{"id":"https://openalex.org/W7222391945","doi":null,"title":"Adaptive Deep Learning for Vision and Multimodal Understanding with Heterogeneous Data","display_name":"Adaptive Deep Learning for Vision and Multimodal Understanding with Heterogeneous Data","publication_year":2026,"publication_date":"2026-10-12","ids":{"openalex":"https://openalex.org/W7222391945"},"language":"en","primary_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt3h17286t","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/3h17286t","pdf_url":"https://escholarship.org/content/qt3h17286t/qt3h17286t.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"etd"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://escholarship.org/content/qt3h17286t/qt3h17286t.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065940713","display_name":"Youwei Liang","orcid":"https://orcid.org/0000-0003-4670-7645","observed_orcids":["https://orcid.org/0000-0003-4670-7645"]},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Liang, Youwei","raw_affiliation_strings":["Doctor of Philosophy in Electrical Engineering (Machine Learning and Data Science ) University of California San Diego , 2026"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Doctor of Philosophy in Electrical Engineering (Machine Learning and Data Science ) University of California San Diego , 2026","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5065940713"],"corresponding_institution_ids":["https://openalex.org/I36258959"],"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7749000191688538,"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":0.7749000191688538,"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":0.20419999957084656,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.014399999752640724,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adaptive-learning","display_name":"adaptive learning","score":0.7929999828338623},{"id":"https://openalex.org/keywords/data-heterogeneity","display_name":"data heterogeneity","score":0.9169999957084656},{"id":"https://openalex.org/keywords/vision-transformer","display_name":"vision transformer","score":0.7200000286102295},{"id":"https://openalex.org/keywords/token-selection","display_name":"token selection","score":0.5759999752044678},{"id":"https://openalex.org/keywords/molecular-graphs","display_name":"molecular graphs","score":0.5059999823570251},{"id":"https://openalex.org/keywords/smiles","display_name":"SMILES","score":0.5299999713897705},{"id":"https://openalex.org/keywords/cryo-electron-tomography","display_name":"cryo-electron tomography","score":0.8389999866485596},{"id":"https://openalex.org/keywords/particle-picking","display_name":"particle picking","score":0.9810000061988831},{"id":"https://openalex.org/keywords/noisy-labels","display_name":"label noise","score":0.6729999780654907},{"id":"https://openalex.org/keywords/label-correction","display_name":"label correction","score":0.8080000281333923},{"id":"https://openalex.org/keywords/class-imbalance","display_name":"class imbalance","score":0.6610000133514404},{"id":"https://openalex.org/keywords/meta-learning","display_name":"meta-learning","score":0.8259999752044678},{"id":"https://openalex.org/keywords/data-reweighting","display_name":"data reweighting","score":0.7820000052452087},{"id":"https://openalex.org/keywords/multimodal-alignment","display_name":"multimodal alignment","score":0.40400001406669617},{"id":"https://openalex.org/keywords/rare-classes","display_name":"rare classes","score":0.39899998903274536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473999857902527},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7336999773979187},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6679999828338623},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5633000135421753},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48260000348091125},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4778999984264374},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44290000200271606},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4106000065803528},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3215000033378601},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3190000057220459},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.314300000667572},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.3077000081539154},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3034000098705292},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.274399995803833},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.26089999079704285},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:escholarship.org:ark:/13030/qt3h17286t","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/3h17286t","pdf_url":"https://escholarship.org/content/qt3h17286t/qt3h17286t.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"etd"}],"best_oa_location":{"id":"pmh:oai:escholarship.org:ark:/13030/qt3h17286t","doi":null,"is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/3h17286t","pdf_url":"https://escholarship.org/content/qt3h17286t/qt3h17286t.pdf","source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"etd"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7222391945.pdf","grobid_xml":"https://content.openalex.org/works/W7222391945.