{"id":"https://openalex.org/W4414580498","doi":"https://doi.org/10.18653/v1/2026.findings-acl.166","title":"Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulation","display_name":"Talk to Your Slides: High-Efficiency Slide Editing via Language-Driven Structured Data Manipulation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414580498","doi":"https://doi.org/10.18653/v1/2026.findings-acl.166"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.166","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.166","pdf_url":"https://aclanthology.org/2026.findings-acl.166.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":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.166.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5107853730","display_name":"K. Jung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyudan Jung","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Hojun Cho","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hojun Cho","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041375258","display_name":"Jooyeol Yun","orcid":"https://orcid.org/0000-0001-7853-7703"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jooyeol Yun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031205975","display_name":"So\u2010Young Yang","orcid":"https://orcid.org/0000-0002-6850-3486"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soyoung Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052567003","display_name":"Jaehyeok Jang","orcid":"https://orcid.org/0000-0002-0781-5646"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaehyeok Jang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047912015","display_name":"Jaegul Choo","orcid":"https://orcid.org/0000-0003-1071-4835"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaegul Choo","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":0.0056034,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3370","last_page":"3399"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.98089998960495,"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":0.98089998960495,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9656999707221985,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9578999876976013,"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/robustness","display_name":"Robustness (evolution)","score":0.5200999975204468},{"id":"https://openalex.org/keywords/disk-formatting","display_name":"Disk formatting","score":0.5109000205993652},{"id":"https://openalex.org/keywords/data-manipulation-language","display_name":"Data manipulation language","score":0.42980000376701355},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.42559999227523804},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4004000127315521},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.3700000047683716},{"id":"https://openalex.org/keywords/hierarchical-database-model","display_name":"Hierarchical database model","score":0.3537999987602234},{"id":"https://openalex.org/keywords/image-manipulation","display_name":"Image manipulation","score":0.35089999437332153},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.34549999237060547},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.33340001106262207}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.871999979019165},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5200999975204468},{"id":"https://openalex.org/C88006597","wikidata":"https://www.wikidata.org/wiki/Q690117","display_name":"Disk formatting","level":2,"score":0.5109000205993652},{"id":"https://openalex.org/C56288433","wikidata":"https://www.wikidata.org/wiki/Q58673","display_name":"Data manipulation language","level":2,"score":0.42980000376701355},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.42559999227523804},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4004000127315521},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3953999876976013},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3741999864578247},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.3700000047683716},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.35089999437332153},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.33889999985694885},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C2777601897","wikidata":"https://www.wikidata.org/wiki/Q3409113","display_name":"Presentation (obstetrics)","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.3001999855041504},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.29919999837875366},{"id":"https://openalex.org/C20894473","wikidata":"https://www.wikidata.org/wiki/Q1116105","display_name":"Object model","level":3,"score":0.2962999939918518},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.29490000009536743},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.2797999978065491},{"id":"https://openalex.org/C55282118","wikidata":"https://www.wikidata.org/wiki/Q252683","display_name":"Snapshot (computer storage)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2639999985694885},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2590999901294708},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C73752529","wikidata":"https://www.wikidata.org/wiki/Q79872","display_name":"Object-oriented programming","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.25540000200271606},{"id":"https://openalex.org/C2777080924","wikidata":"https://www.wikidata.org/wiki/Q334667","display_name":"Storyboard","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.251800000667572},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.25130000710487366},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.166","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.166","pdf_url":"https://aclanthology.org/2026.findings-acl.166.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"},{"id":"pmh:oai:arXiv.org:2505.11604","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11604","pdf_url":"https://arxiv.org/pdf/2505.11604","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"pmh:oai:arXiv.org:2505.11604","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.11604","pdf_url":"https://arxiv.org/pdf/2505.11604","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,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:doi:10.48550/arxiv.2505.11604","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2505.11604","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.11604","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.166","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.166","pdf_url":"https://aclanthology.org/2026.findings-acl.166.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":[],"awards":[{"id":"https://openalex.org/G3736587842","display_name":null,"funder_award_id":"RS-2019-II190075","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G4468082379","display_name":null,"funder_award_id":"RS-2019-II190075","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G8705040809","display_name":null,"funder_award_id":"RS-2025-02304967","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320324161","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414580498.pdf","grobid_xml":"https://content.openalex.org/works/W4414580498.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Editing":[0],"presentation":[1],"slides":[2],"is":[3],"a":[4,58,105,150,158],"frequent":[5],"yet":[6],"tedious":[7],"task,":[8],"ranging":[9],"from":[10],"creative":[11],"layout":[12,35],"design":[13],"to":[14,144,162],"repetitive":[15],"text":[16],"maintenance.While":[17],"recent":[18],"GUI-based":[19,145],"agents":[20],"powered":[21],"by":[22],"Multimodal":[23],"LLMs":[24],"(MLLMs)":[25],"excel":[26],"at":[27,138,176],"tasks":[28],"requiring":[29],"visual":[30,101],"perception,":[31],"such":[32],"as":[33],"spatial":[34],"adjustments,":[36],"they":[37],"often":[38],"incur":[39],"high":[40],"computational":[41],"costs":[42],"and":[43,122,136,167,172],"latency":[44],"when":[45],"handling":[46],"structured,":[47],"text-centric,":[48],"or":[49],"batch":[50],"processing":[51],"tasks.In":[52],"this":[53],"paper,":[54],"we":[55,147],"propose":[56],"TALK-TO-YOUR-SLIDES,":[57],"high-efficiency":[59],"slide":[60],"editing":[61],"agent":[62],"that":[63,108,119],"operates":[64,137],"via":[65],"language-driven":[66],"structured":[67],"data":[68],"manipulation":[69],"rather":[70],"than":[71],"relying":[72],"on":[73],"the":[74,78,97],"image":[75],"modality.By":[76],"leveraging":[77],"underlying":[79],"object":[80],"model":[81],"instead":[82],"of":[83,99],"screen":[84],"pixels,":[85],"our":[86,125],"approach":[87],"ensures":[88],"precise":[89],"content":[90],"modification":[91],"while":[92],"preserving":[93],"style":[94],"fidelity,":[95,135],"addressing":[96],"limitations":[98],"OCR-based":[100],"agents.Our":[102],"system":[103],"features":[104],"hierarchical":[106],"architecture":[107],"effectively":[109],"bridges":[110],"high-level":[111],"user":[112],"instructions":[113],"with":[114],"low-level":[115],"execution":[116],"codes.Experiments":[117],"demonstrate":[118],"for":[120],"text-centric":[121],"formatting":[123],"tasks,":[124],"method":[126],"enables":[127],"34%":[128,132],"faster":[129],"processing,":[130],"achieves":[131],"better":[133],"instruction":[134],"an":[139],"87%":[140],"lower":[141],"cost":[142],"compared":[143],"baselines.Furthermore,":[146],"introduce":[148],"TSBENCH,":[149],"humanverified":[151],"benchmark":[152,173],"dataset":[153],"comprising":[154],"379":[155],"instructions,":[156],"including":[157],"HARD":[159],"subset":[160],"designed":[161],"evaluate":[163],"robustness":[164],"against":[165],"complex":[166],"visually":[168],"dependent":[169],"queries.Our":[170],"code":[171],"are":[174],"available":[175],"here.":[177]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}