{"id":"https://openalex.org/W7156927051","doi":"https://doi.org/10.48550/arxiv.2604.24339","title":"See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflection","display_name":"See Further, Think Deeper: Advancing VLM's Reasoning Ability with Low-level Visual Cues and Reflection","publication_year":2026,"publication_date":"2026-04-27","ids":{"openalex":"https://openalex.org/W7156927051","doi":"https://doi.org/10.48550/arxiv.2604.24339"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.24339","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24339","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.2604.24339","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134800570","display_name":"Zhiheng Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zhiheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134788939","display_name":"Tong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134799403","display_name":"Shuning Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shuning","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134805750","display_name":"Naiming Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Naiming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134763445","display_name":"Yumeng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yumeng","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":0.9940000176429749,"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":0.9940000176429749,"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":0.0008999999845400453,"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":0.0006000000284984708,"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/set","display_name":"Set (abstract data type)","score":0.609000027179718},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.5881999731063843},{"id":"https://openalex.org/keywords/sensory-cue","display_name":"Sensory cue","score":0.508400022983551},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.40869998931884766},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.3919000029563904},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.3695000112056732},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3666999936103821},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.34290000796318054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6973000168800354},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.609000027179718},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.5881999731063843},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.508400022983551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5047000050544739},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4571000039577484},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.40869998931884766},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3695000112056732},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.34290000796318054},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.3303999900817871},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C105842133","wikidata":"https://www.wikidata.org/wiki/Q1899679","display_name":"Visual communication","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C59732488","wikidata":"https://www.wikidata.org/wiki/Q2528440","display_name":"Visual analytics","level":3,"score":0.27619999647140503},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26030001044273376},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C2779916870","wikidata":"https://www.wikidata.org/wiki/Q14467155","display_name":"Gaze","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.24339","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24339","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.2604.24339","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.24339","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2],"Vision-Language":[3],"Models":[4],"(VLMs)":[5],"have":[6],"benefited":[7],"from":[8],"Reinforcement":[9],"Learning":[10],"(RL)":[11],"for":[12],"enhanced":[13],"reasoning.":[14],"However,":[15],"existing":[16],"methods":[17],"still":[18],"face":[19],"critical":[20],"limitations,":[21],"including":[22],"the":[23,79,83,102,106,130,135,140,143,158,165,173,180],"lack":[24],"of":[25,69,85,142],"low-level":[26,54,70],"visual":[27,31,55,62,71,76,87,92,99],"information":[28,77],"and":[29,57,111,126,152,177],"effective":[30,61],"feedback.":[32,63],"To":[33,138],"address":[34],"these":[35],"problems,":[36],"this":[37],"paper":[38],"proposes":[39],"a":[40,67,90,148],"unified":[41],"multimodal":[42],"interleaved":[43],"reasoning":[44,80],"framework":[45],"\\textbf{ForeSight},":[46],"which":[47],"enables":[48],"VLMs":[49],"to":[50,73,97,108,120],"\\textbf{See":[51],"Further}":[52],"with":[53,60,129,172],"cues":[56],"\\textbf{Think":[58],"Deeper}":[59],"First,":[64],"it":[65],"introduces":[66],"set":[68],"tools":[72],"integrate":[74],"essential":[75],"into":[78,101],"chain,":[81],"mitigating":[82],"neglect":[84],"fine-grained":[86],"features.":[88],"Second,":[89],"mask-based":[91],"feedback":[93],"mechanism":[94],"is":[95],"elaborated":[96],"incorporate":[98],"reflection":[100],"thinking":[103],"process,":[104],"enabling":[105],"model":[107,167],"dynamically":[109],"re-examine":[110],"update":[112],"its":[113],"answers.":[114],"Driven":[115],"by":[116],"RL,":[117],"ForeSight":[118],"learns":[119],"autonomously":[121],"decide":[122],"on":[123,157,185],"tool":[124],"invocation":[125],"answer":[127,132],"verification,":[128],"final":[131],"accuracy":[133],"as":[134],"reward":[136],"signal.":[137],"evaluate":[139],"performance":[141],"proposed":[144],"framework,":[145],"we":[146],"construct":[147],"new":[149],"dataset,":[150],"Character":[151],"Grounding":[153],"SalBench":[154,159],"(CG-SalBench),":[155],"based":[156],"dataset.":[160],"Experimental":[161],"results":[162],"demonstrate":[163],"that":[164],"ForeSight-7B":[166],"significantly":[168],"outperforms":[169],"other":[170],"models":[171,184],"same":[174],"parameter":[175],"scale,":[176],"even":[178],"surpasses":[179],"current":[181],"SOTA":[182],"closed-source":[183],"certain":[186],"metrics.":[187]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-29T00:00:00"}