{"id":"https://openalex.org/W4416034217","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.889","title":"VisualEDU: A Benchmark for Assessing Coding and Visual Comprehension through Educational Problem-Solving Video Generation","display_name":"VisualEDU: A Benchmark for Assessing Coding and Visual Comprehension through Educational Problem-Solving Video Generation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034217","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.889"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.889","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.889","pdf_url":"https://aclanthology.org/2025.findings-emnlp.889.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.889.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100353490","display_name":"Hao Chen","orcid":"https://orcid.org/0000-0001-8090-8593"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5097166659","display_name":"Tianyu Shi","orcid":"https://orcid.org/0009-0006-6579-2565"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianyu Shi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Pengran Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengran Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031476612","display_name":"Zeyuan Li","orcid":"https://orcid.org/0000-0003-1691-9487"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeyuan Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023225646","display_name":"Jiahui Pan","orcid":"https://orcid.org/0000-0002-7576-6743"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiahui Pan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086038509","display_name":"Qianglong Chen","orcid":"https://orcid.org/0000-0002-7845-1544"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qianglong Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5112502954","display_name":"Lewei He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lewei He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.4954,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86507817,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"16363","last_page":"16394"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11516","display_name":"Visual and Cognitive Learning Processes","score":0.23800000548362732,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11516","display_name":"Visual and Cognitive Learning Processes","score":0.23800000548362732,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10533","display_name":"Teaching and Learning Programming","score":0.22419999539852142,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.030400000512599945,"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/coding","display_name":"Coding (social sciences)","score":0.6008999943733215},{"id":"https://openalex.org/keywords/comprehension","display_name":"Comprehension","score":0.583899974822998},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4214000105857849},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.33469998836517334}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7106000185012817},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.6008999943733215},{"id":"https://openalex.org/C511192102","wikidata":"https://www.wikidata.org/wiki/Q5156948","display_name":"Comprehension","level":2,"score":0.583899974822998},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.564300000667572},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4636000096797943},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4214000105857849},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3246999979019165},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3018999993801117},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2946999967098236},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2736999988555908},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27000001072883606},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.889","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.889","pdf_url":"https://aclanthology.org/2025.findings-emnlp.889.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.889","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.889","pdf_url":"https://aclanthology.org/2025.findings-emnlp.889.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6059964893","display_name":null,"funder_award_id":"STI 2030","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6812169155","display_name":null,"funder_award_id":"2023A1515140100","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G6948817555","display_name":null,"funder_award_id":"52308250","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8252633260","display_name":null,"funder_award_id":"2022ZD0208900","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034217.pdf","grobid_xml":"https://content.openalex.org/works/W4416034217.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generating":[0],"logically":[1],"coherent":[2],"video":[3,39],"from":[4],"text":[5],"(T2V)":[6],"for":[7,17,41,65,125],"reasoning-intensive":[8],"tasks":[9,107],"like":[10],"mathematical":[11],"problem-solving":[12],"presents":[13],"a":[14,24,45,56,122],"significant":[15],"challenge":[16],"Vision-Language":[18],"Models":[19],"(VLMs).Therefore,":[20],"we":[21],"introduce":[22],"VisualEDU,":[23],"benchmark":[25],"based":[26],"on":[27,105],"Manim":[28],"package":[29],"to":[30,60],"rigorously":[31],"evaluate":[32],"VLM":[33,135],"capabilities":[34],"in":[35,111,129,137],"producing":[36],"coherent,":[37],"step-by-step":[38],"solutions":[40],"educational":[42],"purposes,":[43],"with":[44,92],"framework":[46],"that":[47,82],"integrates":[48],"meta-prompt":[49],"learning,":[50],"visual":[51,71,114],"and":[52,55,70,75,117,132],"code":[53,112],"feedback,":[54],"modular":[57],"drawing":[58],"toolkit":[59],"enhance":[61],"output":[62],"quality.Novel":[63],"metrics":[64],"temporal":[66],"consistency,":[67],"logical":[68],"correctness,":[69],"clarity":[72],"are":[73,102],"proposed,":[74],"extensive":[76],"experiments":[77],"across":[78],"nine":[79],"VLMs":[80],"reveal":[81],"while":[83],"advanced":[84],"proprietary":[85],"models":[86],"show":[87],"promise,":[88],"all":[89],"struggle":[90],"significantly":[91],"increasing":[93],"task":[94],"complexity":[95],"(e.g.,":[96],"the":[97],"performances":[98],"of":[99],"Claude-3.7-Sonnetand":[100],"GPT-4o":[101],"below":[103],"56%":[104],"difficult":[106],"),":[108],"highlighting":[109],"limitations":[110],"generation,":[113],"feedback":[115],"correction":[116],"precise":[118],"tool":[119],"invocation.VisualEDU":[120],"offers":[121],"robust":[123],"platform":[124],"systematic":[126],"T2V":[127],"assessment":[128],"reasoningintensive":[130],"domains":[131],"guides":[133],"future":[134],"improvements":[136],"this":[138],"area.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}