{"id":"https://openalex.org/W7127099830","doi":"https://doi.org/10.48550/arxiv.2601.22920","title":"Q-Hawkeye: Reliable Visual Policy Optimization for Image Quality Assessment","display_name":"Q-Hawkeye: Reliable Visual Policy Optimization for Image Quality Assessment","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7127099830","doi":"https://doi.org/10.48550/arxiv.2601.22920"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.22920","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.22920","pdf_url":"https://arxiv.org/pdf/2601.22920","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.22920","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107746266","display_name":"Wulin Xie","orcid":"https://orcid.org/0009-0000-9535-4116","observed_orcids":["https://orcid.org/0009-0000-9535-4116"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie, Wulin","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences , Beijing , China","University of Chinese Academy of Sciences , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125697267","display_name":"Rui Dai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dai, Rui","raw_affiliation_strings":["Amap , Alibaba Group , Hangzhou , China","Project Leader "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amap , Alibaba Group , Hangzhou , China","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Project Leader ","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124761737","display_name":"Ruidong Ding","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding, Ruidong","raw_affiliation_strings":["Amap , Alibaba Group , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amap , Alibaba Group , Hangzhou , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123207034","display_name":"Kaikui Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Kaikui","raw_affiliation_strings":["Amap , Alibaba Group , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amap , Alibaba Group , Hangzhou , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101512474","display_name":"Xiangxiang Chu","orcid":"https://orcid.org/0000-0003-2548-0605","observed_orcids":["https://orcid.org/0000-0003-2548-0605"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chu, Xiangxiang","raw_affiliation_strings":["Amap , Alibaba Group , Hangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Amap , Alibaba Group , Hangzhou , China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047633782","display_name":"Xinwen Hou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hou, Xinwen","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017617923","display_name":"Jie Wen","orcid":"https://orcid.org/0000-0001-9554-2379","observed_orcids":["https://orcid.org/0000-0001-9554-2379"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen, Jie","raw_affiliation_strings":["Harbin Institute of Technology , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology , Shenzhen , China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9961000084877014,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.9961000084877014,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.0005000000237487257,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.00039999998989515007,"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/image-quality-assessment","display_name":"image quality assessment","score":0.9990000128746033},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5149999856948853},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7590000033378601},{"id":"https://openalex.org/keywords/uncertainty-estimation","display_name":"uncertainty estimation","score":0.6320000290870667},{"id":"https://openalex.org/keywords/perceptual-reliability","display_name":"perceptual reliability","score":0.6499999761581421},{"id":"https://openalex.org/keywords/policy-optimization","display_name":"policy optimization","score":0.5149999856948853},{"id":"https://openalex.org/keywords/perceptual-quality-prediction","display_name":"perceptual quality prediction","score":0.46399998664855957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7057999968528748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6421999931335449},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6320000290870667},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5985999703407288},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5674999952316284},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5496000051498413},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5257999897003174},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5250999927520752},{"id":"https://openalex.org/C55020928","wikidata":"https://www.wikidata.org/wiki/Q3813865","display_name":"Image