{"id":"https://openalex.org/W7127087145","doi":"https://doi.org/10.48550/arxiv.2601.22402","title":"Bifocal Attention: Harmonizing Geometric and Spectral Positional Embeddings for Algorithmic Generalization","display_name":"Bifocal Attention: Harmonizing Geometric and Spectral Positional Embeddings for Algorithmic Generalization","publication_year":2026,"publication_date":"2026-01-29","ids":{"openalex":"https://openalex.org/W7127087145","doi":"https://doi.org/10.48550/arxiv.2601.22402"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2601.22402","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.22402","pdf_url":"https://arxiv.org/pdf/2601.22402","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/2601.22402","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116608608","display_name":"Kanishk Awadhiya","orcid":"https://orcid.org/0009-0006-0557-0936","observed_orcids":["https://orcid.org/0009-0006-0557-0936"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Awadhiya, Kanishk","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5116608608"],"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":0.9384999871253967,"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":0.9384999871253967,"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":0.03189999982714653,"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":0.003800000064074993,"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/rotary-positional-embeddings","display_name":"rotary positional embeddings","score":0.8840000033378601},{"id":"https://openalex.org/keywords/algorithmic-reasoning","display_name":"algorithmic reasoning","score":0.7450000047683716},{"id":"https://openalex.org/keywords/long-term-dependencies","display_name":"long-range dependencies","score":0.6909999847412109},{"id":"https://openalex.org/keywords/recursive-reasoning","display_name":"recursive reasoning","score":0.6330000162124634},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6819999814033508}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5936999917030334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5781999826431274},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.536899983882904},{"id":"https://openalex.org/C181095308","wikidata":"https://www.wikidata.org/wiki/Q1541599","display_name":"Geometric primitive","level":2,"score":0.5339000225067139},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.46540001034736633},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.46309998631477356},{"id":"https://openalex.org/C127934551","wikidata":"https://www.wikidata.org/wiki/Q1148098","display_name":"Harmonic","level":2,"score":0.4587000012397766},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.3792000114917755},{"id":"https://openalex.org/C7305733","wikidata":"https://www.wikidata.org/wiki/Q207961","display_name":"Geometric shape","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3734000027179718},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C128107574","wikidata":"https://www.wikidata.org/wiki/Q182003","display_name":"Injective function","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.34599998593330383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3458999991416931},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.34459999203681946},{"id":"https://openalex.org/C199185054","wikidata":"https://www.wikidata.org/wiki/Q552299","display_name":"Chain (unit)","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32670000195503235},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3203999996185303},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C137800194","wikidata":"https://www.wikidata.org/wiki/Q11713455","display_name":"Interpolation (computer graphics)","level":3,"score":0.2623000144958496},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.25619998574256897}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.22402","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.22402","pdf_url":"https://arxiv.org/pdf/2601.22402","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.2601.22402","doi":"https://doi.org/10.48550/arxiv.2601.22402","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.22402","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:2601.22402","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.22402","pdf_url":"https://arxiv.org/pdf/2601.22402","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Rotary":[0],"Positional":[1],"Embeddings":[2],"(RoPE)":[3],"have":[4],"become":[5],"the":[6,51,149,154],"standard":[7,34],"for":[8,43,104,114,148],"Large":[9],"Language":[10],"Models":[11],"(LLMs)":[12],"due":[13],"to":[14,17,49,76,78,138],"their":[15],"ability":[16],"encode":[18],"relative":[19],"positions":[20],"through":[21],"geometric":[22,39,133],"rotation.":[23],"However,":[24],"we":[25,30,85],"identify":[26],"a":[27,37,65,121,144],"significant":[28],"limitation":[29],"term":[31],"''Spectral":[32],"Rigidity'':":[33],"RoPE":[35],"utilizes":[36],"fixed":[38],"decay":[40],"($\u03b8^{-i}$)":[41],"optimized":[42,147],"local":[44],"syntactic":[45],"coherence,":[46],"which":[47,127],"fails":[48],"capture":[50],"long-range,":[52],"periodic":[53],"structures":[54],"inherent":[55],"in":[56,64],"recursive":[57,80,117],"logic":[58],"and":[59,108],"algorithmic":[60,151],"reasoning.":[61],"This":[62],"results":[63],"''Structure":[66],"Gap'',":[67],"where":[68],"models":[69],"trained":[70],"on":[71],"shallow":[72],"reasoning":[73],"chains":[74],"fail":[75],"extrapolate":[77],"deeper":[79],"steps.":[81],"In":[82],"this":[83],"work,":[84],"introduce":[86],"Bifocal":[87],"Attention,":[88],"an":[89],"architectural":[90],"paradigm":[91],"that":[92],"decouples":[93],"positional":[94,129],"encoding":[95],"into":[96,143],"two":[97],"distinct":[98],"modalities:":[99],"Geometric":[100],"Eyes":[101,110],"(Standard":[102],"RoPE)":[103],"precise":[105],"token-level":[106],"manipulation,":[107],"Spectral":[109,125],"(Learnable":[111],"Harmonic":[112],"Operators)":[113],"tracking":[115],"long-range":[116],"depth.":[118],"We":[119],"propose":[120],"novel":[122],"training":[123],"protocol,":[124],"Evolution,":[126],"initializes":[128],"frequencies":[130],"as":[131],"static":[132],"parameters":[134],"but":[135],"allows":[136],"them":[137],"evolve":[139],"via":[140],"gradient":[141],"descent":[142],"harmonic":[145],"basis":[146],"specific":[150],"topology":[152],"of":[153],"task.":[155]},"counts_by_year":[],"updated_date":"2026-09-25T08:18:29.962427","created_date":"2026-02-03T00:00:00"}