{"id":"https://openalex.org/W7164031616","doi":"https://doi.org/10.48550/arxiv.2606.08063","title":"Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?","display_name":"Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?","publication_year":2026,"publication_date":"2026-06-06","ids":{"openalex":"https://openalex.org/W7164031616","doi":"https://doi.org/10.48550/arxiv.2606.08063"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.08063","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08063","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.2606.08063","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138279986","display_name":"Jiaqi Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jiaqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138216213","display_name":"Jianmin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jianmin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133561047","display_name":"Youyang Zhai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhai, Youyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138211373","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/A5138254849","display_name":"Runtao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Runtao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138235509","display_name":"Mengjie Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Mengjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138281713","display_name":"Xiangyu Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Xiangyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112964246","display_name":"Qingfa Xiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao, Qingfa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138211351","display_name":"Qifeng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Qifeng","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5112000107765198,"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":0.5112000107765198,"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":0.25040000677108765,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.04039999842643738,"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/robustness","display_name":"Robustness (evolution)","score":0.7705000042915344},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4406999945640564},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4027999937534332},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.38609999418258667},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.37599998712539673},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.35839998722076416},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.34610000252723694}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7705000042915344},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7286999821662903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6783000230789185},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4406999945640564},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.38609999418258667},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3675999939441681},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3650999963283539},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.34610000252723694},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.3163999915122986},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.28790000081062317},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.260699987411499},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.08063","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08063","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.2606.08063","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08063","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":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.792884349822998}],"awards":[],"funders":[],"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],"(MLLMs)":[4],"have":[5],"demonstrated":[6],"remarkable":[7],"success":[8],"in":[9],"visual":[10,19,55,73,104,148,162],"understanding,":[11],"yet":[12],"their":[13],"performance":[14,136],"degrades":[15],"significantly":[16],"under":[17,137],"real-world":[18,130],"corruptions.":[20],"While":[21],"existing":[22],"robustness":[23,127],"enhancement":[24],"approaches":[25],"exist,":[26],"they":[27],"are":[28],"limited:":[29],"black-box":[30],"feature":[31],"alignment":[32],"lacks":[33],"interpretability,":[34],"and":[35,97,106,116,133],"white-box":[36],"text-based":[37],"reasoning":[38,108,152],"cannot":[39],"restore":[40],"lost":[41],"pixel-level":[42],"details.":[43],"This":[44],"work":[45],"investigates":[46],"a":[47,65,157],"fundamental":[48],"research":[49],"question:":[50],"Can":[51],"MLLMs":[52,70],"recover":[53],"corrupted":[54,114],"content":[56],"by":[57],"themselves?":[58],"To":[59],"address":[60],"this,":[61],"we":[62],"propose":[63],"Robust-U1,":[64],"novel":[66],"framework":[67],"that":[68,109,123,146],"equips":[69],"with":[71,92],"explicit":[72],"self-recovery":[74,155],"capability":[75],"for":[76,87,101,160],"robust":[77,161],"understanding.":[78,163],"The":[79,164],"approach":[80],"comprises":[81],"three":[82],"core":[83],"stages:":[84],"supervised":[85],"fine-tuning":[86],"initial":[88],"reconstruction,":[89],"reinforcement":[90],"learning":[91],"dual":[93],"rewards":[94],"(pixel-level":[95],"SSIM":[96],"semantic-level":[98],"CLIP":[99],"similarity)":[100],"aligning":[102],"high":[103],"quality,":[105],"multimodal":[107],"jointly":[110],"considers":[111],"both":[112],"the":[113,117,129],"input":[115],"recovered":[118],"image.":[119],"Extensive":[120],"experiments":[121],"demonstrate":[122],"Robust-U1":[124],"achieves":[125],"state-of-the-art":[126],"on":[128,140],"corruption":[131],"benchmark":[132],"maintains":[134],"superior":[135],"adversarial":[138],"corruptions":[139],"general":[141],"VQA":[142],"benchmarks.":[143],"Analysis":[144],"confirms":[145],"high-quality":[147],"recovery":[149],"directly":[150],"enhances":[151],"performance,":[153],"establishing":[154],"as":[156],"critical":[158],"mechanism":[159],"source":[165],"code":[166],"is":[167],"available":[168],"at":[169],"https://github.com/jqtangust/Robust-U1.":[170]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-10T00:00:00"}