{"id":"https://openalex.org/W4401024343","doi":"https://doi.org/10.24963/ijcai.2024/696","title":"GRASP: A Novel Benchmark for Evaluating Language GRounding and Situated Physics Understanding in Multimodal Language Models","display_name":"GRASP: A Novel Benchmark for Evaluating Language GRounding and Situated Physics Understanding in Multimodal Language Models","publication_year":2024,"publication_date":"2024-07-26","ids":{"openalex":"https://openalex.org/W4401024343","doi":"https://doi.org/10.24963/ijcai.2024/696"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2024/696","doi":"https://doi.org/10.24963/ijcai.2024/696","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2024/696","pdf_url":"https://www.ijcai.org/proceedings/2024/0696.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.ijcai.org/proceedings/2024/0696.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Serwan Jassim","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170658231","display_name":"Osnabr\u00fcck University","ror":"https://ror.org/04qmmjx98","country_code":"DE","type":"education","lineage":["https://openalex.org/I170658231"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Serwan Jassim","raw_affiliation_strings":["Osnabr\u00fcck University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osnabr\u00fcck University","institution_ids":["https://openalex.org/I170658231"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mario Holubar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Mario Holubar","raw_affiliation_strings":["University of Amsterdam"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Annika Richter","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170658231","display_name":"Osnabr\u00fcck University","ror":"https://ror.org/04qmmjx98","country_code":"DE","type":"education","lineage":["https://openalex.org/I170658231"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Annika Richter","raw_affiliation_strings":["Osnabr\u00fcck University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osnabr\u00fcck University","institution_ids":["https://openalex.org/I170658231"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Cornelius Wolff","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170658231","display_name":"Osnabr\u00fcck University","ror":"https://ror.org/04qmmjx98","country_code":"DE","type":"education","lineage":["https://openalex.org/I170658231"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Cornelius Wolff","raw_affiliation_strings":["Osnabr\u00fcck University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osnabr\u00fcck University","institution_ids":["https://openalex.org/I170658231"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019662005","display_name":"Xenia Isabel Ohmer","orcid":"https://orcid.org/0000-0002-1295-0973","observed_orcids":["https://orcid.org/0000-0002-1295-0973"]},"institutions":[{"id":"https://openalex.org/I170658231","display_name":"Osnabr\u00fcck University","ror":"https://ror.org/04qmmjx98","country_code":"DE","type":"education","lineage":["https://openalex.org/I170658231"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xenia Ohmer","raw_affiliation_strings":["Osnabr\u00fcck University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osnabr\u00fcck University","institution_ids":["https://openalex.org/I170658231"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007465102","display_name":"Elia Bruni","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I170658231","display_name":"Osnabr\u00fcck University","ror":"https://ror.org/04qmmjx98","country_code":"DE","type":"education","lineage":["https://openalex.org/I170658231"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Elia Bruni","raw_affiliation_strings":["Osnabr\u00fcck University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osnabr\u00fcck University","institution_ids":["https://openalex.org/I170658231"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7647,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.95338069,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6297","last_page":"6305"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.0,"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/language-grounding","display_name":"language grounding","score":0.800000011920929},{"id":"https://openalex.org/keywords/intuitive-physics","display_name":"intuitive physics","score":0.8809999823570251},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9300000071525574},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.6039999723434448},{"id":"https://openalex.org/keywords/video-based-assessment","display_name":"video-based assessment","score":0.5669999718666077},{"id":"https://openalex.org/keywords/unity-simulation","display_name":"Unity simulation","score":0.8849999904632568},{"id":"https://openalex.org/keywords/object-permanence","display_name":"object permanence","score":0.9940000176429749},{"id":"https://openalex.org/keywords/continuity","display_name":"continuity","score":0.4189999997615814},{"id":"https://openalex.org/keywords/prompting-strategies","display_name":"prompting