{"id":"https://openalex.org/W7136658978","doi":"https://doi.org/10.48550/arxiv.2603.12746","title":"Thinking in Dynamics: How Multimodal Large Language Models Perceive, Track, and Reason Dynamics in Physical 4D World","display_name":"Thinking in Dynamics: How Multimodal Large Language Models Perceive, Track, and Reason Dynamics in Physical 4D World","publication_year":2026,"publication_date":"2026-03-13","ids":{"openalex":"https://openalex.org/W7136658978","doi":"https://doi.org/10.48550/arxiv.2603.12746"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.12746","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.12746","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.12746","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051294371","display_name":"Yuzhi Huang","orcid":"https://orcid.org/0009-0008-3903-7667"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Huang, Yuzhi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071397246","display_name":"Kairun Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wen, Kairun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101380999","display_name":"Rongxin Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Rongxin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129453675","display_name":"Dongxuan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Dongxuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129489415","display_name":"Yibin Lou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lou, Yibin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129539803","display_name":"Jie Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jie","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129571970","display_name":"Jing Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Jing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129486956","display_name":"Jian Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129446002","display_name":"Zheng Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129600298","display_name":"Yunlong Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Yunlong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129515810","display_name":"Chenxin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chenxin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129632089","display_name":"Panwang Pan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, Panwang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129421681","display_name":"Junbin Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Junbin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129626829","display_name":"Jingyan Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Jingyan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110603747","display_name":"Xinghao Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Xinghao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129504640","display_name":"Yue Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Yue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129608014","display_name":"Zhi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhi","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":17,"corresponding_author_ids":["https://openalex.org/A5051294371"],"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":0.9886999726295471,"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":0.9886999726295471,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.0012000000569969416,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0010999999940395355,"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/visual-reasoning","display_name":"Visual reasoning","score":0.7454000115394592},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6183000206947327},{"id":"https://openalex.org/keywords/dynamics","display_name":"Dynamics (music)","score":0.5715000033378601},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.571399986743927},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5238000154495239},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4666999876499176},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.46549999713897705},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.39169999957084656}],"concepts":[{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.7454000115394592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7448999881744385},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6183000206947327},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.5715000033378601},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.571399986743927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5436999797821045},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5238000154495239},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4666999876499176},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.46549999713897705},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.39169999957084656},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3594000041484833},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.34439998865127563},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3425999879837036},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2992999851703644},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2924000024795532},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2888999879360199},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.28690001368522644},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.12746","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.12746","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.12746","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.12746","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":"article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7207047343254089,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Humans":[0],"inhabit":[1],"a":[2,16,70,101],"physical":[3,201],"4D":[4,18,96,202],"world":[5],"where":[6],"geometric":[7],"structure":[8],"and":[9,48,62,77,83,95,116,126,138,140,154,164,185,196,205],"semantic":[10],"content":[11],"evolve":[12],"over":[13],"time,":[14],"constituting":[15],"dynamic":[17,105,118,155],"reality":[19],"(spatial":[20],"with":[21],"temporal":[22],"dimension).":[23],"While":[24],"current":[25],"Multimodal":[26],"Large":[27],"Language":[28],"Models":[29],"(MLLMs)":[30],"excel":[31],"in":[32,43,53,134,150,199],"static":[33],"visual":[34,111],"understanding,":[35],"can":[36],"they":[37,132],"also":[38],"be":[39],"adept":[40],"at":[41,209],"\"thinking":[42],"dynamics\",":[44],"i.e.,":[45],"perceive,":[46],"track":[47],"reason":[49],"about":[50],"spatio-temporal":[51,60,87,152,197],"dynamics":[52,64,135,194],"evolving":[54],"scenes?":[55],"To":[56],"systematically":[57],"assess":[58],"their":[59],"reasoning":[61,153,198],"localized":[63],"perception":[65,195],"capabilities,":[66],"we":[67],"introduce":[68],"Dyn-Bench,":[69],"large-scale":[71],"benchmark":[72,206],"built":[73],"from":[74,92],"diverse":[75],"real-world":[76],"synthetic":[78],"video":[79],"datasets,":[80],"enabling":[81],"robust":[82],"scalable":[84],"evaluation":[85],"of":[86,104,162],"understanding.":[88],"Through":[89],"multi-stage":[90],"filtering":[91],"massive":[93],"2D":[94],"data":[97],"sources,":[98],"Dyn-Bench":[99],"provides":[100],"high-quality":[102],"collection":[103],"scenes,":[106],"comprising":[107],"1k":[108],"videos,":[109],"7k":[110],"question":[112],"answering":[113],"(VQA)":[114],"pairs,":[115],"3k":[117],"object":[119,156],"grounding":[120],"pairs.":[121],"We":[122],"probe":[123],"general,":[124],"spatial":[125],"region-level":[127],"MLLMs":[128],"to":[129],"express":[130],"how":[131],"think":[133],"both":[136,151],"linguistically":[137],"visually,":[139],"find":[141],"that":[142],"existing":[143],"models":[144],"cannot":[145],"simultaneously":[146],"maintain":[147],"strong":[148],"performance":[149],"grounding,":[157],"often":[158],"producing":[159],"inconsistent":[160],"interpretations":[161],"motion":[163],"interaction.":[165],"Notably,":[166],"conventional":[167],"prompting":[168],"strategies":[169],"(e.g.,":[170],"chain-of-thought":[171],"or":[172],"caption-based":[173],"hints)":[174],"provide":[175],"limited":[176],"improvement,":[177],"whereas":[178],"structured":[179],"integration":[180],"approaches,":[181],"including":[182],"Mask-Guided":[183],"Fusion":[184],"Spatio-Temporal":[186],"Textual":[187],"Cognitive":[188],"Map":[189],"(ST-TCM),":[190],"significantly":[191],"enhance":[192],"MLLMs'":[193],"the":[200],"world.":[203],"Code":[204],"are":[207],"available":[208],"https://dyn-bench.github.io/.":[210]},"counts_by_year":[],"updated_date":"2026-03-17T07:05:13.627479","created_date":"2026-03-17T00:00:00"}