{"id":"https://openalex.org/W4411631959","doi":"https://doi.org/10.1145/3731715.3733405","title":"MuSeLLM: SDF Generation and Understanding via Multi-Scale Tokenization with Position-Aware Guidance","display_name":"MuSeLLM: SDF Generation and Understanding via Multi-Scale Tokenization with Position-Aware Guidance","publication_year":2025,"publication_date":"2025-06-25","ids":{"openalex":"https://openalex.org/W4411631959","doi":"https://doi.org/10.1145/3731715.3733405"},"language":"en","primary_location":{"id":"doi:10.1145/3731715.3733405","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tianwei Ding","orcid":"https://orcid.org/0009-0004-1487-9113"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianwei Ding","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-1487-9113","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101238929","display_name":"Lanshan He","orcid":"https://orcid.org/0009-0009-6093-8803"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lanshan He","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0009-6093-8803","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054455904","display_name":"Weijian Ma","orcid":"https://orcid.org/0009-0004-0650-6448"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijian Ma","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0004-0650-6448","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046420009","display_name":"Xiangdong Zhou","orcid":"https://orcid.org/0000-0002-5538-7367"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangdong Zhou","raw_affiliation_strings":["Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5538-7367","affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10962691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"192","last_page":"201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9857000112533569,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9857000112533569,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.9750000238418579,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10653","display_name":"Robot Manipulation and Learning","score":0.9706000089645386,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7218307256698608},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.5939140319824219},{"id":"https://openalex.org/keywords/position","display_name":"Position (finance)","score":0.5640799403190613},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5605670213699341},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32332879304885864},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.0489639937877655}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7218307256698608},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.5939140319824219},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5640799403190613},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5605670213699341},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32332879304885864},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0489639937877655},{"id":"https://openalex.org/C10138342","wikidata":"https://www.wikidata.org/wiki/Q43015","display_name":"Finance","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731715.3733405","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3731715.3733405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Multimedia Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2990138404","https://openalex.org/W4200150166","https://openalex.org/W4236965008","https://openalex.org/W4312910764","https://openalex.org/W4382334257","https://openalex.org/W4385318467","https://openalex.org/W4386076002","https://openalex.org/W4390873331","https://openalex.org/W4402716026","https://openalex.org/W4402726963","https://openalex.org/W4402753669","https://openalex.org/W4402753842","https://openalex.org/W4402816865","https://openalex.org/W4403778769","https://openalex.org/W4406259573","https://openalex.org/W6600223117","https://openalex.org/W6600553734","https://openalex.org/W6853450284"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4405003489","https://openalex.org/W4386014872","https://openalex.org/W1847536016","https://openalex.org/W4361193986","https://openalex.org/W3149094754","https://openalex.org/W2148703997","https://openalex.org/W4366851046"],"abstract_inverted_index":{"The":[0],"advancement":[1],"of":[2,37,61,100,122,138,160,172],"3D":[3,44,55,192,196,203,206],"generation":[4,117,137,170,204],"and":[5,16,40,57,205],"understanding":[6,56,208],"stands":[7],"as":[8,25,127,182,224],"a":[9,65,78,87,108,113,128,141,164,183],"critical":[10],"interface":[11],"enabling":[12],"machines":[13],"to":[14,34,50,97,115,131,146,191],"interpret":[15],"interact":[17],"with":[18,95,194,219],"the":[19,59,69,136,147,169,178,220,225],"physical":[20],"world.":[21],"Large":[22],"language":[23],"models,":[24],"trained":[26],"on":[27,86,103,119,157],"internet-scale":[28],"text":[29],"corpus,":[30],"are":[31],"well":[32],"recognized":[33],"possess":[35],"commonsense":[36],"real":[38,43],"world":[39],"perception":[41],"in":[42,174,201],"space.":[45],"However,":[46],"when":[47],"it":[48],"comes":[49],"leveraging":[51],"these":[52],"abilities":[53],"into":[54],"generation,":[58],"difference":[60],"data":[62,90,185,197],"format":[63],"is":[64],"significant":[66],"gap":[67],"between":[68],"two":[70],"ends.":[71],"In":[72],"this":[73],"sense,":[74],"we":[75,105,162],"propose":[76,163],"MuSeLLM,":[77],"specially":[79,88],"designed":[80],"adapting":[81,189],"strategy":[82,187],"for":[83,188],"finetuning":[84],"LLMs":[85,190],"selected":[89],"format,":[91],"namely":[92],"voxelized":[93],"SDFs":[94],"respect":[96],"its":[98],"easiness":[99],"tokenization.":[101],"Based":[102],"this,":[104],"put":[106],"forward":[107],"multi-scale":[109],"tokenization":[110],"strategy,":[111],"allowing":[112],"coarse":[114],"fine":[116],"paradigm":[118],"different":[120],"levels":[121],"codebook":[123],"tokens.":[124],"This":[125],"serves":[126],"natural":[129],"fit":[130],"prevailing":[132],"LLM":[133],"architectures":[134],"where":[135],"tokens":[139,173],"at":[140,151],"certain":[142],"level":[143,176],"may":[144],"refer":[145],"entire":[148],"shape":[149],"representations":[150],"coarser":[152],"levels.":[153],"To":[154],"avoid":[155],"overfitting":[156],"spatial":[158,227],"orders":[159],"tokens,":[161],"position-aware":[165],"guidance":[166],"which":[167],"perturbs":[168],"order":[171],"each":[175],"during":[177],"training":[179,222],"stage,":[180],"serving":[181],"strong":[184],"augmentation":[186],"domains":[193],"few":[195],"available.":[198],"Experiment":[199],"results":[200],"text-guided":[202],"object":[207],"illustrate":[209],"that":[210],"our":[211,234],"method":[212,235],"achieves":[213],"superior":[214],"performance":[215],"against":[216],"previous":[217],"state-of-the-art":[218],"same":[221],"data,":[223],"inherent":[226],"reasoning":[228],"ability":[229],"has":[230],"been":[231],"triggered":[232],"by":[233],"design.":[236]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}