"valid":[148],"Initialized":[151],"from":[152],"Qwen2.5-VL-7B":[154],"model,":[155],"demonstrates":[157,189],"significant":[158],"performance":[159],"gains":[160],"across":[161],"multiple":[162],"challenging":[163,175],"benchmarks.":[164],"It":[165],"achieves":[166],"state-of-the-art":[167],"results":[168],"among":[169],"open-source":[170],"on":[172],"highly":[174],"TreeBench":[176],"V*":[178],"Bench,":[179],"proving":[180],"effectiveness":[182],"complex":[184],"reasoning.":[186],"Our":[187],"work":[188],"moving":[191],"beyond":[192],"simplistic":[193],"rewards":[194],"instead":[196],"cognitively-inspired":[200],"signals":[201],"what":[203],"see":[205],"how":[207],"think":[209],"crucial":[211],"unlocking":[213],"next":[215],"level":[216],"intelligence.":[219],"The":[220],"code":[221],"will":[222],"be":[223],"made":[224],"publicly":[225],"available.":[226]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-12-03T00:00:00"}