{"id":"https://openalex.org/W4417094064","doi":"https://doi.org/10.1109/tvcg.2026.3675978","title":"MARRS: Masked Autoregressive Unit-Based Reaction Synthesis","display_name":"MARRS: Masked Autoregressive Unit-Based Reaction Synthesis","publication_year":2026,"publication_date":"2026-03-20","ids":{"openalex":"https://openalex.org/W4417094064","doi":"https://doi.org/10.1109/tvcg.2026.3675978","pmid":"https://pubmed.ncbi.nlm.nih.gov/41860922"},"language":"en","primary_location":{"id":"doi:10.1109/tvcg.2026.3675978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2026.3675978","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.11334","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028731909","display_name":"Yabiao Wang","orcid":"https://orcid.org/0000-0002-6592-8411"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yabiao Wang","raw_affiliation_strings":["Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-6592-8411","affiliations":[{"raw_affiliation_string":"Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100400174","display_name":"Shuo Wang","orcid":"https://orcid.org/0000-0002-7990-7515"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuo Wang","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0008-3437-3565","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021861529","display_name":"Jiangning Zhang","orcid":"https://orcid.org/0000-0001-8891-6766"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangning Zhang","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025002931","display_name":"Jiafu Wu","orcid":"https://orcid.org/0000-0002-1036-5076"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafu Wu","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010996897","display_name":"Qingdong He","orcid":"https://orcid.org/0000-0003-3203-0071"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingdong He","raw_affiliation_strings":["Tencent Youtu Lab, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-3203-0071","affiliations":[{"raw_affiliation_string":"Tencent Youtu Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100687689","display_name":"Liu Y","orcid":"https://orcid.org/0000-0003-2030-643X"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-4822-8939","affiliations":[{"raw_affiliation_string":"Institute of Cyber-Systems and Control, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01616108,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"7","first_page":"5984","last_page":"5995"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.5580000281333923,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.5580000281333923,"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":0.15219999849796295,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.13779999315738678,"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/codebook","display_name":"Codebook","score":0.7386999726295471},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.6488999724388123},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.605400025844574},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.4803999960422516},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.44929999113082886},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.41659998893737793},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4101000130176544},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.3840000033378601}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.7386999726295471},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.6488999724388123},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.605400025844574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5989999771118164},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.4803999960422516},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44040000438690186},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41690000891685486},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4101000130176544},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.3840000033378601},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3529999852180481},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3312000036239624},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.30480000376701355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.303600013256073},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.28139999508857727},{"id":"https://openalex.org/C33954974","wikidata":"https://www.wikidata.org/wiki/Q486494","display_name":"Sensor fusion","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C97820695","wikidata":"https://www.wikidata.org/wiki/Q387749","display_name":"Human Connectome Project","level":3,"score":0.2671000063419342},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2653999924659729},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.25999999046325684}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/tvcg.2026.3675978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvcg.2026.3675978","pdf_url":null,"source":{"id":"https://openalex.org/S84775595","display_name":"IEEE Transactions on Visualization and Computer Graphics","issn_l":"1077-2626","issn":["1077-2626","1941-0506","2160-9306"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Visualization and Computer Graphics","raw_type":"journal-article"},{"id":"pmid:41860922","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41860922","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on visualization and computer graphics","raw_type":null},{"id":"pmh:oai:arXiv.org:2505.11334","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11334","pdf_url":"https://arxiv.org/pdf/2505.11334","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:arXiv.org:2505.11334","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.11334","pdf_url":"https://arxiv.org/pdf/2505.11334","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.11334","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.11334","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":"pmh:oai:arXiv.org:2505.11334","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.11334","pdf_url":"https://arxiv.org/pdf/2505.11334","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4820967758","display_name":null,"funder_award_id":"62525309","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"work":[1],"aims":[2],"at":[3],"a":[4,87,134,186,190],"challenging":[5],"task:":[6],"human":[7,12],"action-reaction":[8],"synthesis,":[9],"i.e.,":[10],"generating":[11],"reactions":[13],"conditioned":[14],"on":[15],"the":[16,55,63,71,104,112,144,149,169,177,181,200,205],"action":[17],"sequence":[18],"of":[19,73,136,208],"another":[20],"person.":[21],"Currently,":[22],"autoregressive":[23],"modeling":[24],"approaches":[25],"with":[26],"vector":[27],"quantization":[28,44],"(VQ)":[29],"have":[30],"achieved":[31],"remarkable":[32],"performance":[33],"in":[34],"motion":[35],"generation":[36],"tasks.":[37],"However,":[38],"VQ":[39],"has":[40],"inherent":[41],"disadvantages,":[42],"including":[43],"information":[45,142,170],"loss,":[46],"low":[47],"codebook":[48],"utilization,":[49],"etc.":[50],"In":[51,81],"addition,":[52],"while":[53],"dividing":[54],"body":[56,114,117,145,163,196],"into":[57,115],"separate":[58],"units":[59,77,166],"can":[60],"be":[61,68],"beneficial,":[62],"computational":[64],"complexity":[65],"needs":[66],"to":[67,91,159,174,203],"considered.":[69],"Also,":[70],"importance":[72],"mutual":[74],"perception":[75],"among":[76],"is":[78],"often":[79],"neglected.":[80],"this":[82],"work,":[83],"we":[84,102,125,153,184],"propose":[85,126],"MARRS,":[86],"novel":[88],"framework":[89],"designed":[90],"generate":[92],"coordinated":[93],"and":[94,118,139,146,164,198,213],"fine-grained":[95],"reaction":[96],"motions":[97],"using":[98,168],"continuous":[99],"representations.":[100],"Initially,":[101],"present":[103],"Unit-distinguished":[105],"Motion":[106],"Variational":[107],"AutoEncoder":[108],"(UD-VAE),":[109],"which":[110,130],"segments":[111],"entire":[113],"distinct":[116,195],"hand":[119,165],"units,":[120],"encoding":[121],"each":[122,194,209],"independently.":[123],"Subsequently,":[124],"Action-Conditioned":[127],"Fusion":[128],"(ACF),":[129],"involves":[131],"randomly":[132],"masking":[133],"subset":[135],"reactive":[137],"tokens":[138],"extracting":[140],"specific":[141],"about":[143],"hands":[147],"from":[148,171],"active":[150],"tokens.":[151],"Furthermore,":[152],"introduce":[154],"Mutual":[155],"Unit":[156],"Modulation":[157],"(MUM)":[158],"facilitate":[160],"interaction":[161],"between":[162],"by":[167],"one":[172],"unit":[173,197],"adaptively":[175],"modulate":[176],"other.":[178],"Finally,":[179],"for":[180,193],"diffusion":[182,201],"model,":[183],"employ":[185],"compact":[187],"MLP":[188],"as":[189],"noise":[191],"predictor":[192],"incorporate":[199],"loss":[202],"model":[204],"probability":[206],"distribution":[207],"token.":[210],"Both":[211],"quantitative":[212],"qualitative":[214],"results":[215],"demonstrate":[216],"that":[217],"our":[218],"method":[219],"achieves":[220],"superior":[221],"performance.":[222]},"counts_by_year":[],"updated_date":"2026-06-24T06:17:17.354583","created_date":"2025-10-10T00:00:00"}