{"id":"https://openalex.org/W4406892421","doi":"https://doi.org/10.1109/fllm63129.2024.10852430","title":"Towards Multi-Modal Mastery: A 4.5B Parameter Truly Multi-Modal Small Language Model","display_name":"Towards Multi-Modal Mastery: A 4.5B Parameter Truly Multi-Modal Small Language Model","publication_year":2024,"publication_date":"2024-11-26","ids":{"openalex":"https://openalex.org/W4406892421","doi":"https://doi.org/10.1109/fllm63129.2024.10852430"},"language":"en","primary_location":{"id":"doi:10.1109/fllm63129.2024.10852430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm63129.2024.10852430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"},"type":"article","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/A5114656608","display_name":"Ben Koska","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Ben Koska","raw_affiliation_strings":["TU Wien,Informatics,Vienna,Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien,Informatics,Vienna,Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114656609","display_name":"Mojm\u00edr Horv\u00e1th","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Mojm\u00edr Horv\u00e1th","raw_affiliation_strings":["TU Wien,Informatics,Vienna,Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien,Informatics,Vienna,Austria","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5114656608"],"corresponding_institution_ids":["https://openalex.org/I145847075"],"apc_list":null,"apc_paid":null,"fwci":0.6398,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.76819648,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"587","last_page":"592"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9951000213623047,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9951000213623047,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9732999801635742,"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/modal","display_name":"Modal","score":0.8645250797271729},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6492025256156921},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.08295586705207825}],"concepts":[{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.8645250797271729},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6492025256156921},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.08295586705207825},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fllm63129.2024.10852430","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fllm63129.2024.10852430","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 2nd International Conference on Foundation and Large Language Models (FLLM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,34,62],"novel":[3],"4.5B":[4],"parameter":[5],"small":[6,25],"language":[7,55],"model":[8,28,66],"that":[9,67],"can":[10,68],"handle":[11],"multiple":[12,83],"input":[13],"and":[14,21,57,64],"output":[15],"modalities,":[16],"including":[17],"text,":[18],"images,":[19],"videos,":[20],"audio.":[22],"Despite":[23],"its":[24],"size,":[26],"the":[27,39,78,86],"achieves":[29],"near":[30],"state-of-the-art":[31],"performance":[32,81],"on":[33],"variety":[35],"of":[36,41],"tasks,":[37],"demonstrating":[38],"potential":[40],"multi-modal":[42,92],"models":[43],"to":[44,60],"tackle":[45],"complex":[46],"real-world":[47],"problems.":[48],"Our":[49],"approach":[50],"leverages":[51],"recent":[52],"advancements":[53],"in":[54,91],"modeling":[56],"multi-task":[58],"learning":[59],"create":[61],"versatile":[63],"high-performing":[65],"even":[69],"be":[70],"deployed":[71],"for":[72,88],"edge":[73],"inference.":[74],"Experimental":[75],"results":[76],"show":[77],"model's":[79],"strong":[80],"across":[82],"benchmarks,":[84],"paving":[85],"way":[87],"further":[89],"progress":[90],"artificial":[93],"intelligence.":[94]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-14T08:36:36.166977","created_date":"2025-10-10T00:00:00"}