{"id":"https://openalex.org/W7151617258","doi":"https://doi.org/10.48550/arxiv.2604.03302","title":"Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-modal Large Language Models","display_name":"Beyond Static Vision: Scene Dynamic Field Unlocks Intuitive Physics Understanding in Multi-modal Large Language Models","publication_year":2026,"publication_date":"2026-03-30","ids":{"openalex":"https://openalex.org/W7151617258","doi":"https://doi.org/10.48550/arxiv.2604.03302"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.03302","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03302","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.03302","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133076996","display_name":"Nanxi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Nanxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133096603","display_name":"Xiang Guang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133119320","display_name":"Yuanjie Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yuanjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040422065","display_name":"Haode Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Haode","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133100002","display_name":"Hong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133065786","display_name":"Yong-Lu Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yong-Lu","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":0.9262999892234802,"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":0.9262999892234802,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.01489999983459711,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.013000000268220901,"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/field","display_name":"Field (mathematics)","score":0.5458999872207642},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.45419999957084656},{"id":"https://openalex.org/keywords/coherence","display_name":"Coherence (philosophical gambling strategy)","score":0.43470001220703125},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.37310001254081726},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.36739999055862427},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.351500004529953}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6430000066757202},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5458999872207642},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.43470001220703125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4059000015258789},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3562999963760376},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3402000069618225},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3359000086784363},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C55037315","wikidata":"https://www.wikidata.org/wiki/Q5421151","display_name":"Experimental data","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25769999623298645},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C17231256","wikidata":"https://www.wikidata.org/wiki/Q5156540","display_name":"Completeness (order theory)","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.03302","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03302","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.03302","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.03302","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"Multimodal":[1],"Large":[2],"Language":[3],"Models":[4],"(MLLMs)":[5],"have":[6],"demonstrated":[7],"impressive":[8],"capabilities":[9],"in":[10,58,150],"image":[11],"and":[12,67,82,168],"video":[13],"understanding,":[14,54],"their":[15,30],"ability":[16],"to":[17,128,138],"comprehend":[18],"the":[19,45,60],"physical":[20,49,140],"world":[21],"has":[22],"become":[23],"an":[24],"increasingly":[25],"important":[26],"research":[27],"focus.":[28],"Despite":[29],"improvements,":[31],"current":[32,151],"MLLMs":[33,93,152],"struggle":[34],"significantly":[35],"with":[36],"high-level":[37],"physics":[38,53,115],"reasoning.":[39],"In":[40],"this":[41,69,102],"work,":[42],"we":[43,72,104],"investigate":[44],"first":[46],"step":[47],"of":[48,62],"reasoning,":[50],"i.e.,":[51],"intuitive":[52],"revealing":[55],"substantial":[56],"limitations":[57],"understanding":[59],"dynamics":[61],"continuum":[63],"objects.":[64],"To":[65,100],"isolate":[66],"evaluate":[68],"specific":[70],"capability,":[71],"introduce":[73],"two":[74],"fundamental":[75],"benchmark":[76],"tasks:":[77],"Next":[78],"Frame":[79],"Selection":[80],"(NFS)":[81],"Temporal":[83],"Coherence":[84],"Verification":[85],"(TCV).":[86],"Our":[87,166],"experiments":[88],"demonstrate":[89],"that":[90,113],"even":[91],"state-of-the-art":[92],"perform":[94],"poorly":[95],"on":[96,131],"these":[97],"foundational":[98],"tasks.":[99],"address":[101],"limitation,":[103],"propose":[105],"Scene":[106],"Dynamic":[107],"Field":[108],"(SDF),":[109],"a":[110,118,147,156],"concise":[111],"approach":[112,159],"leverages":[114],"simulators":[116],"within":[117],"multi-task":[119],"fine-tuning":[120],"framework.":[121],"SDF":[122],"substantially":[123],"improves":[124],"performance,":[125],"achieving":[126],"up":[127],"20.7%":[129],"gains":[130],"fluid":[132],"tasks":[133],"while":[134],"showing":[135],"strong":[136],"generalization":[137],"unseen":[139],"domains.":[141],"This":[142],"work":[143],"not":[144],"only":[145],"highlights":[146],"critical":[148],"gap":[149],"but":[153],"also":[154],"presents":[155],"promising":[157],"cost-efficient":[158],"for":[160],"developing":[161],"more":[162],"physically":[163],"grounded":[164],"MLLMs.":[165],"code":[167],"data":[169],"are":[170],"available":[171],"at":[172],"https://github.com/andylinx/Scene-Dynamic-Field.":[173]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-08T00:00:00"}