{"id":"https://openalex.org/W7163645134","doi":"https://doi.org/10.48550/arxiv.2606.05949","title":"Faithful, Enriched, and Precise: Benchmarking Natural-Science Illustration Generation by T2I models","display_name":"Faithful, Enriched, and Precise: Benchmarking Natural-Science Illustration Generation by T2I models","publication_year":2026,"publication_date":"2026-06-04","ids":{"openalex":"https://openalex.org/W7163645134","doi":"https://doi.org/10.48550/arxiv.2606.05949"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.05949","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.05949","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.05949","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5010151006","display_name":"Yifan Chang","orcid":"https://orcid.org/0000-0003-2820-0840"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chang, Yifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137948801","display_name":"Jiaxin Ai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ai, Jiaxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138016008","display_name":"Jianwen Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Jianwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137957081","display_name":"Yuandong Pu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pu, Yuandong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137990746","display_name":"Siqi Luo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Siqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122344811","display_name":"Liangliang Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Liangliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137996884","display_name":"Yuchen Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Yuchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137962333","display_name":"Minghao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Minghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137988821","display_name":"Yunfei Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Yunfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138002857","display_name":"Yu Qiao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137924826","display_name":"Kaipeng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Kaipeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137945739","display_name":"Yihao Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yihao","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":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":0.4885999858379364,"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":0.4885999858379364,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.10180000215768814,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10799","display_name":"Data Visualization and Analytics","score":0.08500000089406967,"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/benchmarking","display_name":"Benchmarking","score":0.819599986076355},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7153000235557556},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.597100019454956},{"id":"https://openalex.org/keywords/scientific-modelling","display_name":"Scientific modelling","score":0.5077999830245972},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4036000072956085},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.35350000858306885}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.819599986076355},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7634999752044678},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7153000235557556},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.597100019454956},{"id":"https://openalex.org/C138379479","wikidata":"https://www.wikidata.org/wiki/Q1116876","display_name":"Scientific modelling","level":2,"score":0.5077999830245972},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.46399998664855957},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4284000098705292},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40860000252723694},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4036000072956085},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35350000858306885},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33410000801086426},{"id":"https://openalex.org/C2781083858","wikidata":"https://www.wikidata.org/wiki/Q17327049","display_name":"Scientific literature","level":2,"score":0.3160000145435333},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30970001220703125},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.2996000051498413},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C2992562121","wikidata":"https://www.wikidata.org/wiki/Q3817808","display_name":"Scientific reasoning","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.05949","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.05949","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.05949","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.05949","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7611933946609497}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scientific":[0],"illustrations":[1,70],"are":[2],"essential":[3],"tools":[4],"for":[5,33,160],"communicating":[6],"research":[7],"findings,":[8],"especially":[9],"in":[10,166],"natural":[11],"science,":[12],"where":[13],"they":[14],"visualize":[15],"complex":[16],"concepts":[17],"and":[18,54,74,86,95,107,120,136,148,162,175],"processes.":[19],"As":[20],"Text-to-Image":[21],"(T2I)":[22],"models":[23,84,99,165],"become":[24],"increasingly":[25],"capable,":[26],"researchers":[27],"have":[28],"started":[29],"to":[30],"use":[31],"them":[32],"scientific":[34,51,69,167],"illustration":[35,168],"generation.":[36,169],"However,":[37],"existing":[38],"benchmarks":[39],"often":[40],"assess":[41],"outputs":[42],"at":[43],"a":[44,62],"holistic":[45],"level,":[46],"overlooking":[47],"fine-grained":[48,91],"elements,":[49],"while":[50],"reasoning":[52,105,146],"ability":[53],"output":[55],"conciseness":[56],"remain":[57],"under-quantified.":[58],"We":[59],"introduce":[60],"FEPBench,":[61],"benchmark":[63],"built":[64],"from":[65,142],"carefully":[66],"selected":[67],"high-quality":[68],"across":[71,116],"multiple":[72],"disciplines":[73],"layout":[75,121],"types.":[76],"With":[77],"the":[78],"assistance":[79],"of":[80],"multimodal":[81],"large":[82],"language":[83],"(MLLMs)":[85],"human":[87],"experts,":[88],"we":[89],"provide":[90,157],"atom":[92,172],"set":[93,173],"annotations":[94],"systematically":[96],"evaluate":[97],"T2I":[98,164],"along":[100],"three":[101],"dimensions:":[102],"instruction":[103],"faithfulness,":[104],"enrichment,":[106,147],"semantic":[108],"precision.":[109,154],"Our":[110],"evaluation":[111,176],"further":[112],"decomposes":[113],"model":[114],"performance":[115],"visual,":[117],"textual,":[118],"relation,":[119],"elements.":[122],"Results":[123],"show":[124],"that":[125],"even":[126],"state-of-the-art":[127],"(SOTA)":[128],"closed-source":[129],"models,":[130],"such":[131],"as":[132],"GPT":[133],"Image":[134],"2":[135],"Nano":[137],"Banana":[138],"Pro,":[139],"still":[140],"suffer":[141],"text-rendering":[143],"bottlenecks,":[144],"limited":[145],"difficulty":[149],"balancing":[150],"generation":[151],"richness":[152],"with":[153],"These":[155],"findings":[156],"practical":[158],"guidance":[159],"improving":[161],"deploying":[163],"Benchmark":[170],"data,":[171],"annotations,":[174],"code":[177],"will":[178],"be":[179],"released":[180],"by":[181],"us.":[182]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-06T00:00:00"}