{"id":"https://openalex.org/W4416099320","doi":"https://doi.org/10.1109/iccv51701.2025.01648","title":"Harmonizing Visual Representations for Unified Multimodal Understanding and Generation","display_name":"Harmonizing Visual Representations for Unified Multimodal Understanding and Generation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416099320","doi":"https://doi.org/10.1109/iccv51701.2025.01648"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.21979","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101236497","display_name":"Size Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Size Wu","raw_affiliation_strings":["Nanyang Technological University,S-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,S-Lab","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709484","display_name":"Wenwei Zhang","orcid":"https://orcid.org/0000-0002-2748-4514"},"institutions":[{"id":"https://openalex.org/I113940042","display_name":"Shanghai University","ror":"https://ror.org/006teas31","country_code":"CN","type":"education","lineage":["https://openalex.org/I113940042"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenwei Zhang","raw_affiliation_strings":["Shanghai AI Laboratory Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory Research","institution_ids":["https://openalex.org/I113940042"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032828647","display_name":"Lumin Xu","orcid":"https://orcid.org/0000-0003-2125-2760"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lumin Xu","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100707145","display_name":"Sheng Jin","orcid":"https://orcid.org/0000-0002-9532-4272"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sheng Jin","raw_affiliation_strings":["SenseTime Research and Tetras. AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research and Tetras. AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091312510","display_name":"Zhonghua Wu","orcid":"https://orcid.org/0000-0002-8036-022X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhonghua Wu","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qingyi Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qingyi Tao","raw_affiliation_strings":["SenseTime Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451375","display_name":"Wentao Liu","orcid":"https://orcid.org/0000-0001-6370-4572"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wentao Liu","raw_affiliation_strings":["SenseTime Research and Tetras. AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SenseTime Research and Tetras. AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100683583","display_name":"Wei Li","orcid":"https://orcid.org/0000-0002-7772-5697"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["Nanyang Technological University,S-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,S-Lab","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005626854","display_name":"Chen Change Loy","orcid":"https://orcid.org/0000-0001-5345-1591"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Change Loy","raw_affiliation_strings":["Nanyang Technological University,S-Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,S-Lab","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":"17739","last_page":"17750"},"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":0.42640000581741333,"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":0.42640000581741333,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.4047999978065491,"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":0.05779999867081642,"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/representation","display_name":"Representation (politics)","score":0.5497999787330627},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5339000225067139},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.453900009393692},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.44749999046325684},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4440999925136566},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.397599995136261},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.39739999175071716},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3955000042915344},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.366100013256073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7689999938011169},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6187000274658203},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5497999787330627},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.453900009393692},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.44749999046325684},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4440999925136566},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.397599995136261},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.39739999175071716},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3467000126838684},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3230000138282776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31119999289512634},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3109999895095825},{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2930999994277954},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25529998540878296},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.2547999918460846},{"id":"https://openalex.org/C2983787585","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature matching","level":3,"score":0.251800000667572},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01648","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01648","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.21979","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.21979","pdf_url":"https://arxiv.org/pdf/2503.21979","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.21979","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.21979","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":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:2503.21979","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.21979","pdf_url":"https://arxiv.org/pdf/2503.21979","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":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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unifying":[0],"visual":[1,40,98,105],"understanding":[2,49,106,126,143,174],"and":[3,70,93,127,144,157,178],"generation":[4,111,128,145,151],"within":[5],"a":[6,11,67,120,131,136],"single":[7],"multimodal":[8],"framework":[9,123],"remains":[10],"significant":[12],"challenge,":[13],"as":[14],"the":[15,84,154,162],"two":[16],"inherently":[17],"heterogeneous":[18],"tasks":[19,107,129],"require":[20],"representations":[21],"at":[22,183],"different":[23],"levels":[24],"of":[25,164],"granularity.":[26],"Current":[27],"approaches":[28],"that":[29,62,124,140],"utilize":[30],"vector":[31],"quantization":[32],"(VQ)":[33],"or":[34],"variational":[35],"autoencoders":[36],"(VAE)":[37],"for":[38,104],"unified":[39,121],"representation":[41,87],"prioritize":[42],"intrinsic":[43],"imagery":[44],"features":[45],"over":[46],"semantics,":[47],"compromising":[48],"performance.":[50],"In":[51],"this":[52],"work,":[53],"we":[54,117],"take":[55],"inspiration":[56],"from":[57],"masked":[58,75],"image":[59,78,150,173],"modelling":[60],"(MIM)":[61],"learns":[63],"rich":[64],"semantics":[65],"via":[66],"mask-and-reconstruct":[68],"pre-training":[69],"its":[71,109],"successful":[72],"extension":[73],"to":[74,97],"autoregressive":[76,122],"(MAR)":[77],"generation.":[79],"A":[80],"preliminary":[81],"study":[82],"on":[83,114,153,172],"MAR":[85,133],"encoder's":[86],"reveals":[88],"exceptional":[89],"linear":[90],"probing":[91],"accuracy":[92],"precise":[94],"feature":[95],"response":[96],"concepts,":[99],"which":[100],"indicates":[101],"MAR's":[102],"potential":[103],"beyond":[108],"original":[110],"role.":[112],"Based":[113],"these":[115],"insights,":[116],"present":[118],"\\emph{Harmon},":[119],"harmonizes":[125],"with":[130,166],"shared":[132],"encoder.":[134],"Through":[135],"three-stage":[137],"training":[138],"procedure":[139],"progressively":[141],"optimizes":[142],"capabilities,":[146],"Harmon":[147],"achieves":[148],"state-of-the-art":[149],"results":[152],"GenEval,":[155],"MJHQ30K":[156],"WISE":[158],"benchmarks":[159],"while":[160],"matching":[161],"performance":[163],"methods":[165],"dedicated":[167],"semantic":[168],"encoders":[169],"(e.g.,":[170],"Janus)":[171],"benchmarks.":[175],"Our":[176],"code":[177],"models":[179],"will":[180],"be":[181],"available":[182],"https://github.com/wusize/Harmon.":[184]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}