{"id":"https://openalex.org/W7168370391","doi":"https://doi.org/10.48550/arxiv.2607.12079","title":"The Capacity of Thought: Benchmarking Llama 3.2 in Semantic fMRI Neural Language Decoding and Improving the Huth Encoding-Model Baseline","display_name":"The Capacity of Thought: Benchmarking Llama 3.2 in Semantic fMRI Neural Language Decoding and Improving the Huth Encoding-Model Baseline","publication_year":2026,"publication_date":"2026-07-13","ids":{"openalex":"https://openalex.org/W7168370391","doi":"https://doi.org/10.48550/arxiv.2607.12079"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.12079","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12079","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,"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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2607.12079","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140870663","display_name":"Milos Suvakovic","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Suvakovic, Milos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140832411","display_name":"Dom Marhoefer","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marhoefer, Dom","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140826972","display_name":"Glenn Grant-Richards","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grant-Richards, Glenn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5140817625","display_name":"Aidan Pinero","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pinero, Aidan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":false,"primary_topic":{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.8238000273704529,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.8238000273704529,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10241","display_name":"Functional Brain Connectivity Studies","score":0.09880000352859497,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10094","display_name":"Epilepsy research and treatment","score":0.016599999740719795,"subfield":{"id":"https://openalex.org/subfields/2738","display_name":"Psychiatry and Mental health"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7633000016212463},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.46619999408721924},{"id":"https://openalex.org/keywords/neural-decoding","display_name":"Neural decoding","score":0.4643000066280365},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.46239998936653137},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.46059998869895935},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4207000136375427},{"id":"https://openalex.org/keywords/language-production","display_name":"Language production","score":0.3743000030517578},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.367900013923645},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.36660000681877136}],"concepts":[{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7633000016212463},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.723800003528595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5231999754905701},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.46619999408721924},{"id":"https://openalex.org/C40743351","wikidata":"https://www.wikidata.org/wiki/Q7002049","display_name":"Neural decoding","level":3,"score":0.4643000066280365},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.46239998936653137},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.46059998869895935},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41600000858306885},{"id":"https://openalex.org/C2776264592","wikidata":"https://www.wikidata.org/wiki/Q463837","display_name":"Language production","level":3,"score":0.3743000030517578},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.367900013923645},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C54170458","wikidata":"https://www.wikidata.org/wiki/Q663554","display_name":"Voxel","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.334199994802475},{"id":"https://openalex.org/C2779226451","wikidata":"https://www.wikidata.org/wiki/Q903809","display_name":"Functional magnetic resonance imaging","level":2,"score":0.33329999446868896},{"id":"https://openalex.org/C120843803","wikidata":"https://www.wikidata.org/wiki/Q4955807","display_name":"Brain activity and meditation","level":3,"score":0.3174000084400177},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.31529998779296875},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.311599999666214},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26669999957084656},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.12079","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12079","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2607.12079","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.12079","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,"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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Decoding":[0],"continuous":[1],"language":[2,138,150],"from":[3],"fMRI":[4,122,156],"signals":[5],"remains":[6],"a":[7,86,95,100,109,116],"core":[8],"challenge":[9],"in":[10],"non-invasive":[11],"brain-computer":[12],"interface":[13],"research.":[14],"We":[15],"present":[16],"two":[17],"complementary":[18],"investigations.":[19],"First,":[20],"we":[21,78],"improve":[22,155],"the":[23,43,136],"Huth":[24],"et":[25],"al.":[26],"ridge":[27],"regression":[28],"encoding":[29],"pipeline":[30],"through":[31],"expanded":[32],"voxel":[33],"selection":[34],"(10K->15K),":[35],"substitution":[36],"of":[37],"GPT-2":[38],"medium":[39],"for":[40,64],"GPT-1":[41],"as":[42],"beam-search":[44],"proposal":[45],"model,":[46],"and":[47,56,99,158],"GPU-accelerated":[48],"bootstrap":[49],"training,":[50],"achieving":[51,104],"mean":[52],"METEOR":[53,71],"=":[54,58],"0.149":[55],"BLEU-1":[57],"0.200":[59],"across":[60],"three":[61],"held-out":[62],"narratives":[63],"subject":[65],"UTS03":[66],"--":[67],"an":[68],"11%":[69],"relative":[70],"gain":[72],"over":[73],"our":[74],"replication":[75],"baseline.":[76],"Second,":[77],"introduce":[79],"fMRIFlamingo,":[80],"which":[81],"maps":[82],"BOLD":[83],"activity":[84],"to":[85],"frozen":[87,137],"Llama-3.2-1B":[88],"with":[89,120],"trainable":[90],"gated":[91],"cross-attention":[92],"layers":[93],"via":[94],"learned":[96],"brain":[97],"tokenizer":[98],"Perceiver":[101],"Resampler.":[102],"Despite":[103],"42.86%":[105],"Top-1":[106],"accuracy":[107],"on":[108],"1-in-100":[110],"ranking":[111],"task,":[112],"well":[113],"above":[114],"chance,":[115],"blind":[117],"control":[118],"ablation":[119],"zeroed":[121],"inputs":[123],"yields":[124],"near-identical":[125],"scores,":[126],"revealing":[127],"that":[128,148],"apparent":[129],"decoding":[130,157],"success":[131],"is":[132],"driven":[133],"primarily":[134],"by":[135,142],"prior":[139],"rather":[140],"than":[141],"neural":[143],"input.":[144],"These":[145],"results":[146],"demonstrate":[147],"high-capacity":[149],"models":[151],"do":[152],"not":[153],"inherently":[154],"can":[159],"actively":[160],"obscure":[161],"failures":[162],"without":[163],"rigorous":[164],"blind-control":[165],"evaluation.":[166]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-16T00:00:00"}