{"id":"https://openalex.org/W7163011690","doi":"https://doi.org/10.48550/arxiv.2605.31158","title":"Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models","display_name":"Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7163011690","doi":"https://doi.org/10.48550/arxiv.2605.31158"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.31158","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31158","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":null,"license_id":null,"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.2605.31158","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025845320","display_name":"Jiacheng Lu","orcid":"https://orcid.org/0009-0002-7920-3814"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Jiacheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137521273","display_name":"Haoyi Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Haoyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137524546","display_name":"Sipei Yi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yi, Sipei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137566244","display_name":"Enze Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Enze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137572615","display_name":"Yu Li","orcid":"https://orcid.org/0009-0000-5711-8358"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137564027","display_name":"Cheng Zhuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuo, Cheng","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/T10812","display_name":"Human Pose and Action Recognition","score":0.1728000044822693,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.1728000044822693,"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/T12290","display_name":"Human Motion and Animation","score":0.1467999964952469,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.1421000063419342,"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/context","display_name":"Context (archaeology)","score":0.5860000252723694},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5415999889373779},{"id":"https://openalex.org/keywords/global-illumination","display_name":"Global illumination","score":0.3822000026702881},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.37130001187324524},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.357699990272522},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.3528999984264374},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.34299999475479126},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.31769999861717224},{"id":"https://openalex.org/keywords/context-model","display_name":"Context model","score":0.31690001487731934}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8264999985694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5986999869346619},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5860000252723694},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5418999791145325},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5415999889373779},{"id":"https://openalex.org/C89720835","wikidata":"https://www.wikidata.org/wiki/Q1531701","display_name":"Global illumination","level":3,"score":0.3822000026702881},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37130001187324524},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.357699990272522},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.3528999984264374},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.34299999475479126},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.31769999861717224},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.31690001487731934},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.30559998750686646},{"id":"https://openalex.org/C30814859","wikidata":"https://www.wikidata.org/wiki/Q4119603","display_name":"Video denoising","level":5,"score":0.30250000953674316},{"id":"https://openalex.org/C3018412434","wikidata":"https://www.wikidata.org/wiki/Q7889","display_name":"Video game","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C32653426","wikidata":"https://www.wikidata.org/wiki/Q3813641","display_name":"Background subtraction","level":3,"score":0.28839999437332153},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2797999978065491},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C77660652","wikidata":"https://www.wikidata.org/wiki/Q150971","display_name":"Computer graphics","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C194969405","wikidata":"https://www.wikidata.org/wiki/Q170519","display_name":"Virtual reality","level":2,"score":0.2583000063896179}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.31158","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31158","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.31158","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.31158","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Interactive":[0],"video":[1,5,61],"world":[2,62],"models":[3],"generate":[4],"chunk":[6,8],"by":[7],"in":[9],"response":[10],"to":[11,31,39,90,140],"user-controlled":[12],"camera":[13,103],"movements,":[14],"enabling":[15],"applications":[16],"such":[17],"as":[18],"real-time":[19],"game":[20],"simulation,":[21],"virtual":[22],"scene":[23],"navigation,":[24],"and":[25,46,94,120,134],"embodied":[26],"AI":[27],"training.":[28],"However,":[29],"scaling":[30],"long":[32],"interactive":[33,60],"trajectories":[34],"is":[35,67],"prohibitively":[36],"expensive":[37],"due":[38],"growing":[40],"context":[41,85,115],"memory,":[42],"quadratic":[43],"attention":[44,126],"complexity,":[45],"repeated":[47],"denoising":[48,117],"steps.":[49],"We":[50],"present":[51],"Light":[52,111,136],"Interaction,":[53],"a":[54],"training-free":[55],"inference":[56],"acceleration":[57],"framework":[58],"for":[59],"models.":[63],"Our":[64],"key":[65],"insight":[66],"that":[68],"interaction":[69],"naturally":[70],"enables":[71],"trajectory-dependent":[72],"adaptive":[73,114],"computation:":[74],"retrieved":[75],"spatial":[76],"memory":[77],"can":[78,86,98],"be":[79,87,99],"discarded":[80],"during":[81],"novel":[82],"exploration,":[83],"temporal":[84],"adjusted":[88],"according":[89],"local":[91],"latent":[92],"dynamics,":[93],"early-step":[95],"model":[96,144],"outputs":[97],"reused":[100],"when":[101],"the":[102],"revisits":[104],"familiar":[105],"regions.":[106],"Based":[107],"on":[108,132],"this":[109],"insight,":[110],"Interaction":[112,137],"combines":[113],"management,":[116],"cache":[118],"acceleration,":[119],"hardware-software":[121],"co-designed":[122],"3D":[123],"block":[124],"sparse":[125],"with":[127],"fused":[128],"Triton":[129],"kernels.":[130],"Evaluated":[131],"HY-WorldPlay":[133],"Matrix-Game-3.0,":[135],"achieves":[138],"up":[139],"2.59x":[141],"speedup":[142],"without":[143],"retraining":[145],"while":[146],"maintaining":[147],"competitive":[148],"visual":[149],"quality.":[150]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-02T00:00:00"}