{"id":"https://openalex.org/W7204879293","doi":"https://doi.org/10.48550/arxiv.2608.29662","title":"ACTD: Anchor-Based Cross-Tokenizer Distillation with Residual Regularization","display_name":"ACTD: Anchor-Based Cross-Tokenizer Distillation with Residual Regularization","publication_year":2026,"publication_date":"2026-08-30","ids":{"openalex":"https://openalex.org/W7204879293","doi":"https://doi.org/10.48550/arxiv.2608.29662"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2608.29662","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.29662","pdf_url":"https://arxiv.org/pdf/2608.29662","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":null,"license_id":null,"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/2608.29662","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101567763","display_name":"Huiyi Zhang","orcid":"https://orcid.org/0000-0001-7375-6966","observed_orcids":["https://orcid.org/0000-0001-7375-6966"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Huiyi","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148897964","display_name":"Zijian Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Zijian","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122354432","display_name":"Xiaocheng Feng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng, Xiaocheng","raw_affiliation_strings":["Harbin Institute of Technology","Peng Cheng Laboratory {hyzhang ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Peng Cheng Laboratory {hyzhang ,","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111073904","display_name":"Weitao Ma","orcid":"https://orcid.org/0009-0007-8631-3858","observed_orcids":["https://orcid.org/0009-0007-8631-3858"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ma, Weitao","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748474","display_name":"Xiaoliang Yang","orcid":"https://orcid.org/0000-0002-9353-8373","observed_orcids":["https://orcid.org/0000-0002-9353-8373"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Xiaoliang","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084420549","display_name":"Yi-Chong Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Yichong","raw_affiliation_strings":["Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148846882","display_name":"Bing Qin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin, Bing","raw_affiliation_strings":["Harbin Institute of Technology","Peng Cheng Laboratory {hyzhang ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Peng Cheng Laboratory {hyzhang ,","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T10028","display_name":"Topic Modeling","score":0.711899995803833,"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":0.711899995803833,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1437000036239624,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.060100000351667404,"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/knowledge-distillation","display_name":"knowledge distillation","score":0.9950000047683716},{"id":"https://openalex.org/keywords/anchor-loss","display_name":"anchor loss","score":0.8040000200271606},{"id":"https://openalex.org/keywords/vocabulary-alignment","display_name":"vocabulary alignment","score":0.9390000104904175},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"sequence alignment","score":0.949999988079071},{"id":"https://openalex.org/keywords/multi-teacher-knowledge-distillation","display_name":"multi-teacher distillation","score":0.9309999942779541},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6940000057220459},{"id":"https://openalex.org/keywords/lightweight-student-models","display_name":"lightweight student models","score":0.7289999723434448},{"id":"https://openalex.org/keywords/reasoning-benchmarks","display_name":"reasoning benchmarks","score":0.49799999594688416}],"concepts":[{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.755299985408783},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.7339000105857849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6682999730110168},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.6657000184059143},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5913000106811523},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5705000162124634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.504800021648407},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38199999928474426},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3393999934196472},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3321000039577484},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31929999589920044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2924000024795532},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.29662","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.29662","pdf_url":"https://arxiv.org/pdf/2608.29662","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.29662","doi":"https://doi.org/10.48550/arxiv.2608.29662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.29662","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.29662","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.29662","pdf_url":"https://arxiv.org/pdf/2608.29662","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4156000018119812,"display_name":"Quality education"}],"sustainable_development_goals_aurora":[{"id":"https://metadata.un.org/sdg/4","score":0.8470388054847717,"display_name":"Quality education"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G4442529403","display_name":null,"funder_award_id":"U22B2059","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7930149284","display_name":null,"funder_award_id":"62276078","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":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204879293.pdf","grobid_xml":"https://content.openalex.org/works/W7204879293.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Knowledge":[0],"distillation":[1,29],"effectively":[2],"transfers":[3],"reasoning":[4,94],"capabilities":[5],"from":[6],"large":[7],"language":[8],"models":[9],"to":[10,33,87],"lightweight":[11],"student":[12],"models.":[13],"To":[14,48],"enable":[15],"knowledge":[16],"transfer":[17],"across":[18,92],"disparate":[19],"model":[20],"families,":[21],"researchers":[22],"increasingly":[23],"explore":[24],"cross-tokenizer":[25,28],"distillation.":[26,47],"However,":[27],"remains":[30],"challenging":[31],"due":[32],"vocabulary":[34,40,66],"and":[35,67,113],"sequence":[36,68],"misalignment,":[37],"while":[38,70],"approximate":[39],"alignment":[41,72],"can":[42],"introduce":[43],"additional":[44],"noise":[45,73],"into":[46],"address":[49],"these":[50],"challenges,":[51],"we":[52],"propose":[53],"Anchor-Based":[54],"Cross-Tokenizer":[55],"Distillation":[56],"with":[57,79,96],"Residual":[58],"Regularization":[59],"(ACTD).":[60],"ACTD":[61,101],"bridges":[62],"structural":[63],"heterogeneity":[64],"through":[65],"alignment,":[69],"mitigating":[71],"via":[74],"a":[75,88],"novel":[76],"anchor":[77],"loss":[78],"residual":[80],"regularization.":[81],"We":[82],"further":[83,116],"extend":[84],"this":[85],"framework":[86],"multi-teacher":[89,107,114],"setting.":[90],"Evaluated":[91],"five":[93],"benchmarks":[95],"three":[97],"distinct":[98],"teacher":[99],"models,":[100],"achieves":[102],"state-of-the-art":[103],"performance.":[104],"Moreover,":[105],"its":[106],"extension":[108],"outperforms":[109],"the":[110,118],"strongest":[111],"single-teacher":[112],"baselines,":[115],"demonstrating":[117],"robustness":[119],"of":[120],"our":[121],"method.":[122]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2026-09-02T00:00:00"}