{"id":"https://openalex.org/W7140161214","doi":"https://doi.org/10.48550/arxiv.2603.22187","title":"Seeing is Improving: Visual Feedback for Iterative Text Layout Refinement","display_name":"Seeing is Improving: Visual Feedback for Iterative Text Layout Refinement","publication_year":2026,"publication_date":"2026-03-23","ids":{"openalex":"https://openalex.org/W7140161214","doi":"https://doi.org/10.48550/arxiv.2603.22187"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.22187","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.22187","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.2603.22187","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Guo, Junrong","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Guo, Junrong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Fang, Shancheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Shancheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Qu, Yadong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qu, Yadong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Xie, Hongtao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Hongtao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"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":0.767300009727478,"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":0.767300009727478,"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":0.06509999930858612,"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"}},{"id":"https://openalex.org/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.03750000149011612,"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/readability","display_name":"Readability","score":0.6244000196456909},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5406000018119812},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.5281000137329102},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42719998955726624},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4244000017642975},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.376800000667572},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.374099999666214},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.37279999256134033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8381999731063843},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.6244000196456909},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5406000018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5389000177383423},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.5281000137329102},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42719998955726624},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4244000017642975},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4174000024795532},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39329999685287476},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.376800000667572},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3481999933719635},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3273000121116638},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.3165000081062317},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C3020716817","wikidata":"https://www.wikidata.org/wiki/Q4132092","display_name":"Visual feedback","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2922999858856201},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C117619785","wikidata":"https://www.wikidata.org/wiki/Q6094414","display_name":"Iterative learning control","level":3,"score":0.27410000562667847},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26109999418258667},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.2581999897956848}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.22187","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.22187","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.2603.22187","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.22187","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":[{"score":0.45766621828079224,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,71],"Multimodal":[3],"Large":[4],"Language":[5],"Models":[6],"(MLLMs)":[7],"have":[8],"enabled":[9],"automated":[10],"generation":[11,73],"of":[12,93],"structured":[13],"layouts":[14],"from":[15],"natural":[16],"language":[17],"descriptions.":[18],"Existing":[19],"methods":[20],"typically":[21],"follow":[22],"a":[23,68,81,123],"code-only":[24,165],"paradigm":[25],"that":[26,84,128,155],"generates":[27,109],"code":[28,176],"to":[29,39,47,55,102],"represent":[30],"layouts,":[31],"which":[32,98],"are":[33,45,179],"then":[34],"rendered":[35,49],"by":[36],"graphic":[37],"engines":[38],"produce":[40],"final":[41,136],"images.":[42],"However,":[43],"they":[44],"blind":[46],"the":[48,135,143],"visual":[50,65,86,100,168],"outcome,":[51,138],"making":[52],"it":[53],"difficult":[54],"guarantee":[56],"readability":[57],"and":[58,74,107,146,164,177],"aesthetics.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63,139],"identify":[64],"feedback":[66,87,169],"as":[67,170],"critical":[69,171],"factor":[70],"layout":[72,162],"propose":[75],"Visual":[76],"Feedback":[77],"Layout":[78],"Model":[79],"(VFLM),":[80],"self-improving":[82],"framework":[83],"leverages":[85,99],"iterative":[88,145],"refinement.":[89],"VFLM":[90,156],"is":[91,114,117],"capable":[92],"performing":[94],"adaptive":[95],"reflective":[96,147],"generation,":[97],"information":[101],"reflect":[103],"on":[104],"previous":[105],"issues":[106],"iteratively":[108],"outputs":[110],"until":[111],"satisfactory":[112],"quality":[113],"achieved.":[115],"It":[116],"achieved":[118],"through":[119],"reinforcement":[120],"learning":[121],"with":[122],"visually":[124],"grounded":[125],"reward":[126],"model":[127],"incorporates":[129],"OCR":[130],"accuracy.":[131],"By":[132],"rewarding":[133],"only":[134],"generated":[137],"can":[140],"effectively":[141],"stimulate":[142],"model's":[144],"generative":[148],"capabilities.":[149],"Experiments":[150],"across":[151],"multiple":[152],"benchmarks":[153],"show":[154],"consistently":[157],"outperforms":[158],"advanced":[159],"MLLMs,":[160],"existing":[161],"models,":[163],"baselines,":[166],"establishing":[167],"for":[172],"design-oriented":[173],"MLLMs.":[174],"Our":[175],"data":[178],"available":[180],"at":[181],"https://github.com/FolSpark/VFLM.":[182]},"counts_by_year":[],"updated_date":"2026-04-25T08:17:42.794288","created_date":"2026-03-25T00:00:00"}