{"id":"https://openalex.org/W7153353645","doi":"https://doi.org/10.48550/arxiv.2604.08065","title":"Multimodal Latent Reasoning via Predictive Embeddings","display_name":"Multimodal Latent Reasoning via Predictive Embeddings","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7153353645","doi":"https://doi.org/10.48550/arxiv.2604.08065"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.08065","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08065","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.08065","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112543899","display_name":"Ashutosh Adhikari","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adhikari, Ashutosh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133364628","display_name":"Mirella Lapata","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lapata, Mirella","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9660999774932861,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9660999774932861,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.005100000184029341,"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"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.00279999990016222,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6651999950408936},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6251999735832214},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4652999937534332},{"id":"https://openalex.org/keywords/pearl","display_name":"Pearl","score":0.4611000120639801},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4250999987125397},{"id":"https://openalex.org/keywords/opportunistic-reasoning","display_name":"Opportunistic reasoning","score":0.37070000171661377},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3425000011920929},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.33160001039505005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7483000159263611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6797000169754028},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6651999950408936},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6251999735832214},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5654000043869019},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C2779251273","wikidata":"https://www.wikidata.org/wiki/Q43436","display_name":"Pearl","level":2,"score":0.4611000120639801},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.37070000171661377},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3280999958515167},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.313400000333786},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C917703","wikidata":"https://www.wikidata.org/wiki/Q7239668","display_name":"Predictive inference","level":5,"score":0.27489998936653137},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.25290000438690186},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.08065","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08065","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.08065","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08065","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":"Preprint"},"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":{"Tool-augmented":[0],"multimodal":[1,100],"reasoning":[2,75,140],"enables":[3],"visual":[4],"language":[5],"models":[6],"(VLMs)":[7],"to":[8,33,113],"improve":[9],"perception":[10,126],"by":[11],"interacting":[12],"with":[13,119],"external":[14],"tools":[15],"(e.g.,":[16],"cropping,":[17],"depth":[18],"estimation).":[19],"However,":[20],"such":[21],"approaches":[22],"incur":[23],"substantial":[24],"inference":[25,70],"overhead,":[26],"require":[27],"specialized":[28],"supervision,":[29],"and":[30,82,87,115,137],"are":[31],"prone":[32],"erroneous":[34],"tool":[35,67,92,121],"calls.":[36,122],"We":[37],"propose":[38],"Pearl":[39,94,130],"(Predictive":[40],"Embedding":[41],"Alignment":[42],"for":[43,65,90],"Reasoning":[44],"in":[45,58,157],"Latent":[46],"space),":[47],"a":[48,165],"JEPA-inspired":[49],"framework":[50],"that":[51,129,147],"learns":[52,96],"from":[53,84,99],"expert":[54],"tool-use":[55],"trajectories":[56,101,118],"entirely":[57],"the":[59,63,104],"latent":[60,74,80,139,158],"space,":[61,159],"eliminating":[62],"need":[64],"explicit":[66],"invocation":[68],"at":[69],"time.":[71],"Unlike":[72],"reconstruction-based":[73,138,148],"methods,":[76],"which":[77],"autoregressively":[78],"generate":[79],"tokens":[81],"suffer":[83],"training-inference":[85],"mismatch":[86],"limited":[88],"support":[89],"multi-step":[91],"use,":[93],"directly":[95],"predictive":[97,161],"embeddings":[98,152],"while":[102],"preserving":[103],"standard":[105,134],"vision-language":[106],"generation":[107],"pipeline:":[108],"it":[109],"is":[110],"model-agnostic,":[111],"simple":[112],"train,":[114],"naturally":[116],"supports":[117],"multiple":[120,125],"Experiments":[123],"across":[124],"benchmarks":[127],"show":[128],"matches":[131],"or":[132],"outperforms":[133],"supervised":[135],"fine-tuning":[136],"approaches.":[141],"Furthermore,":[142],"we":[143],"provide":[144],"empirical":[145],"evidence":[146],"methods":[149],"primarily":[150],"learn":[151],"rather":[153],"than":[154],"image":[155],"edits":[156],"motivating":[160],"embedding":[162],"learning":[163],"as":[164],"more":[166],"principled":[167],"alternative.":[168]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-11T00:00:00"}