{"id":"https://openalex.org/W4415538878","doi":"https://doi.org/10.1145/3746027.3755164","title":"A Motion is Worth a Hybrid Sentence: Taming Language Model for Unified Motion Generation by Fine-grained Planning","display_name":"A Motion is Worth a Hybrid Sentence: Taming Language Model for Unified Motion Generation by Fine-grained Planning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415538878","doi":"https://doi.org/10.1145/3746027.3755164"},"language":"en","primary_location":{"id":"doi:10.1145/3746027.3755164","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755164","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3755164","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101419739","display_name":"Ronghui Li","orcid":"https://orcid.org/0000-0001-7703-9315"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ronghui Li","raw_affiliation_strings":["Tsinghua University, Shenzhen, China and Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-7703-9315","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China and Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103504945","display_name":"Lingxiao Han","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingxiao Han","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0009-1288-9656","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087185745","display_name":"Shi Shu","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shi Shu","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0005-4881-8279","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yueyao Liu","orcid":"https://orcid.org/0009-0005-4298-2609"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueyao Liu","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0005-4298-2609","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007053428","display_name":"Yukang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yukang Lin","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0001-2469-5690","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100694246","display_name":"Yue Ma","orcid":"https://orcid.org/0009-0005-7477-5938"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yue Ma","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0005-7477-5938","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100709306","display_name":"Jie Guo","orcid":"https://orcid.org/0000-0002-7411-4751"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Guo","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-7411-4751","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100406050","display_name":"Ziwei Liu","orcid":"https://orcid.org/0000-0002-4220-5958"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ziwei Liu","raw_affiliation_strings":["Nanyang Technological University, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4220-5958","affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100754504","display_name":"Xiu Li","orcid":"https://orcid.org/0000-0003-0403-1923"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiu Li","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-0403-1923","affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"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":"1404","last_page":"1413"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9995999932289124,"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":0.9995999932289124,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9976999759674072,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9923999905586243,"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/motion","display_name":"Motion (physics)","score":0.794700026512146},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5249999761581421},{"id":"https://openalex.org/keywords/motion-field","display_name":"Motion field","score":0.4207000136375427},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.40119999647140503},{"id":"https://openalex.org/keywords/motion-planning","display_name":"Motion planning","score":0.39079999923706055},{"id":"https://openalex.org/keywords/motion-capture","display_name":"Motion capture","score":0.37529999017715454},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.3709000051021576}],"concepts":[{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.794700026512146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6902999877929688},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.576200008392334},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49000000953674316},{"id":"https://openalex.org/C124774092","wikidata":"https://www.wikidata.org/wiki/Q6917782","display_name":"Motion field","level":3,"score":0.4207000136375427},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.39079999923706055},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.37529999017715454},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.32589998841285706},{"id":"https://openalex.org/C10161872","wikidata":"https://www.wikidata.org/wiki/Q557891","display_name":"Motion estimation","level":2,"score":0.30390000343322754},{"id":"https://openalex.org/C145565327","wikidata":"https://www.wikidata.org/wiki/Q852514","display_name":"Motion control","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C100673868","wikidata":"https://www.wikidata.org/wiki/Q6917799","display_name":"Motion system","level":3,"score":0.2930999994277954},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2824000120162964},{"id":"https://openalex.org/C146159030","wikidata":"https://www.wikidata.org/wiki/Q7625099","display_name":"Structure from motion","level":3,"score":0.25679999589920044}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3746027.3755164","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755164","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/202559","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/202559","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":null,"raw_type":"Conference Paper"}],"best_oa_location":{"id":"doi:10.1145/3746027.3755164","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3755164","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3956193058","display_name":null,"funder_award_id":"PCL2023A10-2","funder_id":"https://openalex.org/F4320318558","funder_display_name":"Peng Cheng Laboratory"}],"funders":[{"id":"https://openalex.org/F4320318558","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1985453523","https://openalex.org/W4221142137","https://openalex.org/W4312635677","https://openalex.org/W4312674262","https://openalex.org/W4312936899","https://openalex.org/W4385284180","https://openalex.org/W4386065807","https://openalex.org/W4386075888","https://openalex.org/W4386075984","https://openalex.org/W4386076288","https://openalex.org/W4386160289","https://openalex.org/W4390872297","https://openalex.org/W4390873382","https://openalex.org/W4390874263","https://openalex.org/W4402716181","https://openalex.org/W4402754111","https://openalex.org/W4402754184","https://openalex.org/W4403792047","https://openalex.org/W4408055962"],"related_works":[],"abstract_inverted_index":{"Existing":[0],"LLM-based":[1],"motion":[2,30,48,57,64,69,77,87,99,116,156,168],"models":[3],"fail":[4],"to":[5,24,162],"fully":[6],"leverage":[7],"large":[8,83],"models'":[9],"planning":[10],"capabilities":[11],"for":[12,141],"motion-related":[13],"tasks,":[14],"exhibiting":[15],"poor":[16],"generalization,":[17],"limited":[18],"text-motion":[19,152],"alignment,":[20,124,153],"and":[21,42,66,78,120,144,158],"an":[22],"inability":[23],"perform":[25],"multimodal":[26,164],"condition":[27,165],"joint":[28,166],"driven":[29,167],"generation.":[31],"We":[32],"argue":[33],"that":[34,71,96],"these":[35],"issues":[36],"arise":[37],"from":[38,117],"the":[39,43,55,74,160],"modality":[40],"gap":[41,75],"highly":[44],"coupled":[45],"nature":[46],"of":[47,62,85],"tokens.":[49],"To":[50,80,113],"address":[51],"this,":[52],"we":[53,89,125,132],"proposed":[54],"hybrid":[56,86,118],"sentence,":[58],"which":[59],"is":[60,159],"consistant":[61],"fine-grained":[63,107,151],"decription":[65],"atomic":[67,98],"body-part":[68],"token":[70],"can":[72],"bridge":[73],"between":[76],"text.":[79],"obtain":[81],"a":[82,91],"corpus":[84],"sentences,":[88],"introduced":[90],"novel":[92],"motion-to-text":[93],"generation":[94,169],"method":[95,148],"combines":[97],"operators":[100],"with":[101],"GPT-4o,":[102],"resulting":[103],"in":[104],"68.2":[105],"million":[106],"textual":[108],"descriptions":[109],"across":[110],"diverse":[111],"modalities.":[112],"reconstruct":[114],"high-quality":[115],"sentences":[119],"make":[121],"better":[122],"motion-text":[123],"introduce":[126],"Semantic-Aware":[127],"Decoupled":[128],"Motion":[129],"Tokenization.":[130],"Furthermore,":[131],"propose":[133],"MotionUPG":[134],"based":[135],"on":[136],"LLaMA,":[137],"leveraging":[138],"MotionWords":[139],"dataset":[140],"both":[142],"pretraining":[143],"instruction":[145],"tuning.":[146],"Our":[147],"achieves":[149],"strong":[150],"impressive":[154],"zero-shot":[155],"generation,":[157],"first":[161],"support":[163],"tasks.":[170]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-25T00:00:00"}