{"id":"https://openalex.org/W7214794286","doi":"https://doi.org/10.48550/arxiv.2609.31933","title":"ANaLOG: Anisotropic Native-Latent Operator Guidance for Solving Inverse Problems","display_name":"ANaLOG: Anisotropic Native-Latent Operator Guidance for Solving Inverse Problems","publication_year":2026,"publication_date":"2026-09-25","ids":{"openalex":"https://openalex.org/W7214794286","doi":"https://doi.org/10.48550/arxiv.2609.31933"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.31933","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.31933","pdf_url":"https://arxiv.org/pdf/2609.31933","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.31933","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002186732","display_name":"Darshan Thaker","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thaker, Darshan","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065953740","display_name":"Lachlan Ewen MacDonald","orcid":"https://orcid.org/0000-0003-3601-9777","observed_orcids":["https://orcid.org/0000-0003-3601-9777"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"MacDonald, Lachlan Ewen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5011256828","display_name":"Ren\u00e9 Vidal","orcid":"https://orcid.org/0000-0003-1838-0761","observed_orcids":["https://orcid.org/0000-0003-1838-0761"]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vidal, Ren\u00e9","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8666999936103821,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.8666999936103821,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.04270000010728836,"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/T11205","display_name":"Numerical methods in inverse problems","score":0.023800000548362732,"subfield":{"id":"https://openalex.org/subfields/2610","display_name":"Mathematical Physics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/latent-diffusion-models","display_name":"latent diffusion models","score":0.8550000190734863},{"id":"https://openalex.org/keywords/inverse-problems","display_name":"inverse problems","score":0.9860000014305115},{"id":"https://openalex.org/keywords/covariance-weighting","display_name":"covariance weighting","score":0.652999997138977},{"id":"https://openalex.org/keywords/uncertainty-estimation","display_name":"uncertainty estimation","score":0.48100000619888306},{"id":"https://openalex.org/keywords/image-reconstruction","display_name":"image reconstruction","score":0.5680000185966492},{"id":"https://openalex.org/keywords/sampling-error","display_name":"sampling error","score":0.4659999907016754},{"id":"https://openalex.org/keywords/linear-inverse-problems","display_name":"linear inverse problems","score":0.5879999995231628}],"concepts":[{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5938000082969666},{"id":"https://openalex.org/C135252773","wikidata":"https://www.wikidata.org/wiki/Q1567213","display_name":"Inverse problem","level":2,"score":0.5906000137329102},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5422999858856201},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5015000104904175},{"id":"https://openalex.org/C103692563","wikidata":"https://www.wikidata.org/wiki/Q5178900","display_name":"Covariance operator","level":3,"score":0.4860000014305115},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4717000126838684},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4350000023841858},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4332999885082245},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.41130000352859497},{"id":"https://openalex.org/C207467116","wikidata":"https://www.wikidata.org/wiki/Q4385666","display_name":"Inverse","level":2,"score":0.40779998898506165},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4016000032424927},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3873000144958496},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35580000281333923},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.3142000138759613},{"id":"https://openalex.org/C184050105","wikidata":"https://www.wikidata.org/wiki/Q273163","display_name":"Isotropy","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27410000562667847}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.31933","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.31933","pdf_url":"https://arxiv.org/pdf/2609.31933","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.31933","doi":"https://doi.org/10.48550/arxiv.2609.31933","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.31933","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.31933","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.31933","pdf_url":"https://arxiv.org/pdf/2609.31933","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214794286.pdf","grobid_xml":"https://content.openalex.org/works/W7214794286.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W2767757834","https://openalex.org/W3110257065","https://openalex.org/W4221157442","https://openalex.org/W4283699596","https://openalex.org/W4288099666","https://openalex.org/W4298184813","https://openalex.org/W4384644594","https://openalex.org/W4391590782","https://openalex.org/W4403573401","https://openalex.org/W4403818631","https://openalex.org/W4407820100","https://openalex.org/W7114798229"],"related_works":["https://openalex.org/W7134852357","https://openalex.org/W4417262405","https://openalex.org/W7084076832","https://openalex.org/W7133199587","https://openalex.org/W4386793331","https://openalex.org/W7117663295","https://openalex.org/W4417357155","https://openalex.org/W4412836821","https://openalex.org/W7161560004","https://openalex.org/W7124160741"],"abstract_inverted_index":{"Native-latent":[0],"guidance":[1,30,41,75,97,130],"is":[2,93,123],"a":[3,25,33,70,113],"recent":[4],"paradigm":[5],"for":[6,72,125],"solving":[7],"inverse":[8,138],"problems":[9,139],"with":[10,28,76],"latent":[11,44,78],"diffusion":[12,79],"models.":[13,80],"It":[14],"replaces":[15],"repeated":[16],"evaluations":[17],"of":[18,59],"the":[19,57,96],"image-space":[20],"forward":[21],"model,":[22],"each":[23],"requiring":[24],"decoder":[26],"pass,":[27],"efficient":[29,73],"computed":[31],"using":[32],"learned":[34],"latent-space":[35],"surrogate.":[36],"However,":[37],"existing":[38,148],"methods":[39,149],"apply":[40],"uniformly":[42],"across":[43,63,135],"dimensions,":[45],"ignoring":[46],"that":[47,56,92,119,141],"measurements":[48],"are":[49],"informative":[50],"only":[51],"along":[52],"certain":[53],"directions":[54,102],"and":[55,65,89,103,117],"reliability":[58],"model":[60,115],"predictions":[61],"varies":[62],"inputs":[64],"timesteps.":[66],"We":[67,107],"propose":[68],"ANaLOG,":[69],"framework":[71,111],"uncertainty-aware":[74,121],"pretrained":[77],"ANaLOG":[81,142],"models":[82],"uncertainty":[83],"by":[84],"learning":[85],"an":[86],"anisotropic,":[87,120],"input-":[88],"time-dependent":[90],"covariance":[91],"integrated":[94],"into":[95],"mechanism":[98],"to":[99],"emphasize":[100],"reliable":[101],"downweight":[104],"uncertain":[105],"ones.":[106],"theoretically":[108],"analyze":[109],"this":[110],"in":[112],"linear":[114],"setting":[116],"prove":[118],"weighting":[122],"necessary":[124],"correct":[126],"sampling,":[127],"whereas":[128],"isotropic":[129],"induces":[131],"sampling":[132],"errors.":[133],"Experiments":[134],"five":[136],"challenging":[137],"show":[140],"improves":[143],"perceptual":[144],"reconstruction":[145],"quality":[146],"over":[147],"while":[150],"preserving":[151],"efficiency.":[152]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}