{"id":"https://openalex.org/W7160037241","doi":"https://doi.org/10.1109/iccv51701.2025.01554","title":"X2i: Seamless Integration of Multimodal Understanding Into Diffusion Transformer Via Attention Distillation","display_name":"X2i: Seamless Integration of Multimodal Understanding Into Diffusion Transformer Via Attention Distillation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7160037241","doi":"https://doi.org/10.1109/iccv51701.2025.01554"},"language":null,"primary_location":{"id":"doi:10.1109/iccv51701.2025.01554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01554","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":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135159150","display_name":"Jian Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Ma","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135135456","display_name":"Qirong Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qirong Peng","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129722475","display_name":"Xu Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu Guo","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135113319","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0002-8499-3323"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135183219","display_name":"Haonan Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haonan Lu","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135103578","display_name":"Zhenyu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenyu Yang","raw_affiliation_strings":["OPPO AI Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO AI Center","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":"16733","last_page":"16744"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.0471000000834465,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10914","display_name":"Tactile and Sensory Interactions","score":0.0471000000834465,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.03830000013113022,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.03750000149011612,"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/transformer","display_name":"Transformer","score":0.3944999873638153},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.3589000105857849},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.28209999203681946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5236999988555908},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3944999873638153},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.3589000105857849},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.32499998807907104},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.28209999203681946},{"id":"https://openalex.org/C171146098","wikidata":"https://www.wikidata.org/wiki/Q124192","display_name":"Automotive engineering","level":1,"score":0.24889999628067017},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.24690000712871552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24230000376701355},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.23489999771118164},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.2303999960422516}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccv51701.2025.01554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01554","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","score":0.46818414330482483,"display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2962770929","https://openalex.org/W3129831491","https://openalex.org/W3180355996","https://openalex.org/W4312933868","https://openalex.org/W4386065512","https://openalex.org/W4386072096","https://openalex.org/W4386076425","https://openalex.org/W4388989557","https://openalex.org/W4390872297","https://openalex.org/W4390873054","https://openalex.org/W4390874002","https://openalex.org/W4390874468","https://openalex.org/W4400573550","https://openalex.org/W4402672034","https://openalex.org/W4402916399","https://openalex.org/W4403601051","https://openalex.org/W4403942675","https://openalex.org/W4404792725","https://openalex.org/W4406610920","https://openalex.org/W4409367325","https://openalex.org/W4413145833","https://openalex.org/W4413147134","https://openalex.org/W4413147555","https://openalex.org/W7133185348","https://openalex.org/W7133193597","https://openalex.org/W7133196460","https://openalex.org/W7133217041","https://openalex.org/W7133250524","https://openalex.org/W7160185424"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-05-05T00:00:00"}