strategies","score":0.652999997138977}],"concepts":[{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.8513712286949158},{"id":"https://openalex.org/C132829578","wikidata":"https://www.wikidata.org/wiki/Q581151","display_name":"Situated","level":2,"score":0.7606179714202881},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.753913164138794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6444698572158813},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.6021561622619629},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3640576899051666},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32815825939178467},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15867114067077637},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14843493700027466},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08798277378082275},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.06566262245178223},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.24963/ijcai.2024/696","doi":"https://doi.org/10.24963/ijcai.2024/696","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2024/696","pdf_url":"https://www.ijcai.org/proceedings/2024/0696.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2311.09048","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.09048","pdf_url":"https://arxiv.org/pdf/2311.09048","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2311.09048","doi":"https://doi.org/10.48550/arxiv.2311.09048","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.09048","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2024/696","doi":"https://doi.org/10.24963/ijcai.2024/696","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2024/696","pdf_url":"https://www.ijcai.org/proceedings/2024/0696.pdf","source":{"id":"https://openalex.org/S4306419999","display_name":"International Joint Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401024343.pdf","grobid_xml":"https://content.openalex.org/works/W4401024343.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W3135367836","https://openalex.org/W3205839208","https://openalex.org/W4225323055","https://openalex.org/W4318718936","https://openalex.org/W4366330503","https://openalex.org/W4366850747","https://openalex.org/W4378711593","https://openalex.org/W4379918953","https://openalex.org/W4386071707","https://openalex.org/W4402671548","https://openalex.org/W7108068597"],"related_works":["https://openalex.org/W4414424223","https://openalex.org/W7116848295","https://openalex.org/W7164032484","https://openalex.org/W4391128605","https://openalex.org/W4414593837","https://openalex.org/W4416034100","https://openalex.org/W7216230434","https://openalex.org/W4417451791","https://openalex.org/W7130910896","https://openalex.org/W7125516733"],"abstract_inverted_index":{"This":[0,23],"paper":[1],"presents":[2],"GRASP,":[3],"a":[4,28,43],"novel":[5],"benchmark":[6],"to":[7,46,73,80,162],"evaluate":[8,81],"the":[9,58,75,92,120,124,133,139,155,164],"language":[10,20,39,93],"grounding":[11,40,94,108],"and":[12,69,95,113],"physical":[13],"understanding":[14,60],"capabilities":[15,98,116],"of":[16,61,99,136,157,166],"video-based":[17],"multimodal":[18,84],"large":[19],"models":[21,128,168],"(LLMs).":[22],"evaluation":[24,87],"is":[25],"accomplished":[26],"via":[27],"two-tier":[29],"approach":[30],"leveraging":[31],"Unity":[32],"simulations.":[33],"The":[34,54],"first":[35],"level":[36,56,135],"tests":[37],"for":[38,111],"by":[41],"assessing":[42],"model's":[44,59],"ability":[45],"relate":[47],"simple":[48],"textual":[49],"descriptions":[50],"with":[51],"visual":[52],"information.":[53],"second":[55],"evaluates":[57],"\"Intuitive":[62],"Physics\"":[63],"principles,":[64],"such":[65],"as":[66],"object":[67],"permanence":[68],"continuity.":[70],"In":[71],"addition":[72],"releasing":[74],"benchmark,":[76],"we":[77],"use":[78],"it":[79],"several":[82],"state-of-the-art":[83],"LLMs.":[85],"Our":[86],"reveals":[88],"significant":[89],"shortcomings":[90],"in":[91,138,169],"intuitive":[96],"physics":[97],"these":[100,115,171],"models.":[101],"Although":[102],"they":[103],"exhibit":[104],"at":[105,132],"least":[106],"some":[107],"capabilities,":[109],"particularly":[110],"colors":[112],"shapes,":[114],"depend":[117],"heavily":[118],"on":[119,147],"prompting":[121],"strategy.":[122],"At":[123],"same":[125],"time,":[126],"all":[127],"perform":[129],"below":[130],"or":[131],"chance":[134],"50%":[137],"Intuitive":[140],"Physics":[141],"tests,":[142],"while":[143],"human":[144],"subjects":[145],"are":[146],"average":[148],"80%":[149],"correct.":[150],"These":[151],"identified":[152],"limitations":[153],"underline":[154],"importance":[156],"using":[158],"benchmarks":[159],"like":[160],"GRASP":[161],"monitor":[163],"progress":[165],"future":[167],"developing":[170],"competencies.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":4}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2024-07-27T00:00:00"}