{"id":"https://openalex.org/W4416213877","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229146","title":"FlexFFN: Hierarchical Dynamic Selection of Feedforward Networks for Large Language Models","display_name":"FlexFFN: Hierarchical Dynamic Selection of Feedforward Networks for Large Language Models","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416213877","doi":"https://doi.org/10.1109/ijcnn64981.2025.11229146"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11229146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5027369574","display_name":"Miaobo Hu","orcid":"https://orcid.org/0000-0002-6417-3280"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Miaobo Hu","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,BeiJing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,BeiJing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091470265","display_name":"Bokun Wang","orcid":"https://orcid.org/0000-0003-1091-3324"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bokun Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,BeiJing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,BeiJing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110958878","display_name":"Haibo Teng","orcid":"https://orcid.org/0009-0007-7066-5779"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoyuan Teng","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,BeiJing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,BeiJing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100878234","display_name":"Hongyu Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongyu Yao","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,BeiJing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,BeiJing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051666209","display_name":"Daren Zha","orcid":"https://orcid.org/0009-0002-6042-3454"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Daren Zha","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,BeiJing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,BeiJing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692679","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-9632-9094"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,BeiJing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,BeiJing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012943082","display_name":"Jun Xiao","orcid":"https://orcid.org/0000-0002-4935-7866"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xiao","raw_affiliation_strings":["University of Chinese Academy of Sciences,BeiJing,China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences,BeiJing,China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100435771","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0001-7266-148X"},"institutions":[{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Information Engineering,BeiJing,China"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Information Engineering,BeiJing,China","institution_ids":["https://openalex.org/I4210156404","https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5027369574"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210156404"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19290337,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.35839998722076416,"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/T10028","display_name":"Topic Modeling","score":0.35839998722076416,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.07329999655485153,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.06459999829530716,"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/interpretability","display_name":"Interpretability","score":0.8662999868392944},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.7092000246047974},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5874000191688538},{"id":"https://openalex.org/keywords/feed-forward","display_name":"Feed forward","score":0.5360999703407288},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.47110000252723694},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.47049999237060547},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.41190001368522644},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3953000009059906}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8662999868392944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8166999816894531},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.7092000246047974},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5874000191688538},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.5360999703407288},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5332000255584717},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.47110000252723694},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.47049999237060547},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4544999897480011},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.3375999927520752},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C13540734","wikidata":"https://www.wikidata.org/wiki/Q5318996","display_name":"Dynamic network analysis","level":2,"score":0.28189998865127563},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2671999931335449},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C47702885","wikidata":"https://www.wikidata.org/wiki/Q5441227","display_name":"Feedforward neural network","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11229146","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11229146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2593833795","https://openalex.org/W2912924812","https://openalex.org/W2949153209","https://openalex.org/W2970023150","https://openalex.org/W3194676777"],"related_works":[],"abstract_inverted_index":{"Optimizing":[0],"the":[1,42,64,82,89],"efficiency":[2],"and":[3,37,78,92,109,126,135,153],"adaptability":[4,152],"of":[5,49,86,95],"large":[6],"language":[7],"models":[8],"(LLMs)":[9],"for":[10,132],"diverse":[11],"downstream":[12],"tasks":[13],"remains":[14],"a":[15,24,47,71,120],"critical":[16],"challenge.":[17],"We":[18],"propose":[19],"FlexFFN":[20,45,98,118,141],"(Flexible":[21],"Feedforward":[22],"Network),":[23],"novel":[25],"framework":[26],"that":[27,140],"introduces":[28],"hierarchical":[29],"dynamic":[30,72],"selection":[31],"to":[32,53,104],"enhance":[33],"computational":[34,110,124,147],"efficiency,":[35],"flexibility,":[36],"performance":[38],"in":[39],"LLMs.":[40],"At":[41,63],"macro":[43],"level,":[44,66],"leverages":[46],"Mixture":[48],"Experts":[50],"(MoE)":[51],"architecture":[52],"dynamically":[54],"activate":[55],"distinct":[56],"FFN":[57,69],"modules":[58],"based":[59],"on":[60],"input":[61],"characteristics.":[62],"micro":[65],"within":[67],"each":[68],"module,":[70],"switching":[73],"mechanism":[74],"selects":[75],"between":[76,123],"KAN":[77],"traditional":[79,143],"MLP,":[80],"combining":[81],"rapid":[83],"convergence":[84],"capabilities":[85],"MLPs":[87],"with":[88],"compositional":[90],"learning":[91],"interpretability":[93],"strengths":[94],"KAN.":[96],"Additionally,":[97],"integrates":[99],"QLoRA":[100],"(Quantized":[101],"Low-Rank":[102],"Adaptation)":[103],"significantly":[105],"reduce":[106],"memory":[107],"requirements":[108],"costs":[111],"during":[112],"fine-tuning.":[113],"By":[114],"introducing":[115],"these":[116],"innovations,":[117],"achieves":[119],"fine-grained":[121],"balance":[122],"cost":[125],"model":[127,154],"expressiveness,":[128],"making":[129],"it":[130],"well-suited":[131],"large-scale":[133],"training":[134],"deployment.":[136],"Experimental":[137],"results":[138],"demonstrate":[139],"outperforms":[142],"architectures":[144],"by":[145],"reducing":[146],"overhead":[148],"while":[149],"improving":[150],"task-specific":[151],"efficiency.":[155]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}