{"id":"https://openalex.org/W7126022698","doi":"https://doi.org/10.48550/arxiv.2601.20742","title":"Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification","display_name":"Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification","publication_year":2026,"publication_date":"2026-01-28","ids":{"openalex":"https://openalex.org/W7126022698","doi":"https://doi.org/10.48550/arxiv.2601.20742"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.20742","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.20742","pdf_url":"https://arxiv.org/pdf/2601.20742","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.20742","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124277479","display_name":"Xin Jin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4394709157","display_name":"Eastern Institute of Technology, Ningbo","ror":"https://ror.org/036mbz113","country_code":"CN","type":"education","lineage":["https://openalex.org/I4394709157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin, Xin","raw_affiliation_strings":["Eastern Institute of Technology , Ningbo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology , Ningbo","institution_ids":["https://openalex.org/I4394709157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122982915","display_name":"Jinming Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4394709157","display_name":"Eastern Institute of Technology, Ningbo","ror":"https://ror.org/036mbz113","country_code":"CN","type":"education","lineage":["https://openalex.org/I4394709157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Jinming","raw_affiliation_strings":["Eastern Institute of Technology , Ningbo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology , Ningbo","institution_ids":["https://openalex.org/I4394709157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124199855","display_name":"Yuntao Wei","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4394709157","display_name":"Eastern Institute of Technology, Ningbo","ror":"https://ror.org/036mbz113","country_code":"CN","type":"education","lineage":["https://openalex.org/I4394709157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei, Yuntao","raw_affiliation_strings":["Eastern Institute of Technology , Ningbo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology , Ningbo","institution_ids":["https://openalex.org/I4394709157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049747474","display_name":"Junyan Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4394709157","display_name":"Eastern Institute of Technology, Ningbo","ror":"https://ror.org/036mbz113","country_code":"CN","type":"education","lineage":["https://openalex.org/I4394709157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin, Junyan","raw_affiliation_strings":["Eastern Institute of Technology , Ningbo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology , Ningbo","institution_ids":["https://openalex.org/I4394709157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124295126","display_name":"Zhicheng Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4394709157","display_name":"Eastern Institute of Technology, Ningbo","ror":"https://ror.org/036mbz113","country_code":"CN","type":"education","lineage":["https://openalex.org/I4394709157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Zhicheng","raw_affiliation_strings":["Eastern Institute of Technology , Ningbo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology , Ningbo","institution_ids":["https://openalex.org/I4394709157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100651268","display_name":"Jianguo Huang","orcid":"https://orcid.org/0000-0003-0825-3056","observed_orcids":["https://orcid.org/0000-0003-0825-3056"]},"institutions":[{"id":"https://openalex.org/I4394709157","display_name":"Eastern Institute of Technology, Ningbo","ror":"https://ror.org/036mbz113","country_code":"CN","type":"education","lineage":["https://openalex.org/I4394709157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Jianguo","raw_affiliation_strings":["Eastern Institute of Technology , Ningbo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology , Ningbo","institution_ids":["https://openalex.org/I4394709157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126459759","display_name":"Xudong Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4394709157","display_name":"Eastern Institute of Technology, Ningbo","ror":"https://ror.org/036mbz113","country_code":"CN","type":"education","lineage":["https://openalex.org/I4394709157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Xudong","raw_affiliation_strings":["Eastern Institute of Technology , Ningbo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology , Ningbo","institution_ids":["https://openalex.org/I4394709157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124195559","display_name":"Yanxiao Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4394709157","display_name":"Eastern Institute of Technology, Ningbo","ror":"https://ror.org/036mbz113","country_code":"CN","type":"education","lineage":["https://openalex.org/I4394709157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Yanxiao","raw_affiliation_strings":["Eastern Institute of Technology , Ningbo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology , Ningbo","institution_ids":["https://openalex.org/I4394709157"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124287967","display_name":"Wenjun Zeng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4394709157","display_name":"Eastern Institute of Technology, Ningbo","ror":"https://ror.org/036mbz113","country_code":"CN","type":"education","lineage":["https://openalex.org/I4394709157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zeng, Wenjun","raw_affiliation_strings":["Eastern Institute of Technology , Ningbo"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Eastern Institute of Technology , Ningbo","institution_ids":["https://openalex.org/I4394709157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4394709157"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.4934000074863434,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.4934000074863434,"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/T10741","display_name":"Video Coding and Compression Technologies","score":0.42750000953674316,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.03009999915957451,"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/visual-coding","display_name":"visual coding","score":0.9359999895095825},{"id":"https://openalex.org/keywords/image-compression","display_name":"image