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W992687842","https://openalex.org/W1655274992","https://openalex.org/W1690739335","https://openalex.org/W1738019091","https://openalex.org/W1821462560","https://openalex.org/W1845051632","https://openalex.org/W2060531713","https://openalex.org/W2178031510","https://openalex.org/W2179423374","https://openalex.org/W2279490987","https://openalex.org/W2325237720","https://openalex.org/W2608353599","https://openalex.org/W2707890836","https://openalex.org/W2894175828","https://openalex.org/W2896457183","https://openalex.org/W2899663614","https://openalex.org/W2948018782","https://openalex.org/W2964121744","https://openalex.org/W2970608575","https://openalex.org/W2994673210","https://openalex.org/W2996290406","https://openalex.org/W3014974815","https://openalex.org/W3033188311","https://openalex.org/W3033529678","https://openalex.org/W3035030897","https://openalex.org/W3091156754","https://openalex.org/W3092462694","https://openalex.org/W3121523901","https://openalex.org/W3133696297","https://openalex.org/W3137278571","https://openalex.org/W3137963805","https://openalex.org/W3138516171","https://openalex.org/W3146097248","https://openalex.org/W3152694111","https://openalex.org/W3159481202","https://openalex.org/W3159732141","https://openalex.org/W3168124404","https://openalex.org/W3170188883","https://openalex.org/W3202698164","https://openalex.org/W3202715235","https://openalex.org/W3203166921","https://openalex.org/W3203418141","https://openalex.org/W3204647170","https://openalex.org/W3213235722","https://openalex.org/W4226483979","https://openalex.org/W4320005767","https://openalex.org/W4322718191","https://openalex.org/W4327810158","https://openalex.org/W4389523661","https://openalex.org/W7116072043"],"related_works":["https://openalex.org/W6885140044","https://openalex.org/W4415196398","https://openalex.org/W4382766735","https://openalex.org/W2922199553","https://openalex.org/W4413146254","https://openalex.org/W4387642367","https://openalex.org/W7164006350","https://openalex.org/W7157678433","https://openalex.org/W3168463823","https://openalex.org/W2399950394"],"abstract_inverted_index":{"Large-scale":[0],"pretraining":[1],"has":[2],"produced":[3],"powerful":[4],"deep":[5],"learning":[6,103,367,380],"representations,":[7],"but":[8,69],"real-world":[9],"data":[10,25,325,371],"rarely":[11],"match":[12],"the":[13,250,344,366],"clean,":[14],"uniform":[15],"assumptions":[16],"of":[17,89,253,365],"standard":[18],"transfer":[19],"learning.":[20],"This":[21,99,191],"dissertation":[22,100],"uses":[23,166],"heterogeneous":[24,122,270,375],"to":[26,82,85,94,158,169,343,349,372],"describe":[27],"settings":[28,77],"in":[29,33,75,175,272],"which":[30,80],"information":[31,81],"differs":[32],"modality,":[34],"representation,":[35],"relevance,":[36],"quality,":[37],"or":[38,44,64,137,235,351],"frequency":[39],"across":[40,308],"inputs,":[41],"outputs,":[42,378],"tasks,":[43,124],"supervision.":[45,383],"Examples":[46],"include":[47],"molecules":[48],"represented":[49,216],"as":[50,104,217],"graphs,":[51,219],"images,":[52,221],"strings,":[53,223],"and":[54,60,67,91,125,132,178,224,242,258,264,277,305,323,338,358,377,379],"text;":[55],"images":[56,243],"containing":[57],"both":[58],"informative":[59],"redundant":[61],"regions;":[62],"noisy":[63],"incomplete":[65],"labels;":[66],"rare":[68,350],"important":[70,171],"classes.":[71,354],"Applying":[72],"pretrained":[73,245],"models":[74],"these":[76,333],"requires":[78],"deciding":[79],"process,":[83,373],"how":[84,92],"connect":[86],"different":[87],"forms":[88],"information,":[90],"much":[93],"trust":[95],"each":[96,340],"supervision":[97,134,293],"signal.":[98],"develops":[101],"adaptive":[102,111,119,133,146,207,292],"a":[105,128,183,273,283,316,319,324],"unifying":[106],"approach":[107],"through":[108,282],"three":[109],"paradigms:":[110],"selection":[112,147],"focuses":[113],"computation":[114,157,196],"on":[115,261],"useful":[116],"input":[117],"components;":[118],"alignment":[120,208],"maps":[121],"modalities,":[123],"outputs":[126],"into":[127,182,249],"shared":[129,274],"predictive":[130],"space;":[131],"adjusts":[135],"imperfect":[136,336,382],"imbalanced":[138,307],"training":[139],"signals.":[140],"The":[141,202,287],"first":[142],"contribution,":[143,204,289],"EViT,":[144,356],"demonstrates":[145,206,291],"for":[148,209,294],"efficient":[149],"Vision":[150,153],"Transformers.":[151],"Standard":[152],"Transformers":[154],"devote":[155],"equal":[156],"all":[159],"image":[160],"patches":[161],"despite":[162],"substantial":[163],"redundancy.":[164],"EViT":[165],"class-token":[167],"attention":[168],"identify":[170],"tokens,":[172],"preserves":[173],"them":[174,248],"subsequent":[176],"layers,":[177],"fuses":[179],"inattentive":[180],"tokens":[181],"compact":[184],"representation":[185,275],"rather":[186],"than":[187],"discarding":[188],"their":[189],"context.":[190],"progressive":[192],"token":[193],"reorganization":[194],"reduces":[195],"while":[197,227],"maintaining":[198],"accurate":[199],"visual":[200],"recognition.":[201],"second":[203],"DrugChat,":[205,357],"multimodal":[210],"molecular":[211,240,262],"prediction.":[212],"Molecules":[213],"can":[214],"be":[215],"chemical":[218],"rendered":[220],"SMILES":[222],"natural-language":[225],"prompts,":[226],"predictions":[228],"may":[229],"require":[230],"labels,":[231],"probabilities,":[232],"categorical":[233],"decisions,":[234],"free-form":[236],"descriptions.":[237],"DrugChat":[238],"encodes":[239],"graphs":[241],"with":[244],"encoders,":[246],"projects":[247],"latent":[251],"space":[252,276],"an":[254],"instruction-following":[255],"language":[256],"model,":[257],"conditions":[259],"generation":[260],"structure":[263],"task":[265],"prompts.":[266],"It":[267],"thereby":[268],"aligns":[269],"inputs":[271],"expresses":[278],"diverse":[279],"prediction":[280],"targets":[281],"common":[284],"language-generation":[285],"interface.":[286],"third":[288],"RobPicker,":[290],"cryo-electron":[295],"tomography":[296],"particle":[297,353],"picking,":[298],"where":[299],"annotations":[300],"are":[301],"expensive,":[302],"incomplete,":[303],"noisy,":[304],"highly":[306],"macromolecular":[309],"species.":[310],"Its":[311],"meta-learning":[312],"framework":[313],"jointly":[314],"trains":[315],"segmentation":[317],"network,":[318,322],"label":[320],"correction":[321],"reweighting":[326],"network.":[327],"Guided":[328],"by":[329],"cleaner":[330],"validation":[331],"data,":[332],"components":[334],"refine":[335],"labels":[337],"adapt":[339],"subtomogram's":[341],"contribution":[342],"loss,":[345],"giving":[346],"greater":[347],"influence":[348],"small":[352],"Together,":[355],"RobPicker":[359],"apply":[360],"adaptation":[361],"at":[362],"complementary":[363],"levels":[364],"pipeline:":[368],"selecting":[369],"what":[370],"aligning":[374],"representations":[376],"from":[381]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-16T00:00:00"}