{"id":"https://openalex.org/W7166858751","doi":"https://doi.org/10.18653/v1/2026.acl-long.2097","title":"Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning","display_name":"Render-of-Thought: Rendering Textual Chain-of-Thought as Images for Visual Latent Reasoning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166858751","doi":"https://doi.org/10.18653/v1/2026.acl-long.2097"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.2097","doi":"https://doi.org/10.18653/v1/2026.acl-long.2097","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2097","pdf_url":"https://aclanthology.org/2026.acl-long.2097.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.acl-long.2097.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139746013","display_name":"Yifan Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4405263052","display_name":"Tsinghua Shenzhen International Graduate School","ror":"https://ror.org/01vceef04","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405263052","https://openalex.org/I99065089"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Wang","raw_affiliation_strings":["Shenzhen International Graduate School , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen International Graduate School , Tsinghua University","institution_ids":["https://openalex.org/I4405263052","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139809766","display_name":"Shiyu Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiyu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119840491","display_name":"Peiming Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiming Li","raw_affiliation_strings":["School of Electronic and Computer Engineering , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic and Computer Engineering , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038412984","display_name":"Xiaochen Yang","orcid":"https://orcid.org/0000-0002-9299-5951","observed_orcids":["https://orcid.org/0000-0002-9299-5951"]},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xiaochen Yang","raw_affiliation_strings":["School of Mathematics and Statistics , University of Glasgow"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mathematics and Statistics , University of Glasgow","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057269672","display_name":"Zheng Wei","orcid":"https://orcid.org/0000-0001-7444-2547","observed_orcids":["https://orcid.org/0000-0001-7444-2547"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5123543897","display_name":"Yang Tang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Tang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.48127765,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"45236","last_page":"45253"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8978999853134155,"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":0.8978999853134155,"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":0.0812000036239624,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.007699999958276749,"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/chain-of-thought-prompting","display_name":"chain-of-thought prompting","score":0.9279999732971191},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"visual reasoning","score":0.3869999945163727},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6589999794960022},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9179999828338623},{"id":"https://openalex.org/keywords/token-compression","display_name":"token compression","score":0.5860000252723694},{"id":"https://openalex.org/keywords/inference-acceleration","display_name":"inference acceleration","score":0.6940000057220459},{"id":"https://openalex.org/keywords/mathematical-reasoning","display_name":"mathematical reasoning","score":0.5320000052452087},{"id":"https://openalex.org/keywords/logical-reasoning","display_name":"logical reasoning","score":0.9819999933242798}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6675999760627747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6327999830245972},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5286999940872192},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5049999952316284},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.323199987411499},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2840999960899353},{"id":"https://openalex.org/C172367668","wikidata":"https://www.wikidata.org/wiki/Q6504956","display_name":"Data visualization","level":3,"score":0.24539999663829803},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.24490000307559967},{"id":"https://openalex.org/C36816356","wikidata":"https://www.wikidata.org/wiki/Q16911860","display_name":"3D rendering","level":3,"score":0.24140000343322754}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.2097","doi":"https://doi.org/10.18653/v1/2026.acl-long.2097","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2097","pdf_url":"https://aclanthology.org/2026.acl-long.2097.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:392597","doi":null,"is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/57667.html>","pdf_url":"https://eprints.gla.ac.uk/392597/2/392597.pdf","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"listed_in":["doaj"],"host_organization":"https://openalex.org/I4405259220","host_organization_name":"Institut Agama Islam Negeri Langsa","host_organization_lineage":["https://openalex.org/I4405259220"],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.2097","doi":"https://doi.org/10.18653/v1/2026.acl-long.2097","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2097","pdf_url":"https://aclanthology.org/2026.acl-long.2097.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166858751.pdf","grobid_xml":"https://content.openalex.org/works/W7166858751.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7127164814","https://openalex.org/W7127131438","https://openalex.org/W7129304271","https://openalex.org/W7127933762","https://openalex.org/W7197002998","https://openalex.org/W4415145351","https://openalex.org/W7161353660","https://openalex.org/W7166851948","https://openalex.org/W7162422688","https://openalex.org/W7211990310"],"abstract_inverted_index":{"Chain-of-Thought":[0],"(CoT)":[1],"prompting":[2,18],"has":[3],"achieved":[4],"remarkable":[5],"success":[6],"in":[7],"unlocking":[8],"the":[9,38,44,47,58,63,73,81,95,99,146],"reasoning":[10,40,49,64,116],"capabilities":[11],"of":[12,46,84,148],"Large":[13],"Language":[14,87],"Models":[15,88],"(LLMs).Although":[16],"CoT":[17],"enhances":[19],"reasoning,":[20],"its":[21],"verbosity":[22],"imposes":[23],"substantial":[24,127],"computational":[25],"overhead.Recent":[26],"works":[27],"often":[28],"focus":[29],"exclusively":[30],"on":[31,37,112],"outcome":[32],"alignment":[33],"and":[34,77,114,126],"lack":[35],"supervision":[36],"intermediate":[39],"process.These":[41],"deficiencies":[42],"obscure":[43],"analyzability":[45],"latent":[48,74],"chain.To":[50],"address":[51],"these":[52],"challenges,":[53],"we":[54,79],"introduce":[55],"Render-of-Thought":[56],"(RoT),":[57],"first":[59],"framework":[60],"to":[61,93,131,142],"reify":[62],"chain":[65],"by":[66],"rendering":[67],"textual":[68,100],"steps":[69],"into":[70],"images,":[71],"making":[72],"rationale":[75],"explicit":[76,132],"traceable.Specifically,":[78],"leverage":[80],"vision":[82,96],"encoders":[83],"existing":[85],"Vision":[86],"(VLMs)":[89],"as":[90],"semantic":[91],"anchors":[92],"align":[94],"embeddings":[97],"with":[98],"space.This":[101],"design":[102],"ensures":[103],"plug-and-play":[104],"implementation":[105],"without":[106],"incurring":[107],"additional":[108],"pre-training":[109],"overhead.Extensive":[110],"experiments":[111],"mathematical":[113],"logical":[115],"benchmarks":[117],"demonstrate":[118],"that":[119],"our":[120],"method":[121],"achieves":[122],"3-4\u00d7":[123],"token":[124],"compression":[125],"inference":[128],"acceleration":[129],"compared":[130,141],"CoT.Furthermore,":[133],"it":[134],"demonstrates":[135],"a":[136],"competitive":[137],"efficiency-accuracy":[138],"Pareto":[139],"exploration":[140],"other":[143],"methods,":[144],"validating":[145],"feasibility":[147],"this":[149],"paradigm.Our":[150],"code":[151],"is":[152],"available":[153],"at":[154],"https://github.com/TencentBAC/RoT":[155]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-07-02T00:00:00"}