{"id":"https://openalex.org/W7161310561","doi":"https://doi.org/10.48550/arxiv.2605.14333","title":"InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation","display_name":"InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation","publication_year":2026,"publication_date":"2026-05-14","ids":{"openalex":"https://openalex.org/W7161310561","doi":"https://doi.org/10.48550/arxiv.2605.14333"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.14333","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14333","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.2605.14333","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121637713","display_name":"Yang Yue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090973869","display_name":"Fangyun Wei","orcid":"https://orcid.org/0000-0001-8784-4916"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Fangyun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136246452","display_name":"Tianyu He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Tianyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048138933","display_name":"Jinjing Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Jinjing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019968848","display_name":"Zanlin Ni","orcid":"https://orcid.org/0009-0006-6428-1456"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ni, Zanlin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136245601","display_name":"Zeyu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zeyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136244624","display_name":"Jiayi Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Jiayi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136199948","display_name":"Lei Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136226071","display_name":"Yue Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Yue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136192580","display_name":"Li Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136254821","display_name":"Ji Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136252085","display_name":"Gao Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136196927","display_name":"Dong Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Dong","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9135000109672546,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9135000109672546,"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/T11448","display_name":"Face recognition and analysis","score":0.0430000014603138,"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/T10481","display_name":"Computer Graphics and Visualization Techniques","score":0.004900000058114529,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/upsampling","display_name":"Upsampling","score":0.7559999823570251},{"id":"https://openalex.org/keywords/codebook","display_name":"Codebook","score":0.7149999737739563},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.5401999950408936},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.534500002861023},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.46140000224113464},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4584999978542328},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4113999903202057},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.40209999680519104},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.3894999921321869}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7936000227928162},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.7559999823570251},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.7149999737739563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6776000261306763},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.5401999950408936},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.534500002861023},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.46140000224113464},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4584999978542328},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45730000734329224},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4113999903202057},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.40209999680519104},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C205203396","wikidata":"https://www.wikidata.org/wiki/Q612143","display_name":"Bilinear interpolation","level":2,"score":0.3797999918460846},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3767000138759613},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.34470000863075256},{"id":"https://openalex.org/C142816647","wikidata":"https://www.wikidata.org/wiki/Q5573018","display_name":"Glyph (data visualization)","level":3,"score":0.34130001068115234},{"id":"https://openalex.org/C2779332521","wikidata":"https://www.wikidata.org/wiki/Q1820694","display_name":"Legibility","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C19743564","wikidata":"https://www.wikidata.org/wiki/Q25378119","display_name":"Flicker","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.31150001287460327},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27549999952316284},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2630999982357025},{"id":"https://openalex.org/C4641261","wikidata":"https://www.wikidata.org/wiki/Q11681085","display_name":"Face detection","level":4,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.14333","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14333","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.2605.14333","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.14333","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Text":[0],"and":[1,9,35,47,65,97,110,122,145],"faces":[2],"are":[3],"among":[4],"the":[5,31,39,154],"most":[6],"perceptually":[7],"salient":[8],"practically":[10],"important":[11],"patterns":[12],"in":[13,120,138,159],"visual":[14,91],"generation,":[15],"yet":[16,88],"they":[17],"remain":[18],"challenging":[19],"for":[20,162],"autoregressive":[21,135],"generators":[22],"built":[23],"on":[24],"discrete":[25,90,164],"tokenization.":[26],"A":[27],"central":[28],"bottleneck":[29],"is":[30],"tokenizer:":[32],"aggressive":[33],"downsampling":[34,113],"quantization":[36],"often":[37],"discard":[38],"fine-grained":[40],"structures":[41],"needed":[42],"to":[43,55,134],"preserve":[44],"readable":[45],"glyphs":[46],"distinctive":[48],"facial":[49,66,148],"features.":[50],"We":[51],"attribute":[52],"this":[53],"gap":[54],"standard":[56],"discrete-tokenizer":[57],"objectives":[58,70],"being":[59],"weakly":[60],"aligned":[61],"with":[62,142],"text":[63,96,121,144],"legibility":[64],"fidelity,":[67],"as":[68],"these":[69],"typically":[71],"optimize":[72],"generic":[73],"reconstruction":[74,124,128],"while":[75],"compressing":[76],"diverse":[77],"content":[78],"uniformly.":[79],"To":[80],"address":[81],"this,":[82],"we":[83],"propose":[84],"InsightTok,":[85],"a":[86,106,111],"simple":[87],"effective":[89],"tokenization":[92],"framework":[93],"that":[94],"enhances":[95],"face":[98,123],"fidelity":[99],"through":[100],"localized,":[101],"content-aware":[102],"perceptual":[103],"losses.":[104],"With":[105],"compact":[107],"16k":[108],"codebook":[109],"16x":[112],"rate,":[114],"InsightTok":[115],"significantly":[116],"outperforms":[117],"prior":[118],"tokenizers":[119],"without":[125],"compromising":[126],"general":[127],"quality.":[129],"These":[130],"gains":[131],"consistently":[132],"transfer":[133],"image":[136,165],"generation":[137],"InsightAR,":[139],"producing":[140],"images":[141],"clearer":[143],"more":[146],"faithful":[147],"details.":[149],"Overall,":[150],"our":[151],"results":[152],"highlight":[153],"potential":[155],"of":[156],"specialized":[157],"supervision":[158],"tokenizer":[160],"training":[161],"advancing":[163],"generation.":[166]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-16T00:00:00"}