{"id":"https://openalex.org/W4415540212","doi":"https://doi.org/10.1145/3746027.3755221","title":"LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models","display_name":"LongWriter-V: Enabling Ultra-Long and High-Fidelity Generation in Vision-Language Models","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415540212","doi":"https://doi.org/10.1145/3746027.3755221"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3755221","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755221","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755221","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070578353","display_name":"Shangqing Tu","orcid":"https://orcid.org/0009-0008-0640-3413"},"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":"Shangqing Tu","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-0640-3413","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070997816","display_name":"Yucheng Wang","orcid":"https://orcid.org/0009-0007-8940-5133"},"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":"Yucheng Wang","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-8940-5133","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014232813","display_name":"Daniel Zhang-Li","orcid":"https://orcid.org/0009-0009-3681-1896"},"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":"Daniel Zhang-Li","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-3681-1896","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037091113","display_name":"Yushi Bai","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":"Yushi Bai","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0009-7611-1093","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038246814","display_name":"Jifan Yu","orcid":"https://orcid.org/0000-0003-3430-4048"},"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":"Jifan Yu","raw_affiliation_strings":["IoE, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3430-4048","affiliations":[{"raw_affiliation_string":"IoE, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuhao Wu","orcid":"https://orcid.org/0009-0002-0817-7508"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yuhao Wu","raw_affiliation_strings":["Singapore University of Technology and Design, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0009-0002-0817-7508","affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060498828","display_name":"Lei Hou","orcid":"https://orcid.org/0000-0002-8907-3526"},"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":"Lei Hou","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8907-3526","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016019821","display_name":"Huiqin Liu","orcid":"https://orcid.org/0000-0002-5754-2623"},"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":"Huiqin Liu","raw_affiliation_strings":["IoE, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5754-2623","affiliations":[{"raw_affiliation_string":"IoE, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100320723","display_name":"Zhiyuan Liu","orcid":"https://orcid.org/0000-0002-7709-2543"},"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":"Zhiyuan Liu","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7709-2543","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101639735","display_name":"Bin Xu","orcid":"https://orcid.org/0000-0003-3040-4391"},"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":"Bin Xu","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3040-4391","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003324011","display_name":"Juanzi Li","orcid":"https://orcid.org/0000-0002-6244-0664"},"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":"Juanzi Li","raw_affiliation_strings":["DCST, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6244-0664","affiliations":[{"raw_affiliation_string":"DCST, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"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":0.2614894,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10965","last_page":"10974"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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":0.9993000030517578,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9921000003814697,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9822999835014343,"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/benchmark","display_name":"Benchmark (surveying)","score":0.667900025844574},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6378999948501587},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.604200005531311},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5591999888420105},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.48669999837875366},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.46700000762939453},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.4440999925136566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7305999994277954},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.667900025844574},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6378999948501587},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.604200005531311},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5591999888420105},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.48669999837875366},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.46700000762939453},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.4440999925136566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43709999322891235},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3982999920845032},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35670000314712524},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3149000108242035},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3755221","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755221","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755221","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755221","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2437089788","display_name":null,"funder_award_id":"62476150, 62277033 and 62407027","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W2009766544","https://openalex.org/W4381611941","https://openalex.org/W4392172801","https://openalex.org/W4404509535"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"Large":[1],"Vision-Language":[2],"Models":[3],"(LVLMs)":[4],"can":[5],"process":[6],"inputs":[7],"with":[8,59,127,152],"context":[9],"lengths":[10],"up":[11],"to":[12,21,71,75,82,92,123,140],"128k":[13],"visual":[14],"and":[15,65,119,154,171],"text":[16],"tokens,":[17],"yet":[18],"they":[19],"struggle":[20],"generate":[22],"coherent":[23],"outputs":[24,67,78,106,116],"beyond":[25],"1,000":[26],"words.":[27,73],"We":[28],"find":[29],"that":[30,79],"the":[31,35,83,93,97,128,142],"primary":[32],"limitation":[33],"is":[34],"absence":[36],"of":[37,100,145],"long":[38,77,115],"output":[39],"examples":[40],"during":[41],"supervised":[42],"fine-tuning":[43],"(SFT).":[44],"To":[45],"tackle":[46],"this":[47,160],"issue,":[48],"we":[49,86,110,132],"introduce":[50],"LongWriter-V-22k,":[51],"a":[52,135],"SFT":[53,94],"dataset":[54],"comprising":[55],"22,158":[56],"examples,":[57],"each":[58],"multiple":[60],"input":[61,84],"images,":[62,85],"an":[63],"instruction,":[64],"corresponding":[66],"ranging":[68],"from":[69],"0":[70],"10,000":[72],"Moreover,":[74],"achieve":[76],"maintain":[80],"high-fidelity":[81],"employ":[87],"Direct":[88],"Preference":[89],"Optimization":[90],"(DPO)":[91],"model.":[95],"Given":[96],"high":[98],"cost":[99],"collecting":[101],"human":[102],"feedback":[103],"for":[104],"lengthy":[105],"(e.g.,":[107],"3,000":[108],"words),":[109],"propose":[111],"IterDPO,":[112,155],"which":[113],"breaks":[114],"into":[117],"segments":[118],"uses":[120],"iterative":[121],"corrections":[122],"form":[124],"preference":[125],"pairs":[126],"original":[129],"outputs.":[130],"Additionally,":[131],"develop":[133],"MMLongBench-Write,":[134],"benchmark":[136],"featuring":[137],"six":[138],"tasks":[139],"evaluate":[141],"long-generation":[143],"capabilities":[144],"VLMs.":[146],"Our":[147,168],"7B":[148],"parameter":[149],"model,":[150],"trained":[151],"LongWriter-V-22k":[153],"achieves":[156],"impressive":[157],"performance":[158],"on":[159],"benchmark,":[161],"outperforming":[162],"larger":[163],"proprietary":[164],"models":[165],"like":[166],"GPT-4o.":[167],"models,":[169],"data":[170],"code":[172],"are":[173],"available":[174],"at:":[175],"https://github.com/THU-KEG/LongWriter-V.":[176]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-25T00:00:00"}