compression","score":0.43799999356269836},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.8360000252723694},{"id":"https://openalex.org/keywords/compression-efficiency","display_name":"compression efficiency","score":0.46700000762939453},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.6050000190734863},{"id":"https://openalex.org/keywords/semantic-fidelity","display_name":"semantic fidelity","score":0.5950000286102295},{"id":"https://openalex.org/keywords/unified-formulation","display_name":"unified formulation","score":0.6359999775886536},{"id":"https://openalex.org/keywords/ai-generated-content","display_name":"AI-generated content","score":0.703000009059906},{"id":"https://openalex.org/keywords/embodied-ai","display_name":"embodied AI","score":0.9070000052452087},{"id":"https://openalex.org/keywords/tokenization","display_name":"tokenization","score":0.4620000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591999769210815},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7317000031471252},{"id":"https://openalex.org/C96146094","wikidata":"https://www.wikidata.org/wiki/Q609057","display_name":"Unification","level":2,"score":0.5328999757766724},{"id":"https://openalex.org/C161765866","wikidata":"https://www.wikidata.org/wiki/Q184748","display_name":"Codec","level":2,"score":0.5142999887466431},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5109999775886536},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.49889999628067017},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.49720001220703125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4336000084877014},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33899998664855957},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.33070001006126404},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.30230000615119934},{"id":"https://openalex.org/C2780330621","wikidata":"https://www.wikidata.org/wiki/Q7936609","display_name":"Visual modeling","level":4,"score":0.3009999990463257},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2662999927997589},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C2778061373","wikidata":"https://www.wikidata.org/wiki/Q1315146","display_name":"Predictive coding","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2558000087738037},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.20742","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.20742","pdf_url":"https://arxiv.org/pdf/2601.20742","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,"listed_in":[],"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.2601.20742","doi":"https://doi.org/10.48550/arxiv.2601.20742","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.20742","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.20742","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.20742","pdf_url":"https://arxiv.org/pdf/2601.20742","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,"listed_in":[],"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":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3527258163","display_name":null,"funder_award_id":"62302246","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126022698.pdf","grobid_xml":"https://content.openalex.org/works/W7126022698.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6967210562","https://openalex.org/W4416348134","https://openalex.org/W4415955360","https://openalex.org/W4414991888","https://openalex.org/W4416873702","https://openalex.org/W7155043590","https://openalex.org/W7204765602","https://openalex.org/W4404652925","https://openalex.org/W7155068464","https://openalex.org/W4416375271"],"abstract_inverted_index":{"\"Compression":[0],"Tells":[1],"Intelligence\",":[2],"is":[3],"supported":[4],"by":[5],"research":[6],"in":[7,52,175,221],"artificial":[8],"intelligence,":[9],"particularly":[10],"concerning":[11],"(multimodal)":[12],"large":[13,67,168],"language":[14],"models":[15,68],"(LLMs/MLLMs),":[16],"where":[17],"compression":[18,125],"efficiency":[19,126,213],"often":[20],"correlates":[21],"with":[22,45,211],"improved":[23],"model":[24,128],"performance":[25,129],"and":[26,106,127,151,157,187,224],"capabilities.":[27],"For":[28],"compression,":[29],"classical":[30],"visual":[31,76,140,155],"coding":[32,141],"based":[33,133],"on":[34,134,195],"traditional":[35,207],"information":[36,80],"theory":[37],"has":[38],"developed":[39],"over":[40],"decades,":[41],"achieving":[42],"great":[43],"success":[44],"numerous":[46],"international":[47],"industrial":[48],"standards":[49],"widely":[50],"applied":[51],"multimedia":[53],"(e.g.,":[54,209],"image/video)":[55],"systems.":[56],"Except":[57],"that,":[58],"the":[59,83,117,122,135,153,171,176,196,206],"recent":[60],"emergingvisual":[61],"token":[62,143,158,173,203],"technology":[63,204],"of":[64,97,119,124,149,170,199,218],"generative":[65],"multi-modal":[66],"also":[69],"shares":[70],"a":[71,94,167,201,215,222],"similar":[72],"fundamental":[73],"objective":[74],"like":[75,180,205],"coding:":[77],"maximizing":[78],"semantic":[79],"fidelity":[81],"during":[82],"representation":[84],"learning":[85],"while":[86],"minimizing":[87],"computational":[88],"cost.":[89],"Therefore,":[90],"this":[91],"paper":[92],"provides":[93],"comprehensive":[95],"overview":[96],"two":[98],"dominant":[99],"technique":[100],"families":[101],"first":[102],"--":[103,110],"Visual":[104],"Coding":[105],"Vision":[107],"Token":[108],"Technology":[109],"then":[111],"we":[112,145,164],"further":[113],"unify":[114],"them":[115],"from":[116],"aspect":[118],"optimization,":[120],"discussing":[121],"essence":[123],"trade-off":[130],"behind.":[131],"Next,":[132],"proposed":[136],"unified":[137,223],"formulation":[138],"bridging":[139],"andvisual":[142],"technology,":[144],"synthesize":[146],"bidirectional":[147],"insights":[148],"themselves":[150],"forecast":[152],"next-gen":[154],"codec":[156],"techniques.":[159],"Last":[160],"but":[161],"not":[162],"least,":[163],"experimentally":[165],"show":[166],"potential":[169],"task-oriented":[172],"developments":[174],"more":[177],"practical":[178],"tasks":[179,220],"multimodal":[181],"LLMs":[182],"(MLLMs),":[183],"AI-generated":[184],"content":[185],"(AIGC),":[186],"embodied":[188],"AI,":[189],"as":[190,192],"well":[191],"shedding":[193],"light":[194],"future":[197],"possibility":[198],"standardizing":[200],"general":[202],"codecs":[208],"H.264/265)":[210],"high":[212],"for":[214],"wide":[216],"range":[217],"intelligent":[219],"effective":[225],"manner.":[226]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-01-30T00:00:00"}