{"id":"https://openalex.org/W7130595718","doi":"https://doi.org/10.48550/arxiv.2602.16704","title":"Reinforced Fast Weights with Next-Sequence Prediction","display_name":"Reinforced Fast Weights with Next-Sequence Prediction","publication_year":2026,"publication_date":"2026-02-18","ids":{"openalex":"https://openalex.org/W7130595718","doi":"https://doi.org/10.48550/arxiv.2602.16704"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.16704","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126415889","display_name":"Hee Seung Hwang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hwang, Hee Seung","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126420598","display_name":"Xindi Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Xindi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067167236","display_name":"Sanghyuk Chun","orcid":"https://orcid.org/0000-0002-4533-2610"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chun, Sanghyuk","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126375950","display_name":"Olga Russakovsky","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Russakovsky, Olga","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5126415889"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.7077999711036682,"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":0.7077999711036682,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0771000012755394,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07129999995231628,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.5881999731063843},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.5184999704360962},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4950000047683716},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.4731000065803528},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44929999113082886},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4259999990463257},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.40459999442100525},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.3625999987125397}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896000146865845},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5881999731063843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5758000016212463},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.565500020980835},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.5184999704360962},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4950000047683716},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4731000065803528},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4259999990463257},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.40459999442100525},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3513000011444092},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3260999917984009},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.3093999922275543},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2612000107765198},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.16704","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},{"id":"doi:10.48550/arxiv.2602.16704","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.16704","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.16704","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fast":[0,74],"weight":[1,50,87,176],"architectures":[2],"offer":[3],"a":[4,46,80],"promising":[5],"alternative":[6],"to":[7,57,66],"attention-based":[8],"transformers":[9],"for":[10,170],"long-context":[11,155,172],"modeling":[12,173],"by":[13,27],"maintaining":[14],"constant":[15],"memory":[16],"overhead":[17],"regardless":[18],"of":[19,128],"context":[20],"length.":[21],"However,":[22],"their":[23,55],"potential":[24],"is":[25,122],"limited":[26],"the":[28,90,113,125],"next-token":[29],"prediction":[30,92,102],"(NTP)":[31],"training":[32,126],"paradigm.":[33],"NTP":[34,151],"optimizes":[35,112],"single-token":[36],"predictions":[37],"and":[38,111,134,141,158,167],"ignores":[39],"semantic":[40],"coherence":[41],"across":[42,152],"multiple":[43],"tokens":[44],"following":[45],"prefix.":[47],"Consequently,":[48],"fast":[49,86,175],"models,":[51],"which":[52],"dynamically":[53],"update":[54],"parameters":[56],"store":[58],"contextual":[59],"information,":[60],"learn":[61],"suboptimal":[62],"representations":[63],"that":[64,84,144],"fail":[65],"capture":[67],"long-range":[68],"dependencies.":[69],"We":[70],"introduce":[71],"REFINE":[72,95,121,145,163],"(Reinforced":[73],"weIghts":[75],"with":[76,115,150],"Next":[77],"sEquence":[78],"prediction),":[79],"reinforcement":[81],"learning":[82],"framework":[83,169],"trains":[85],"models":[88],"under":[89],"next-sequence":[91],"(NSP)":[93],"objective.":[94],"selects":[96],"informative":[97],"token":[98],"positions":[99],"based":[100],"on":[101,139],"entropy,":[103],"generates":[104],"multi-token":[105],"rollouts,":[106],"assigns":[107],"self-supervised":[108],"sequence-level":[109],"rewards,":[110],"model":[114],"group":[116],"relative":[117],"policy":[118],"optimization":[119],"(GRPO).":[120],"applicable":[123],"throughout":[124],"lifecycle":[127],"pre-trained":[129],"language":[130],"models:":[131],"mid-training,":[132],"post-training,":[133],"test-time":[135],"training.":[136],"Our":[137],"experiments":[138],"LaCT-760M":[140],"DeltaNet-1.3B":[142],"demonstrate":[143],"consistently":[146],"outperforms":[147],"supervised":[148],"fine-tuning":[149],"needle-in-a-haystack":[153],"retrieval,":[154],"question":[156],"answering,":[157],"diverse":[159],"tasks":[160],"in":[161,174],"LongBench.":[162],"provides":[164],"an":[165],"effective":[166],"versatile":[168],"improving":[171],"architectures.":[177]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-20T00:00:00"}