{"id":"https://openalex.org/W4400104563","doi":"https://doi.org/10.48550/arxiv.2406.18193","title":"MammothModa: Multi-Modal Large Language Model","display_name":"MammothModa: Multi-Modal Large Language Model","publication_year":2024,"publication_date":"2024-06-26","ids":{"openalex":"https://openalex.org/W4400104563","doi":"https://doi.org/10.48550/arxiv.2406.18193"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2406.18193","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.18193","pdf_url":"https://arxiv.org/pdf/2406.18193","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2406.18193","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018523545","display_name":"Qi She","orcid":"https://orcid.org/0000-0002-4490-2941","observed_orcids":["https://orcid.org/0000-0002-4490-2941"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"She, Qi","raw_affiliation_strings":["ByteDance , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance , Beijing , China","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057847376","display_name":"Junwen Pan","orcid":"https://orcid.org/0000-0002-8781-6090","observed_orcids":["https://orcid.org/0000-0002-8781-6090"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan, Junwen","raw_affiliation_strings":["ByteDance , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance , Beijing , China","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101613678","display_name":"Xin Wan","orcid":"https://orcid.org/0000-0002-1677-2684","observed_orcids":["https://orcid.org/0000-0002-1677-2684"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wan, Xin","raw_affiliation_strings":["ByteDance , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance , Beijing , China","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100651179","display_name":"Rui Zhang","orcid":"https://orcid.org/0000-0002-2264-8735","observed_orcids":["https://orcid.org/0000-0002-2264-8735"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Rui","raw_affiliation_strings":["ByteDance , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance , Beijing , China","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102088081","display_name":"Lu Dawei","orcid":"https://orcid.org/0000-0002-5062-6402","observed_orcids":["https://orcid.org/0000-0002-5062-6402"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu, Dawei","raw_affiliation_strings":["ByteDance , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance , Beijing , China","institution_ids":["https://openalex.org/I4405256866"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058808484","display_name":"Kai Huang","orcid":"https://orcid.org/0000-0002-9876-2913","observed_orcids":["https://orcid.org/0000-0002-9876-2913"]},"institutions":[{"id":"https://openalex.org/I4405256866","display_name":"ByteDance (China)","ror":"https://ror.org/04m8av638","country_code":"CN","type":"company","lineage":["https://openalex.org/I4405256866"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Kai","raw_affiliation_strings":["ByteDance , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ByteDance , Beijing , China","institution_ids":["https://openalex.org/I4405256866"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4405256866"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0,"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/multimodal-large-language-models","display_name":"multimodal large language models","score":0.8519999980926514},{"id":"https://openalex.org/keywords/vision-language-understanding","display_name":"visual language understanding","score":0.7799999713897705}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.7280312776565552},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6005821228027344},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.4051942825317383},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07796424627304077},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.06391772627830505},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2406.18193","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.18193","pdf_url":"https://arxiv.org/pdf/2406.18193","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2406.18193","doi":"https://doi.org/10.48550/arxiv.2406.18193","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2406.18193","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"pmh:oai:arXiv.org:2406.18193","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2406.18193","pdf_url":"https://arxiv.org/pdf/2406.18193","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400104563.pdf","grobid_xml":"https://content.openalex.org/works/W4400104563.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"In":[0,39],"this":[1],"report,":[2],"we":[3,45,114],"introduce":[4],"MammothModa,":[5],"yet":[6],"another":[7],"multi-modal":[8],"large":[9],"language":[10,129],"model":[11],"(MLLM)":[12],"designed":[13],"to":[14,41,54,75,89,107],"achieve":[15],"state-of-the-art":[16,121],"performance":[17],"starting":[18],"from":[19],"an":[20],"elementary":[21],"baseline.":[22],"We":[23,69,97],"focus":[24],"on":[25],"three":[26],"key":[27],"design":[28],"insights:":[29],"(i)":[30],"Integrating":[31],"Visual":[32,48,67,72],"Capabilities":[33],"while":[34],"Maintaining":[35],"Complex":[36],"Language":[37],"Understanding:":[38],"addition":[40],"the":[42,47,52,71,78,120],"vision":[43],"encoder,":[44],"incorporated":[46,85],"Attention":[49],"Experts":[50],"into":[51],"LLM":[53],"enhance":[55],"its":[56],"visual":[57,109,128],"capabilities.":[58],"(ii)":[59],"Extending":[60],"Context":[61],"Window":[62],"for":[63],"High-Resolution":[64],"and":[65,84,100,133],"Long-Duration":[66],"Feature:":[68],"explore":[70],"Merger":[73],"Module":[74],"effectively":[76],"reduce":[77,108],"token":[79],"number":[80],"of":[81],"high-resolution":[82],"images":[83],"frame":[86],"position":[87,91],"ids":[88],"avoid":[90],"interpolation.":[92],"(iii)":[93],"High-Quality":[94],"Bilingual":[95],"Datasets:":[96],"meticulously":[98],"curated":[99],"filtered":[101],"a":[102],"high-quality":[103],"bilingual":[104],"multimodal":[105],"dataset":[106],"hallucinations.":[110],"With":[111],"above":[112],"recipe":[113],"build":[115],"MammothModa":[116],"that":[117],"consistently":[118],"outperforms":[119],"models,":[122],"e.g.,":[123],"LLaVA-series,":[124],"across":[125],"main":[126],"real-world":[127],"benchmarks":[130],"without":[131],"bells":[132],"whistles.":[134]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2025-10-10T00:00:00"}
