{"id":"https://openalex.org/W7077896577","doi":"https://doi.org/10.48550/arxiv.2508.16771","title":"EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention","display_name":"EyeMulator: Improving Code Language Models by Mimicking Human Visual Attention","publication_year":2025,"publication_date":"2025-08-22","ids":{"openalex":"https://openalex.org/W7077896577","doi":"https://doi.org/10.48550/arxiv.2508.16771"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2508.16771","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.16771","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2508.16771","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhang, Yifan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Yifan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Huang, Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Yueke","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yueke","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Jiahao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiahao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Toby Jia-Jun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Toby Jia-Jun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"McMillan, Collin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"McMillan, Collin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Leach, Kevin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leach, Kevin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Huang, Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yu","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":[],"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":true,"primary_topic":{"id":"https://openalex.org/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6629999876022339,"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/T12157","display_name":"Geochemistry and Geologic Mapping","score":0.6629999876022339,"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/T13067","display_name":"Geological Modeling and Analysis","score":0.02969999983906746,"subfield":{"id":"https://openalex.org/subfields/1906","display_name":"Geochemistry and Petrology"},"field":{"id":"https://openalex.org/fields/19","display_name":"Earth and Planetary Sciences"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14311","display_name":"Electrical and Electromagnetic Research","score":0.019300000742077827,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.737500011920929},{"id":"https://openalex.org/keywords/salience","display_name":"Salience (neuroscience)","score":0.6554999947547913},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5936999917030334},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5412999987602234},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4862000048160553},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4575999975204468},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.36070001125335693},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.35920000076293945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7982000112533569},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.737500011920929},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.6554999947547913},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5936999917030334},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5412999987602234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5321000218391418},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4862000048160553},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4575999975204468},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4235000014305115},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.36070001125335693},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.33090001344680786},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32100000977516174},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.31439998745918274},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.29010000824928284},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2508.16771","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.16771","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":"doi:10.48550/arxiv.2508.16771","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.16771","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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5288859605789185,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Code":[0],"Language":[1],"Models":[2],"(CodeLLMs)":[3],"traditionally":[4],"learn":[5],"attention":[6,41,45,59,118],"based":[7],"solely":[8],"on":[9,21,25],"statistical":[10],"input-output":[11],"token":[12],"correlations":[13],"(\"machine":[14],"attention\").":[15],"In":[16],"contrast,":[17],"human":[18,43,75,117],"developers":[19],"rely":[20],"intuition,":[22],"selectively":[23],"fixating":[24],"semantically":[26],"salient":[27],"tokens":[28],"during":[29,67],"program":[30],"comprehension.":[31],"We":[32],"present":[33],"EyeMulator,":[34],"a":[35],"model-agnostic":[36],"technique":[37],"to":[38,62,73,101],"align":[39],"CodeLLM":[40],"with":[42],"visual":[44],"without":[46],"architectural":[47],"changes.":[48],"By":[49],"extracting":[50],"scan":[51],"paths":[52],"from":[53,115],"eye-tracking":[54],"data,":[55],"we":[56],"derive":[57],"token-level":[58],"weights":[60],"used":[61],"augment":[63],"the":[64,71],"loss":[65],"function":[66],"fine-tuning.":[68],"This":[69],"induces":[70],"model":[72],"mimic":[74],"focus.":[76],"Our":[77],"evaluation":[78],"across":[79],"StarCoder,":[80],"Llama-3.2,":[81],"and":[82,99],"DeepSeek-Coder":[83],"shows":[84],"that":[85,110],"EyeMulator":[86],"significantly":[87],"outperforms":[88],"baselines,":[89],"achieving":[90],"gains":[91,112],"of":[92],"over":[93],"30":[94],"CodeBLEU":[95],"points":[96,104],"in":[97,105],"translation":[98],"up":[100],"22":[102],"BERTScore":[103],"summarization.":[106],"Ablation":[107],"studies":[108],"confirm":[109],"these":[111],"stem":[113],"directly":[114],"replicating":[116],"dynamics.":[119],"Artifacts":[120],"are":[121],"available":[122],"at":[123],"https://zenodo.org/records/17205682.":[124]},"counts_by_year":[],"updated_date":"2026-04-22T06:01:30.510260","created_date":"2025-10-10T00:00:00"}