{"id":"https://openalex.org/W7138332259","doi":"https://doi.org/10.1609/aaai.v40i11.37902","title":"Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding","display_name":"Robust-R1: Degradation-Aware Reasoning for Robust Visual Understanding","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138332259","doi":"https://doi.org/10.1609/aaai.v40i11.37902"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i11.37902","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37902","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i11.37902","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129724057","display_name":"Jiaqi Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaqi Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129691091","display_name":"Jianmin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianmin Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129649610","display_name":"Wei Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129671677","display_name":"Xiaogang Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaogang Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065755228","display_name":"RunTao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Runtao Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129725459","display_name":"Xiangyu Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangyu Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121034648","display_name":"Qipeng Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qipeng Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129675631","display_name":"Jiafei Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiafei Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129692205","display_name":"Lei Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129731521","display_name":"Qifeng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qifeng Chen","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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"11","first_page":"9421","last_page":"9429"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3544999957084656,"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":0.3544999957084656,"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":0.10400000214576721,"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/T11019","display_name":"Image Enhancement Techniques","score":0.06509999930858612,"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/interpretability","display_name":"Interpretability","score":0.9061999917030334},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.6219000220298767},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5551999807357788},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47929999232292175},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4551999866962433},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4083000123500824},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.40619999170303345},{"id":"https://openalex.org/keywords/degradation","display_name":"Degradation (telecommunications)","score":0.4016999900341034}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9061999917030334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7732999920845032},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6833999752998352},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6219000220298767},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5551999807357788},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47929999232292175},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47600001096725464},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4551999866962433},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4083000123500824},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.40619999170303345},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40459999442100525},{"id":"https://openalex.org/C2779679103","wikidata":"https://www.wikidata.org/wiki/Q5251805","display_name":"Degradation (telecommunications)","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3540000021457672},{"id":"https://openalex.org/C2778251979","wikidata":"https://www.wikidata.org/wiki/Q7936617","display_name":"Visual processing","level":3,"score":0.33559998869895935},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.2547000050544739}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1609/aaai.v40i11.37902","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37902","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-171644","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-171644","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"},{"id":"pmh:oai:ojs.aaai.org:article/37902","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/37902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i11.37902","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i11.37902","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1787580432","display_name":null,"funder_award_id":"62536007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3420112582","display_name":null,"funder_award_id":"62372379","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3820912390","display_name":null,"funder_award_id":"24ZDCYJSGG0003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5981921176","display_name":null,"funder_award_id":"62472359","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"struggle":[4],"to":[5,85],"maintain":[6],"reliable":[7],"performance":[8,147],"under":[9,148],"extreme":[10],"real-world":[11,105,139],"visual":[12,31,54,106],"degradations,":[13],"which":[14],"impede":[15],"their":[16],"practical":[17],"robustness.":[18],"Existing":[19],"robust":[20,135],"MLLMs":[21],"predominantly":[22],"rely":[23],"on":[24,30,137,152],"implicit":[25],"training/adaptation":[26],"that":[27,51],"focuses":[28],"solely":[29],"encoder":[32],"generalization,":[33],"suffering":[34],"from":[35],"limited":[36],"interpretability":[37],"and":[38,78,123,134,155],"isolated":[39],"optimization.":[40],"To":[41,88],"overcome":[42],"these":[43],"limitations,":[44],"we":[45,92],"propose":[46],"Robust-R1,":[47],"a":[48,94],"novel":[49],"framework":[50],"explicitly":[52],"models":[53],"degradations":[55,100,151],"through":[56],"structured":[57,112],"reasoning":[58,68,81,121],"chains.":[59],"Our":[60],"approach":[61],"integrates:":[62],"(i)":[63],"supervised":[64],"fine-tuning":[65],"for":[66,73],"degradation-aware":[67],"foundations,":[69],"(ii)":[70],"reward-driven":[71],"alignment":[72],"accurately":[74],"perceiving":[75],"degradation":[76,86,115,140],"parameters,":[77,116],"(iii)":[79],"dynamic":[80],"depth":[82],"scaling":[83],"adapted":[84],"intensity.":[87],"facilitate":[89],"this":[90],"approach,":[91],"introduce":[93],"specialized":[95],"11K":[96],"dataset":[97],"featuring":[98],"realistic":[99],"synthesized":[101],"across":[102],"four":[103],"critical":[104],"processing":[107],"stages,":[108],"each":[109],"annotated":[110],"with":[111],"chains":[113],"connecting":[114],"perceptual":[117],"influence,":[118],"pristine":[119],"semantic":[120],"chain,":[122],"conclusion.":[124],"Comprehensive":[125],"evaluations":[126],"demonstrate":[127],"state-of-theart":[128],"robustness:":[129],"Robust-R1":[130],"outperforms":[131],"all":[132],"general":[133],"baselines":[136],"the":[138],"benchmark":[141],"R-Bench,":[142],"while":[143],"maintaining":[144],"superior":[145],"anti-degradation":[146],"multi-intensity":[149],"adversarial":[150],"MMMB,":[153],"MMStar,":[154],"RealWorldQA.":[156]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}