{"id":"https://openalex.org/W7161559808","doi":"https://doi.org/10.48550/arxiv.2605.16081","title":"MIND: Decoupling Model-Induced Label Noise via Latent Manifold Disentanglement","display_name":"MIND: Decoupling Model-Induced Label Noise via Latent Manifold Disentanglement","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W7161559808","doi":"https://doi.org/10.48550/arxiv.2605.16081"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.16081","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16081","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":null,"license_id":null,"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.2605.16081","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136418196","display_name":"Dayong Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ren, Dayong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5136418196"],"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/T12535","display_name":"Machine Learning and Data Classification","score":0.730400025844574,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.730400025844574,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.05640000104904175,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.03449999913573265,"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/identifiability","display_name":"Identifiability","score":0.7455999851226807},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.6570000052452087},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5975000262260437},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5925999879837036},{"id":"https://openalex.org/keywords/manifold","display_name":"Manifold (fluid mechanics)","score":0.45170000195503235},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.3815999925136566},{"id":"https://openalex.org/keywords/nonlinear-dimensionality-reduction","display_name":"Nonlinear dimensionality reduction","score":0.3634999990463257},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.33820000290870667}],"concepts":[{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.7455999851226807},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.6570000052452087},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5975000262260437},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5925999879837036},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.588100016117096},{"id":"https://openalex.org/C529865628","wikidata":"https://www.wikidata.org/wiki/Q1790740","display_name":"Manifold (fluid mechanics)","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4496999979019165},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44290000200271606},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C151876577","wikidata":"https://www.wikidata.org/wiki/Q7049464","display_name":"Nonlinear dimensionality reduction","level":3,"score":0.3634999990463257},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33550000190734863},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.320499986410141},{"id":"https://openalex.org/C179024874","wikidata":"https://www.wikidata.org/wiki/Q5395728","display_name":"Errors-in-variables models","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C67226441","wikidata":"https://www.wikidata.org/wiki/Q1665389","display_name":"Robust statistics","level":3,"score":0.2865000069141388},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.27410000562667847},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C18015164","wikidata":"https://www.wikidata.org/wiki/Q6935000","display_name":"Multiplicative noise","level":5,"score":0.2558000087738037},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.16081","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16081","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.16081","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16081","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.40828239917755127,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"paradigm":[1],"of":[2],"learning":[3,62],"from":[4,36,133,173],"automatic":[5],"annotations":[6],"driven":[7],"by":[8],"pre-trained":[9],"experts":[10],"and":[11,168],"Foundation":[12,187],"Models":[13,175],"dominates":[14],"data-hungry":[15],"applications.":[16],"However,":[17],"it":[18],"introduces":[19],"a":[20,74,129,139,182],"critical":[21],"challenge:":[22],"model-induced":[23],"label":[24],"noise.":[25],"Unlike":[26],"stochastic":[27],"noise":[28,34,86,117,135],"in":[29],"classical":[30],"robust":[31,183],"learning,":[32],"this":[33,79],"stems":[35],"annotator":[37],"inductive":[38],"biases,":[39],"manifesting":[40],"as":[41,181],"systematic":[42],"errors":[43],"tightly":[44],"coupled":[45],"with":[46,112,155],"local":[47],"feature":[48],"manifolds.":[49,157],"Existing":[50],"methods":[51,163],"relying":[52],"on":[53,136,143,164],"global":[54],"transition":[55],"matrices":[56,64],"underfit":[57],"these":[58,165],"structural":[59,110,140],"patterns,":[60],"while":[61],"instance-specific":[63],"remains":[65],"mathematically":[66],"intractable.":[67],"We":[68,81],"propose":[69],"Model-Induced":[70],"Noise":[71],"Decoupling":[72,102],"(MIND),":[73],"theoretically":[75],"grounded":[76],"framework":[77,185],"addressing":[78],"dilemma.":[80],"demonstrate":[82],"that":[83],"the":[84],"high-dimensional":[85],"manifold":[87],"can":[88],"be":[89],"decoupled":[90],"into":[91,108],"tractable,":[92],"subspace-dependent":[93],"components":[94],"via":[95],"Latent":[96,101],"Manifold":[97],"Disentanglement.":[98],"Specifically,":[99],"our":[100],"Estimator":[103],"(LDE)":[104],"dynamically":[105],"projects":[106],"samples":[107],"latent":[109],"clusters":[111],"consistent":[113],"error":[114,151],"modes,":[115],"facilitating":[116],"identifiability":[118],"without":[119],"ground-truth":[120],"anchor":[121],"points.":[122],"To":[123],"rigorously":[124],"evaluate":[125],"robustness,":[126],"we":[127],"adopt":[128],"hierarchical":[130],"protocol:":[131],"moving":[132],"controlled":[134],"CIFAR-100":[137],"to":[138],"stress":[141],"test":[142],"large-scale":[144],"real-world":[145],"3D":[146],"datasets":[147],"(S3DIS,":[148],"ScanNet),":[149],"where":[150],"patterns":[152],"explicitly":[153],"couple":[154],"geometric":[156],"Empirically,":[158],"MIND":[159],"significantly":[160],"outperforms":[161],"state-of-the-art":[162],"complex":[166],"benchmarks":[167],"effectively":[169],"corrects":[170],"zero-shot":[171],"hallucinations":[172],"Vision-Language":[174],"(e.g.,":[176],"OpenSeg),":[177],"highlighting":[178],"its":[179],"potential":[180],"distillation":[184],"for":[186],"Models.":[188]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-19T00:00:00"}