{"id":"https://openalex.org/W4416981724","doi":"https://doi.org/10.48550/arxiv.2512.01675","title":"GRASP: Guided Residual Adapters with Sample-wise Partitioning","display_name":"GRASP: Guided Residual Adapters with Sample-wise Partitioning","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W4416981724","doi":"https://doi.org/10.48550/arxiv.2512.01675"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2512.01675","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.01675","pdf_url":"https://arxiv.org/pdf/2512.01675","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.01675","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120712470","display_name":"Felix N\u00fctzel","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"N\u00fctzel, Felix","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012312857","display_name":"Mischa Dombrowski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dombrowski, Mischa","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078127596","display_name":"Bernhard Kainz","orcid":"https://orcid.org/0000-0002-7813-5023"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kainz, Bernhard","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5120712470"],"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.35929998755455017,"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":0.35929998755455017,"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/T10862","display_name":"AI in cancer detection","score":0.24809999763965607,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.10779999941587448,"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/residual","display_name":"Residual","score":0.6668000221252441},{"id":"https://openalex.org/keywords/grasp","display_name":"GRASP","score":0.6570000052452087},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5001999735832214},{"id":"https://openalex.org/keywords/leak","display_name":"Leak","score":0.4968000054359436},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4659000039100647},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4449999928474426},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.384799987077713},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.362199991941452},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.35920000076293945},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3546000123023987}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6883000135421753},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6668000221252441},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.6570000052452087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5006999969482422},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5001999735832214},{"id":"https://openalex.org/C2780378346","wikidata":"https://www.wikidata.org/wiki/Q1349983","display_name":"Leak","level":2,"score":0.4968000054359436},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4659000039100647},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4449999928474426},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3833000063896179},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3546000123023987},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.34709998965263367},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.33880001306533813},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.32989999651908875},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31839999556541443},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.28769999742507935},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2840000092983246},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C2777317252","wikidata":"https://www.wikidata.org/wiki/Q18393516","display_name":"Rare events","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.27079999446868896},{"id":"https://openalex.org/C38858127","wikidata":"https://www.wikidata.org/wiki/Q5441228","display_name":"Feed forward","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.2606000006198883},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.25690001249313354},{"id":"https://openalex.org/C99821215","wikidata":"https://www.wikidata.org/wiki/Q1136583","display_name":"Swap (finance)","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.250900000333786},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2512.01675","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.01675","pdf_url":"https://arxiv.org/pdf/2512.01675","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2512.01675","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.01675","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":"pmh:oai:arXiv.org:2512.01675","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.01675","pdf_url":"https://arxiv.org/pdf/2512.01675","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"Recent":[0],"advances":[1],"in":[2,16,34],"text-to-image":[3],"diffusion":[4,184],"models":[5,14,117],"enable":[6],"high-fidelity":[7],"generation":[8],"across":[9],"diverse":[10],"prompts.":[11],"However,":[12],"these":[13],"falter":[15],"long-tail":[17,136],"settings,":[18],"such":[19],"as":[20,64],"medical":[21],"imaging,":[22],"where":[23],"rare":[24,61,148],"pathologies":[25],"comprise":[26],"a":[27,68],"small":[28],"fraction":[29],"of":[30,46,157],"data.":[31],"This":[32],"results":[33],"mode":[35],"collapse:":[36],"tail-class":[37],"outputs":[38],"lack":[39],"quality":[40],"and":[41,60,132,143,155,180],"diversity,":[42],"undermining":[43],"the":[44,65,83,135],"goal":[45],"synthetic":[47],"data":[48],"augmentation":[49],"for":[50,130,147,166],"underrepresented":[51],"conditions.":[52],"We":[53],"pinpoint":[54],"gradient":[55,111],"conflicts":[56],"between":[57],"frequent":[58],"head":[59],"tail":[62,167],"classes":[63],"primary":[66],"culprit,":[67],"factor":[69],"unaddressed":[70],"by":[71,118],"existing":[72],"sampling":[73],"or":[74],"conditioning":[75],"methods":[76],"that":[77,108],"mainly":[78],"steer":[79],"inference":[80],"without":[81],"altering":[82],"learned":[84,128],"distribution.":[85],"To":[86],"resolve":[87],"this,":[88],"we":[89],"propose":[90],"GRASP:":[91],"Guided":[92],"Residual":[93],"Adapters":[94],"with":[95,183],"Sample-wise":[96],"Partitioning.":[97],"GRASP":[98,139],"uses":[99],"external":[100],"priors":[101],"to":[102,170],"statically":[103],"partition":[104],"samples":[105],"into":[106,123],"clusters":[107],"minimize":[109],"intra-group":[110],"clashes.":[112],"It":[113],"then":[114],"fine-tunes":[115],"pre-trained":[116],"injecting":[119],"cluster-specific":[120],"residual":[121],"adapters":[122],"transformer":[124],"feedforward":[125],"layers,":[126],"bypassing":[127],"gating":[129],"stability":[131],"efficiency.":[133],"On":[134],"MIMIC-CXR-LT":[137],"dataset,":[138],"yields":[140],"superior":[141],"FID":[142],"diversity":[144],"metrics,":[145],"especially":[146],"classes,":[149],"outperforming":[150],"baselines":[151],"like":[152],"vanilla":[153],"fine-tuning":[154],"Mixture":[156],"Experts":[158],"variants.":[159],"Downstream":[160],"classification":[161],"on":[162],"NIH-CXR-LT":[163],"improves":[164],"considerably":[165],"labels.":[168],"Generalization":[169],"ImageNet-LT":[171],"confirms":[172],"broad":[173],"applicability.":[174],"Our":[175],"method":[176],"is":[177],"lightweight,":[178],"scalable,":[179],"readily":[181],"integrates":[182],"pipelines.":[185]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-12-03T00:00:00"}