{"id":"https://openalex.org/W4417257558","doi":"https://doi.org/10.48550/arxiv.2506.08652","title":"JoFormer (Journey-based Transformer): Theory and Empirical Analysis on the Tiny Shakespeare Dataset","display_name":"JoFormer (Journey-based Transformer): Theory and Empirical Analysis on the Tiny Shakespeare Dataset","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4417257558","doi":"https://doi.org/10.48550/arxiv.2506.08652"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2506.08652","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.08652","pdf_url":"https://arxiv.org/pdf/2506.08652","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/2506.08652","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119862714","display_name":"Mahesh Godavarti","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Godavarti, Mahesh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5119862714"],"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":0.9477999806404114,"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":0.9477999806404114,"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":0.03200000151991844,"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":0.0015999999595806003,"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/relative-position-encoding","display_name":"relative position encoding","score":0.6549999713897705},{"id":"https://openalex.org/keywords/noncommutative-algebras","display_name":"noncommutative algebras","score":0.9539999961853027},{"id":"https://openalex.org/keywords/directional-transforms","display_name":"directional transforms","score":0.875}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.8751999735832214},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6596999764442444},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6274999976158142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49810001254081726},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4083999991416931},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39430001378059387},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C78780964","wikidata":"https://www.wikidata.org/wiki/Q7233193","display_name":"Position paper","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2542000114917755},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2517000138759613},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2506.08652","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.08652","pdf_url":"https://arxiv.org/pdf/2506.08652","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.2506.08652","doi":"https://doi.org/10.48550/arxiv.2506.08652","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.08652","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.08652","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.08652","pdf_url":"https://arxiv.org/pdf/2506.08652","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4388979610","https://openalex.org/W7203687871","https://openalex.org/W3200520312","https://openalex.org/W3214332533","https://openalex.org/W3135294600","https://openalex.org/W3106210592","https://openalex.org/W3209632425","https://openalex.org/W3132607382","https://openalex.org/W3201859176","https://openalex.org/W4416451854"],"abstract_inverted_index":{"Transformers":[0],"have":[1],"demonstrated":[2],"remarkable":[3],"success":[4],"in":[5,32,184],"sequence":[6],"modeling,":[7],"yet":[8,147],"effectively":[9],"incorporating":[10],"positional":[11,176],"information":[12],"remains":[13],"a":[14,27,33,140,156,171],"challenging":[15],"and":[16,60,78,120],"active":[17],"area":[18],"of":[19,126,132,158],"research.":[20],"In":[21],"this":[22,185],"paper,":[23],"we":[24,96],"introduce":[25],"JoFormer,":[26],"journey-based":[28,130],"Transformer":[29,179],"architecture":[30],"grounded":[31],"recently":[34],"proposed":[35],"non-commutative":[36],"algebra":[37],"for":[38,160],"composing":[39],"transformations":[40,88],"across":[41],"positions.":[42],"JoFormer":[43,72,98,115,137,169],"represents":[44],"relative":[45,66],"positions":[46],"through":[47],"learnable":[48],"directional":[49],"transforms":[50],"that":[51,80,114],"are":[52],"sequentially":[53],"composed":[54],"along":[55],"the":[56,71,100,104,124,135],"input,":[57],"thereby":[58],"extending":[59],"generalizing":[61],"existing":[62],"approaches":[63],"based":[64],"on":[65,103],"position":[67],"representations.":[68],"We":[69,164],"derive":[70],"attention":[73],"mechanism":[74],"from":[75],"first":[76],"principles":[77],"show":[79],"it":[81,148],"subsumes":[82],"standard":[83],"methods":[84],"such":[85],"as":[86,89,155],"rotary":[87],"special":[90],"cases.":[91],"To":[92],"evaluate":[93],"its":[94,127,153],"effectiveness,":[95],"compare":[97],"to":[99,174],"RoFormer":[101],"baseline":[102],"Tiny":[105],"Shakespeare":[106],"character-level":[107],"language":[108],"modeling":[109],"task.":[110],"Our":[111],"results":[112],"demonstrate":[113],"consistently":[116],"achieves":[117],"lower":[118],"perplexity":[119],"faster":[121],"convergence,":[122],"highlighting":[123],"advantages":[125],"more":[128,161],"expressive,":[129],"treatment":[131],"position.":[133],"Notably,":[134],"per-token":[136],"is":[138,187],"still":[139],"primitive,":[141],"conceptual":[142],"variant":[143],"with":[144],"layer-independent":[145],"angles,":[146],"already":[149],"demonstrates":[150],"strong":[151],"performance-underscoring":[152],"promise":[154],"proof":[157],"concept":[159],"expressive":[162],"architectures.":[163,180],"conclude":[165],"by":[166],"discussing":[167],"how":[168],"offers":[170],"principled":[172],"approach":[173],"integrating":[175],"structure":[177],"into":[178],"The":[181],"code":[182],"used":[183],"work":[186],"available":[188],"at":[189],"https://github.com/mahesh-godavarti/joformer.":[190]},"counts_by_year":[],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2025-10-10T00:00:00"}