{"id":"https://openalex.org/W7113903671","doi":"https://doi.org/10.1145/3757376.3771402","title":"Lost in the Interface: How Structured UI Complexity Challenges Large Vision Language Models in Games","display_name":"Lost in the Interface: How Structured UI Complexity Challenges Large Vision Language Models in Games","publication_year":2025,"publication_date":"2025-12-10","ids":{"openalex":"https://openalex.org/W7113903671","doi":"https://doi.org/10.1145/3757376.3771402"},"language":null,"primary_location":{"id":"doi:10.1145/3757376.3771402","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757376.3771402","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Technical Communications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3757376.3771402","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiang Li","orcid":"https://orcid.org/0009-0002-6012-9183"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":["Hokkaido University, Sapporo, Japan"],"raw_orcid":"https://orcid.org/0009-0002-6012-9183","affiliations":[{"raw_affiliation_string":"Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ren Togo","orcid":"https://orcid.org/0000-0002-4474-3995"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ren Togo","raw_affiliation_strings":["Hokkaido University, Sapporo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4474-3995","affiliations":[{"raw_affiliation_string":"Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Keisuke Maeda","orcid":"https://orcid.org/0000-0001-8039-3462"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Maeda","raw_affiliation_strings":["Hokkaido University, Sapporo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8039-3462","affiliations":[{"raw_affiliation_string":"Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Takahiro Ogawa","orcid":"https://orcid.org/0000-0001-5332-8112"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Ogawa","raw_affiliation_strings":["Hokkaido University, Sapporo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5332-8112","affiliations":[{"raw_affiliation_string":"Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":null,"display_name":"Miki Haseyama","orcid":"https://orcid.org/0000-0003-1496-1761"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Miki Haseyama","raw_affiliation_strings":["Hokkaido University, Sapporo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1496-1761","affiliations":[{"raw_affiliation_string":"Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205349734"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7364000082015991,"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":0.7364000082015991,"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/T10799","display_name":"Data Visualization and Analytics","score":0.03720000013709068,"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/T12031","display_name":"Speech and dialogue systems","score":0.01860000006854534,"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/key","display_name":"Key (lock)","score":0.5819000005722046},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.5370000004768372},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.49239999055862427},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4731000065803528},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4456000030040741},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.35510000586509705}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.762499988079071},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.5963000059127808},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5819000005722046},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.5370000004768372},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.49239999055862427},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4731000065803528},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4456000030040741},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3504999876022339},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3010999858379364},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.25870001316070557}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3757376.3771402","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757376.3771402","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Technical Communications","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3757376.3771402","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3757376.3771402","pdf_url":null,"source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the SIGGRAPH Asia 2025 Technical Communications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1573822705","https://openalex.org/W2574978968","https://openalex.org/W2902907165","https://openalex.org/W3209391877"],"related_works":[],"abstract_inverted_index":{"Current":[0],"Large":[1],"Vision-Language":[2],"Models":[3],"(LVLMs)":[4],"have":[5],"struggled":[6],"to":[7,17],"interpret":[8],"complex":[9],"game":[10],"user":[11],"interfaces":[12],"(UIs).":[13],"LVLMs":[14,33,61,81],"frequently":[15],"failing":[16],"distinguish":[18],"core":[19],"gameplay":[20],"components":[21],"from":[22],"irrelevant":[23],"elements.":[24],"These":[25],"insights":[26],"highlight":[27],"both":[28],"the":[29,35,53,58],"limitations":[30],"of":[31,37,60],"existing":[32],"and":[34,82,92],"importance":[36],"incorporating":[38],"UI":[39,63,79],"complexity":[40,64],"as":[41,72],"a":[42,73],"key":[43],"factor":[44],"in":[45],"evaluation.":[46],"To":[47],"overcome":[48],"this":[49,70],"limitation,":[50],"we":[51],"introduce":[52],"first":[54],"benchmark":[55],"for":[56],"evaluating":[57],"performance":[59],"against":[62],"across":[65],"different":[66],"games.":[67],"We":[68],"consider":[69],"work":[71],"stepping":[74],"stone":[75],"toward":[76],"building":[77],"more":[78],"aware":[80],"enabling":[83],"domain-specific":[84],"evaluations":[85],"that":[86],"better":[87],"capture":[88],"real-world":[89],"challenges.":[90],"Code":[91],"data":[93],"are":[94],"publicly":[95],"available":[96],"at":[97],"https://github.com/XiangLiSky/Lost-in-the-interface":[98]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-11T00:00:00"}
