{"id":"https://openalex.org/W7166800294","doi":"https://doi.org/10.18653/v1/2026.findings-acl.519","title":"SimpleOCR: Rendering Visual Questions to Teach MLLMs to Read","display_name":"SimpleOCR: Rendering Visual Questions to Teach MLLMs to Read","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166800294","doi":"https://doi.org/10.18653/v1/2026.findings-acl.519"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.519","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.519","pdf_url":"https://aclanthology.org/2026.findings-acl.519.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.519.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139721876","display_name":"Yibo Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yibo Peng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139809635","display_name":"Peng Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng Xia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139833016","display_name":"Ding Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding Zhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125507472","display_name":"Kaide Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kaide Zeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139834416","display_name":"Siwei Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siwei Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139755764","display_name":"Yiyang Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yiyang Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139846000","display_name":"Jiaqi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaqi Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139761576","display_name":"Ruiyi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruiyi Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139790117","display_name":"Huaxiu Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huaxiu Yao","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.78965847,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10697","last_page":"10710"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.3885999917984009,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.3885999917984009,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.10509999841451645,"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/T11587","display_name":"Second Language Acquisition and Learning","score":0.053599998354911804,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.4341000020503998},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.36070001125335693},{"id":"https://openalex.org/keywords/line-drawings","display_name":"Line drawings","score":0.27649998664855957},{"id":"https://openalex.org/keywords/data-visualization","display_name":"Data visualization","score":0.2635999917984009}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6516000032424927},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5148000121116638},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4341000020503998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3752000033855438},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.36070001125335693},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31839999556541443},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3052000105381012},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.296999990940094},{"id":"https://openalex.org/C2983864324","wikidata":"https://www.wikidata.org/wiki/Q16872183","display_name":"Line drawings","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2630000114440918}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.519","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.519","pdf_url":"https://aclanthology.org/2026.findings-acl.519.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.519","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.519","pdf_url":"https://aclanthology.org/2026.findings-acl.519.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7816765308380127,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166800294.pdf","grobid_xml":"https://content.openalex.org/works/W7166800294.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,38,49,89,113,120,132,156],"rapid":[2],"advancements":[3],"in":[4,27,37,88],"Multimodal":[5],"Large":[6],"Language":[7],"Models":[8],"(MLLMs),":[9],"a":[10,70,81,93,103,109],"critical":[11],"question":[12],"regarding":[13],"their":[14],"visual":[15,64,139],"grounding":[16],"mechanism":[17],"remains":[18],"unanswered:":[19],"do":[20,30],"these":[21],"models":[22,79],"genuinely":[23],"\"read\"":[24],"text":[25,39,54,140],"embedded":[26],"images,":[28],"or":[29],"they":[31],"merely":[32],"rely":[33],"on":[34,68,112,164],"parametric":[35],"shortcuts":[36],"prompt?In":[40],"this":[41,45,98],"work,":[42],"we":[43,100],"diagnose":[44],"issue":[46],"by":[47,159,167],"introducing":[48],"Visualized-Question":[50],"(VQ)":[51],"setting,":[52,91],"where":[53],"queries":[55],"are":[56],"rendered":[57],"directly":[58],"onto":[59],"images":[60,166],"to":[61,86,134,198],"structurally":[62],"mandate":[63],"engagement.Our":[65],"diagnostic":[66],"experiments":[67],"Qwen2.5-VLreveal":[69],"startling":[71],"capability-utilization":[72],"gap:":[73],"despite":[74],"possessing":[75],"strong":[76],"OCR":[77],"capabilities,":[78],"suffer":[80],"performance":[82,176],"degradation":[83],"of":[84],"up":[85],"12.7%":[87],"VQ":[90,121],"exposing":[92],"deepseated":[94],"\"modality":[95],"laziness.\"To":[96],"bridge":[97],"gap,":[99],"propose":[101],"SimpleOCR,":[102],"plug-and-play":[104,187],"training":[105,117],"strategy":[106],"that":[107],"imposes":[108],"structural":[110],"constraint":[111],"learning":[114],"process.By":[115],"transforming":[116],"samples":[118,180],"into":[119],"format":[122],"with":[123,177,192],"randomized":[124],"styles,":[125],"SimpleOCR":[126,143],"effectively":[127],"invalidates":[128],"text-based":[129],"shortcuts,":[130],"compelling":[131],"model":[133,158],"activate":[135],"and":[136,161],"optimize":[137],"its":[138,186],"extraction":[141],"pathways.Empirically,":[142],"yields":[144],"robust":[145],"gains":[146],"without":[147],"architectural":[148],"modifications.On":[149],"four":[150],"representative":[151],"OOD":[152],"benchmarks,":[153],"it":[154],"surpasses":[155],"base":[157],"5.4%":[160],"GRPO":[162],"based":[163],"original":[165],"2.7%,":[168],"while":[169],"exhibiting":[170],"extreme":[171],"data":[172],"efficiency,":[173],"achieving":[174],"superior":[175],"30x":[178],"fewer":[179],"(8.5K)":[181],"than":[182],"recent":[183],"RL-based":[184],"methods.Furthermore,":[185],"nature":[188],"allows":[189],"seamless":[190],"integration":[191],"advanced":[193],"RL":[194],"strategies":[195],"like":[196],"NoisyRollout":[197],"yield":[199],"complementary":[200],"improvements.Code":[201],"is":[202],"available":[203],"at":[204],"https://github.com/aiming-lab/SimpleOCR.":[205]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}