{"id":"https://openalex.org/W4415539611","doi":"https://doi.org/10.1145/3746027.3758207","title":"GOBench: Benchmarking Geometric Optics Generation and Understanding of MLLMs","display_name":"GOBench: Benchmarking Geometric Optics Generation and Understanding of MLLMs","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539611","doi":"https://doi.org/10.1145/3746027.3758207"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3758207","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102861796","display_name":"Xiaorong Zhu","orcid":"https://orcid.org/0009-0004-9145-3829"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaorong Zhu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-9145-3829","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075029034","display_name":"Ziheng Jia","orcid":"https://orcid.org/0009-0002-2623-4756"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziheng Jia","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0002-2623-4756","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115594995","display_name":"Jiarui Wang","orcid":"https://orcid.org/0009-0005-9890-2698"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiarui Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-9890-2698","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiangyu Zhao","orcid":"https://orcid.org/0009-0009-1313-9451"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangyu Zhao","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China and Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-1313-9451","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China and Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028468431","display_name":"Haodong Duan","orcid":"https://orcid.org/0000-0002-3052-4177"},"institutions":[{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":null,"type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haodong Duan","raw_affiliation_strings":["Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3052-4177","affiliations":[{"raw_affiliation_string":"Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4391012619"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043405654","display_name":"Xiongkuo Min","orcid":"https://orcid.org/0000-0001-5693-0416"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiongkuo Min","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5693-0416","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100404634","display_name":"Jia Wang","orcid":"https://orcid.org/0000-0002-1714-3206"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-1714-3206","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101797192","display_name":"Zicheng Zhang","orcid":"https://orcid.org/0000-0002-7247-7938"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zicheng Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China and Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7247-7938","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China and Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064168853","display_name":"Guangtao Zhai","orcid":"https://orcid.org/0000-0001-8165-9322"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangtao Zhai","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China and Shanghai AI Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8165-9322","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China and Shanghai AI Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12690","last_page":"12697"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9675999879837036,"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":0.9675999879837036,"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/construct","display_name":"Construct (python library)","score":0.6877999901771545},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6819999814033508},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.566100001335144},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5181999802589417},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.49239999055862427},{"id":"https://openalex.org/keywords/geometrical-optics","display_name":"Geometrical optics","score":0.4047999978065491},{"id":"https://openalex.org/keywords/physical-optics","display_name":"Physical optics","score":0.3978999853134155}],"concepts":[{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6877999901771545},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6819999814033508},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.635699987411499},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.566100001335144},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5181999802589417},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.49239999055862427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4187999963760376},{"id":"https://openalex.org/C110277352","wikidata":"https://www.wikidata.org/wiki/Q467980","display_name":"Geometrical optics","level":2,"score":0.4047999978065491},{"id":"https://openalex.org/C154236941","wikidata":"https://www.wikidata.org/wiki/Q942347","display_name":"Physical optics","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.334199994802475},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.31459999084472656},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28850001096725464},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C199639397","wikidata":"https://www.wikidata.org/wiki/Q1788588","display_name":"Engineering drawing","level":1,"score":0.2818000018596649},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2809999883174896},{"id":"https://openalex.org/C92630104","wikidata":"https://www.wikidata.org/wiki/Q4115103","display_name":"Optical imaging","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.263700008392334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26100000739097595},{"id":"https://openalex.org/C40319758","wikidata":"https://www.wikidata.org/wiki/Q5535477","display_name":"Geometric design","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3758207","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3758207","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1933349210","https://openalex.org/W3095319910","https://openalex.org/W4312933868","https://openalex.org/W4387954093","https://openalex.org/W4393149524","https://openalex.org/W4401362547","https://openalex.org/W4402753874","https://openalex.org/W4405221137","https://openalex.org/W4405595839","https://openalex.org/W4415354699"],"related_works":[],"abstract_inverted_index":{"The":[0,127,143],"rapid":[1],"evolution":[2],"of":[3,22,69,123],"Multi-modality":[4],"Large":[5],"Language":[6],"Models":[7],"(MLLMs)":[8],"is":[9],"driving":[10],"significant":[11,135],"advancements":[12],"in":[13,31,137,165],"visual":[14],"understanding":[15,110,121],"and":[16,59,73,97,141,154,169],"generation.":[17],"Nevertheless,":[18],"a":[19,161],"comprehensive":[20],"assessment":[21],"their":[23],"capabilities,":[24],"concerning":[25],"the":[26,43,78,88,109,119,155],"fine-grained":[27],"physical":[28],"principles":[29],"especially":[30],"geometric":[32,70],"optics,":[33],"remains":[34],"underexplored.":[35],"To":[36],"address":[37],"this":[38],"gap,":[39],"we":[40,112],"introduce":[41],"GOBench,":[42],"first":[44],"benchmark":[45],"to":[46,76,86,117],"systematically":[47],"evaluate":[48],"MLLMs'":[49,101],"ability":[50,122],"across":[51],"two":[52],"tasks:":[53],"1)":[54],"Generating":[55],"Optically":[56],"Authentic":[57],"Imagery":[58],"2)":[60],"Understanding":[61],"Underlying":[62],"Optical":[63,93],"Phenomena.":[64],"We":[65,81],"curate":[66],"high-quality":[67],"prompts":[68],"optical":[71,106,120,139,166],"scenarios":[72],"use":[74],"MLLMs":[75],"construct":[77],"GOBench-Gen-1k":[79],"dataset.":[80],"then":[82],"organize":[83],"subjective":[84],"experiments":[85],"assess":[87],"generated":[89],"imagery":[90],"based":[91],"on":[92],"Authenticity,":[94],"Aesthetic":[95],"Quality,":[96],"Instruction":[98],"Fidelity,":[99],"revealing":[100],"generation":[102,140,152],"flaws":[103],"that":[104,131],"violate":[105],"principles.":[107],"For":[108],"task,":[111],"apply":[113],"crafted":[114],"evaluation":[115],"instructions":[116],"test":[118],"eleven":[124],"prominent":[125],"MLLMs.":[126],"experimental":[128],"results":[129],"demonstrate":[130],"current":[132],"models":[133],"face":[134],"challenges":[136],"both":[138],"understanding.":[142,167],"top-performing":[144],"generative":[145],"model,":[146,158],"GPT-4o-Image,":[147],"cannot":[148],"perfectly":[149],"complete":[150],"all":[151],"tasks,":[153],"best-performing":[156],"MLLM":[157],"Gemini-2.5Pro,":[159],"attains":[160],"mere":[162],"37.35%":[163],"accuracy":[164],"Database":[168],"codes":[170],"are":[171],"publicly":[172],"available":[173],"at:":[174],"https://github.com/aiben-ch/GOBench.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}