{"id":"https://openalex.org/W4417307892","doi":"https://doi.org/10.1109/iccv51701.2025.00561","title":"Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers","display_name":"Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4417307892","doi":"https://doi.org/10.1109/iccv51701.2025.00561"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00561","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00561","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.07986","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045652891","display_name":"Zepeng Lv","orcid":"https://orcid.org/0000-0001-5979-8967"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhengyao Lv","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tianlin Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianlin Pan","raw_affiliation_strings":["Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023000066","display_name":"Chenyang Si","orcid":"https://orcid.org/0000-0002-3354-1968"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Si","raw_affiliation_strings":["Nanjing University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhaoxi Chen","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":"Zhaoxi Chen","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042587571","display_name":"Wangmeng Zuo","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wangmeng Zuo","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406050","display_name":"Ziwei Liu","orcid":"https://orcid.org/0000-0002-4220-5958"},"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":"Ziwei Liu","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":null,"display_name":"Kwan-Yee K. Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Kwan-Yee K. Wong","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35883462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5934","last_page":"5943"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5898000001907349,"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":0.5898000001907349,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.32919999957084656,"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/T10028","display_name":"Topic Modeling","score":0.00860000029206276,"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/fidelity","display_name":"Fidelity","score":0.559499979019165},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5504000186920166},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5435000061988831},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.535099983215332},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4896000027656555},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.4361000061035156},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.42669999599456787},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.328900009393692}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7253000140190125},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.559499979019165},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5504000186920166},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5435000061988831},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.535099983215332},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4896000027656555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4607999920845032},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.42669999599456787},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.32089999318122864},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2759999930858612},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2639999985694885}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00561","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00561","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:2506.07986","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.07986","pdf_url":"https://arxiv.org/pdf/2506.07986","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2506.07986","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.07986","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.07986","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.07986","pdf_url":"https://arxiv.org/pdf/2506.07986","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":{"Multimodal":[0],"Diffusion":[1],"Transformers":[2],"(MM-DiTs)":[3],"have":[4],"achieved":[5],"remarkable":[6],"progress":[7],"in":[8,35,128,147,151],"text-driven":[9],"visual":[10,53],"generation.":[11],"However,":[12],"even":[13],"state-of-the-art":[14,115],"MM-DiT":[15],"models":[16,116],"like":[17,117],"FLUX":[18,118],"struggle":[19],"with":[20,95,107],"achieving":[21],"precise":[22],"alignment":[23,102,127],"between":[24,52],"text":[25],"prompts":[26],"and":[27,54,57,90,119,135],"generated":[28],"content.":[29],"We":[30,111],"identify":[31],"two":[32],"key":[33],"issues":[34],"the":[36,43,59,67,104,141],"attention":[37,47,63,146],"mechanism":[38],"of":[39,45,61,130,143],"MM-DiT,":[40],"namely":[41],"1)":[42],"suppression":[44],"cross-modal":[46,145],"due":[48],"to":[49,124],"token":[50],"imbalance":[51],"textual":[55],"modalities":[56],"2)":[58],"lack":[60],"timestep-aware":[62],"weighting,":[64],"which":[65],"hinder":[66],"alignment.":[68],"To":[69],"address":[70],"these":[71],"issues,":[72],"we":[73],"propose":[74],"\\textbf{Temperature-Adjusted":[75],"Cross-modal":[76],"Attention":[77],"(TACA)},":[78],"a":[79],"parameter-efficient":[80],"method":[81],"that":[82],"dynamically":[83],"rebalances":[84],"multimodal":[85],"interactions":[86],"through":[87],"temperature":[88],"scaling":[89],"timestep-dependent":[91],"adjustment.":[92],"When":[93],"combined":[94],"LoRA":[96],"fine-tuning,":[97],"TACA":[98,113],"significantly":[99],"enhances":[100],"text-image":[101],"on":[103,114],"T2I-CompBench":[105],"benchmark":[106],"minimal":[108],"computational":[109],"overhead.":[110],"tested":[112],"SD3.5,":[120],"demonstrating":[121],"its":[122],"ability":[123],"improve":[125],"image-text":[126],"terms":[129],"object":[131],"appearance,":[132],"attribute":[133],"binding,":[134],"spatial":[136],"relationships.":[137],"Our":[138,155],"findings":[139],"highlight":[140],"importance":[142],"balancing":[144],"improving":[148],"semantic":[149],"fidelity":[150],"text-to-image":[152],"diffusion":[153],"models.":[154],"codes":[156],"are":[157],"publicly":[158],"available":[159],"at":[160],"\\href{https://github.com/Vchitect/TACA}":[161]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}