{"id":"https://openalex.org/W7141124124","doi":"https://doi.org/10.48550/arxiv.2603.24965","title":"Self-Corrected Image Generation with Explainable Latent Rewards","display_name":"Self-Corrected Image Generation with Explainable Latent Rewards","publication_year":2026,"publication_date":"2026-03-26","ids":{"openalex":"https://openalex.org/W7141124124","doi":"https://doi.org/10.48550/arxiv.2603.24965"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.24965","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24965","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.24965","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053386173","display_name":"Yinyi Luo","orcid":"https://orcid.org/0000-0001-8465-8325"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Luo, Yinyi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120695829","display_name":"Hrishikesh Gokhale","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gokhale, Hrishikesh","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130778218","display_name":"Marios Savvides","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Savvides, Marios","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130757000","display_name":"Jindong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jindong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130747921","display_name":"Shengfeng He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Shengfeng","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5053386173"],"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":0.3684999942779541,"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":0.3684999942779541,"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":0.32749998569488525,"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/T10028","display_name":"Topic Modeling","score":0.05350000038743019,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.7014999985694885},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6360999941825867},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.6079999804496765},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.585099995136261},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.576200008392334},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5177000164985657},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4296000003814697}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7936999797821045},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7014999985694885},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6360999941825867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6310999989509583},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.6079999804496765},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.585099995136261},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.576200008392334},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5177000164985657},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4296000003814697},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.350600004196167},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2915000021457672},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2896000146865845},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.2890999913215637},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.26589998602867126}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.24965","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24965","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.24965","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.24965","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":"article"},"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":{"Despite":[0],"significant":[1],"progress":[2],"in":[3],"text-to-image":[4],"generation,":[5,28],"aligning":[6],"outputs":[7],"with":[8],"complex":[9],"prompts":[10],"remains":[11],"challenging,":[12],"particularly":[13],"for":[14],"fine-grained":[15],"semantics":[16],"and":[17,115,124,133],"spatial":[18],"relations.":[19],"This":[20,107],"difficulty":[21],"stems":[22],"from":[23,82,92,103],"the":[24,36,110],"feed-forward":[25],"nature":[26],"of":[27],"which":[29],"requires":[30],"anticipating":[31],"alignment":[32,132],"without":[33],"fully":[34],"understanding":[35],"output.":[37],"In":[38],"contrast,":[39],"evaluating":[40],"generated":[41],"images":[42],"is":[43,88,141],"more":[44],"tractable.":[45],"Motivated":[46],"by":[47],"this":[48],"asymmetry,":[49],"we":[50],"propose":[51],"xLARD,":[52],"a":[53,71,89],"self-correcting":[54],"framework":[55],"that":[56,74,128],"uses":[57],"multimodal":[58],"large":[59],"language":[60],"models":[61],"to":[62,95,112],"guide":[63],"generation":[64,123],"through":[65],"Explainable":[66],"LAtent":[67],"RewarDs.":[68],"xLARD":[69,129],"introduces":[70],"lightweight":[72],"corrector":[73],"refines":[75],"latent":[76,93],"representations":[77],"based":[78],"on":[79],"structured":[80],"feedback":[81],"model-generated":[83],"references.":[84],"A":[85],"key":[86],"component":[87],"differentiable":[90],"mapping":[91],"edits":[94],"interpretable":[96],"reward":[97],"signals,":[98],"enabling":[99],"continuous":[100],"latent-level":[101],"guidance":[102],"non-differentiable":[104],"image-level":[105],"evaluations.":[106],"mechanism":[108],"allows":[109],"model":[111],"understand,":[113],"assess,":[114],"correct":[116],"itself":[117],"during":[118],"generation.":[119],"Experiments":[120],"across":[121],"diverse":[122],"editing":[125],"tasks":[126],"show":[127],"improves":[130],"semantic":[131],"visual":[134],"fidelity":[135],"while":[136],"maintaining":[137],"generative":[138],"priors.":[139],"Code":[140],"available":[142],"at":[143],"https://yinyiluo.github.io/xLARD/.":[144]},"counts_by_year":[],"updated_date":"2026-03-28T06:16:51.555046","created_date":"2026-03-28T00:00:00"}