{"id":"https://openalex.org/W7166719565","doi":"https://doi.org/10.48550/arxiv.2606.29837","title":"Robust Trajectory Distillation: Hybrid Reweighting Meets Teacher-Inspired Targets","display_name":"Robust Trajectory Distillation: Hybrid Reweighting Meets Teacher-Inspired Targets","publication_year":2026,"publication_date":"2026-06-29","ids":{"openalex":"https://openalex.org/W7166719565","doi":"https://doi.org/10.48550/arxiv.2606.29837"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.29837","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29837","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.2606.29837","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139667025","display_name":"Kaifeng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Kaifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139639874","display_name":"Lechao Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Lechao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139692255","display_name":"Jiyang Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139644137","display_name":"Shengeng Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Shengeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047301622","display_name":"F Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139658277","display_name":"Yantao Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Yantao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139647304","display_name":"Yaxiong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yaxiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139710357","display_name":"Tuanrui Hui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui, Tuanrui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139643756","display_name":"Zhun Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Zhun","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/T12535","display_name":"Machine Learning and Data Classification","score":0.8138999938964844,"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":0.8138999938964844,"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":0.029500000178813934,"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":0.02319999970495701,"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/noise","display_name":"Noise (video)","score":0.6958000063896179},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.6092000007629395},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.5874000191688538},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5407999753952026},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.505299985408783},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.47929999232292175},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.46779999136924744},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.4343000054359436}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7093999981880188},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6958000063896179},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6092000007629395},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5874000191688538},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5407999753952026},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.505299985408783},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.47929999232292175},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.46779999136924744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4537999927997589},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3499999940395355},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3418999910354614},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30820000171661377},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.2953000068664551},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.2825999855995178},{"id":"https://openalex.org/C132459708","wikidata":"https://www.wikidata.org/wiki/Q744069","display_name":"Extrapolation","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.2770000100135803},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C86781634","wikidata":"https://www.wikidata.org/wiki/Q2478325","display_name":"Environmental noise","level":3,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.29837","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29837","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.2606.29837","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29837","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dataset":[0],"distillation":[1],"(DD)":[2],"condenses":[3],"large":[4],"corpora":[5],"into":[6,105],"compact,":[7,62],"information-rich":[8],"subsets":[9],"for":[10],"efficient":[11],"training":[12],"and":[13,50,76,118,143,150,163,176],"reuse.":[14],"However,":[15],"under":[16,153],"noisy":[17,154],"supervision,":[18],"DD":[19,70,171],"risks":[20],"condensing":[21],"corrupted":[22],"associations":[23],"together":[24],"with":[25,43,58,101,148],"useful":[26],"signals,":[27],"degrading":[28],"robustness.":[29],"Conventional":[30],"noisy-label":[31],"remedies":[32],"(sample":[33],"selection,":[34],"loss":[35],"weighting,":[36],"label":[37],"correction)":[38],"tightly":[39],"couple":[40],"noise":[41,75],"estimation":[42],"model":[44],"optimization,":[45],"often":[46],"require":[47],"clean":[48,83,112],"anchors,":[49],"can":[51],"amplify":[52],"confirmation":[53],"bias-assumptions":[54],"that":[55,72,110],"are":[56],"misaligned":[57],"DD's":[59],"goal":[60],"of":[61],"plug-and-play":[63],"supervision.":[64,155],"We":[65],"therefore":[66],"propose":[67],"a":[68,106],"trajectory-based":[69],"framework":[71,157],"jointly":[73],"suppresses":[74],"preserves":[77],"transferable":[78],"knowledge":[79],"without":[80],"relabeling":[81],"or":[82],"subsets.":[84],"It":[85],"comprises":[86],"two":[87],"complementary":[88],"components:":[89],"Selective":[90],"Guidance":[91],"Reweighting":[92],"(SGR),":[93],"which":[94,123],"fuses":[95],"global":[96],"forgetting":[97],"patterns":[98],"(second-split":[99],"forgetting)":[100],"local":[102],"neighborhood":[103],"consistency":[104],"progressive":[107],"reweighting":[108],"scheme":[109],"prioritizes":[111],"supervision":[113],"along":[114],"the":[115],"teacher":[116,131],"trajectory;":[117],"Teacher-Inspired":[119],"Auxiliary":[120],"Targets":[121],"(TIAT),":[122],"inject":[124],"auxiliary":[125],"residual":[126],"guidance":[127],"distilled":[128,146],"from":[129],"intermediate":[130],"dynamics":[132],"to":[133],"reinforce":[134],"informative":[135],"signals":[136],"while":[137],"remaining":[138],"internally":[139],"consistent.":[140],"Together,":[141],"SGR":[142],"TIAT":[144],"produce":[145],"datasets":[147],"cleaner":[149],"richer":[151],"representations":[152],"The":[156],"is":[158],"robust,":[159],"label-preserving,":[160],"computationally":[161],"lightweight,":[162],"broadly":[164],"applicable,":[165],"yielding":[166],"consistent":[167],"gains":[168],"over":[169],"state-of-the-art":[170],"baselines":[172],"across":[173],"symmetric,":[174],"asymmetric,":[175],"real-world":[177],"noise.":[178]},"counts_by_year":[],"updated_date":"2026-07-01T06:29:00.853634","created_date":"2026-07-01T00:00:00"}