quality","level":3,"score":0.5102999806404114},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.4943000078201294},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.487199991941452},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.4738999903202057},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4390000104904175},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.3853999972343445},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.36000001430511475},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.34450000524520874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.32199999690055847},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.26089999079704285}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.22920","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.22920","pdf_url":"https://arxiv.org/pdf/2601.22920","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2601.22920","doi":"https://doi.org/10.48550/arxiv.2601.22920","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.22920","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.22920","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.22920","pdf_url":"https://arxiv.org/pdf/2601.22920","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7127099830.pdf","grobid_xml":"https://content.openalex.org/works/W7127099830.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W2143331230","https://openalex.org/W2148848374","https://openalex.org/W2754213847","https://openalex.org/W3002992380","https://openalex.org/W3035712445","https://openalex.org/W3044937051","https://openalex.org/W4221161695","https://openalex.org/W4301400622","https://openalex.org/W4321594373","https://openalex.org/W4382462760","https://openalex.org/W4386076169","https://openalex.org/W4387010079","https://openalex.org/W4390438010","https://openalex.org/W4391631327","https://openalex.org/W4407633293","https://openalex.org/W4407794264","https://openalex.org/W4411113087","https://openalex.org/W4414580753","https://openalex.org/W4415023986","https://openalex.org/W4416036816","https://openalex.org/W4416037161","https://openalex.org/W4416424590","https://openalex.org/W4416529508","https://openalex.org/W4417095764","https://openalex.org/W4417300720","https://openalex.org/W4417408676","https://openalex.org/W4417537776","https://openalex.org/W6910471724","https://openalex.org/W6910693295","https://openalex.org/W6929620718","https://openalex.org/W7083493645","https://openalex.org/W7120022702","https://openalex.org/W7160205379"],"related_works":["https://openalex.org/W4415023986","https://openalex.org/W4416424590","https://openalex.org/W7168358913","https://openalex.org/W7137985266","https://openalex.org/W7154289368","https://openalex.org/W7118274590","https://openalex.org/W3021151504","https://openalex.org/W4416274346","https://openalex.org/W7090856074","https://openalex.org/W2754425236"],"abstract_inverted_index":{"Image":[0],"Quality":[1],"Assessment":[2],"(IQA)":[3],"predicts":[4],"perceptual":[5,132],"quality":[6,23,158],"scores":[7,113],"consistent":[8],"with":[9],"human":[10],"judgments.":[11],"Recent":[12],"RL-based":[13,85],"IQA":[14],"methods":[15,45,171],"built":[16],"on":[17,20],"MLLMs":[18],"focus":[19],"generating":[21],"visual":[22,72,87,162],"descriptions":[24],"and":[25,101,117,141,145,172,180],"scores,":[26],"ignoring":[27],"two":[28],"key":[29],"reliability":[30],"limitations:":[31],"(i)":[32],"although":[33],"the":[34,70,93,109,153],"model's":[35,71],"prediction":[36],"stability":[37],"varies":[38],"significantly":[39],"across":[40,114,175],"training":[41],"samples,":[42],"existing":[43],"GRPO-based":[44],"apply":[46],"uniform":[47],"advantage":[48],"weighting,":[49],"thereby":[50],"amplifying":[51],"noisy":[52],"signals":[53],"from":[54],"unstable":[55],"samples":[56],"in":[57,160],"gradient":[58],"updates;":[59],"(ii)":[60],"most":[61],"works":[62],"emphasize":[63],"text-grounded":[64],"reasoning":[65],"over":[66],"images":[67,140,144],"while":[68],"overlooking":[69],"perception":[73],"ability":[74],"of":[75,111,138],"image":[76],"content.":[77],"In":[78],"this":[79,119],"paper,":[80],"we":[81,134],"propose":[82],"Q-Hawkeye,":[83],"an":[84,147],"reliable":[86],"policy":[88,128],"optimization":[89],"framework":[90],"that":[91,151,167],"redesigns":[92],"learning":[94],"signal":[95],"through":[96],"unified":[97],"Uncertainty-Aware":[98],"Dynamic":[99],"Optimization":[100],"Perception-Aware":[102],"Optimization.":[103],"Q-Hawkeye":[104,168],"estimates":[105],"predictive":[106],"uncertainty":[107,120],"using":[108],"variance":[110],"predicted":[112],"multiple":[115,176],"rollouts":[116],"leverages":[118],"to":[121,155],"reweight":[122],"each":[123],"sample's":[124],"update":[125],"strength,":[126],"stabilizing":[127],"optimization.":[129],"To":[130],"strengthen":[131],"reliability,":[133],"construct":[135],"paired":[136],"inputs":[137],"degraded":[139],"their":[142],"original":[143],"introduce":[146],"Implicit":[148],"Perception":[149],"Loss":[150],"constrains":[152],"model":[154],"ground":[156],"its":[157],"judgments":[159],"genuine":[161],"evidence.":[163],"Extensive":[164],"experiments":[165],"demonstrate":[166],"outperforms":[169],"state-of-the-art":[170],"generalizes":[173],"better":[174],"datasets.":[177],"Our":[178],"dataset":[179],"code":[181],"are":[182],"available":[183],"at":[184],"https://github.com/AMAP-ML/Q-Hawkeye.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-02-03T00:00:00"}