{"id":"https://openalex.org/W4416035073","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.349","title":"Bridging the Dynamic Perception Gap: Training-Free Draft Chain-of-Thought for Dynamic Multimodal Spatial Reasoning","display_name":"Bridging the Dynamic Perception Gap: Training-Free Draft Chain-of-Thought for Dynamic Multimodal Spatial Reasoning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416035073","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.349"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.349","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.349","pdf_url":"https://aclanthology.org/2025.findings-emnlp.349.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.349.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110733796","display_name":"Shan\u2010Hwei Ou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siqu Ou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100778701","display_name":"Hongcheng Liu","orcid":"https://orcid.org/0009-0000-3271-9544"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongcheng Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113123604","display_name":"Pingjie Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pingjie Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111276615","display_name":"Yusheng Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yusheng Liao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106214912","display_name":"Chuan Xuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuan Xuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100645705","display_name":"Yanfeng Wang","orcid":"https://orcid.org/0000-0002-3196-2347"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanfeng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100710570","display_name":"Yibin Wang","orcid":"https://orcid.org/0000-0003-0852-0767"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu Wang","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44128953,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6560","last_page":"6578"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11904","display_name":"Spatial Cognition and Navigation","score":0.6147000193595886,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11904","display_name":"Spatial Cognition and Navigation","score":0.6147000193595886,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.18230000138282776,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.04580000042915344,"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/bridging","display_name":"Bridging (networking)","score":0.7247999906539917},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5497000217437744},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.3070000112056732},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.29980000853538513},{"id":"https://openalex.org/keywords/mode","display_name":"Mode (computer interface)","score":0.2791000008583069}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.7247999906539917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6068999767303467},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5497000217437744},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4634999930858612},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3070000112056732},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.25839999318122864}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.349","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.349","pdf_url":"https://aclanthology.org/2025.findings-emnlp.349.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.349","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.349","pdf_url":"https://aclanthology.org/2025.findings-emnlp.349.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6360183275","display_name":null,"funder_award_id":"22DZ2229005","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416035073.pdf","grobid_xml":"https://content.openalex.org/works/W4416035073.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"chains-of-thought":[1],"(CoT)":[2],"have":[3],"advanced":[4],"complex":[5],"reasoning":[6,28,52,71,115],"in":[7,25,72],"multimodal":[8],"large":[9],"language":[10],"models":[11],"(MLLMs),":[12],"existing":[13],"methods":[14],"remain":[15],"confined":[16],"to":[17,42],"text":[18],"or":[19],"static":[20],"visual":[21,56,94],"domains,":[22],"often":[23],"faltering":[24],"dynamic":[26,44,55,113],"spatial":[27,45,70,114],"tasks.To":[29],"bridge":[30],"this":[31,76],"gap,":[32],"we":[33,78],"present":[34],"GRASS-LAND,":[35],"a":[36,84,109],"novel":[37],"maze":[38],"navigation":[39],"benchmark":[40],"designed":[41],"evaluate":[43],"reasoning.Our":[46],"experiments":[47],"show":[48],"that":[49,87,100],"augmenting":[50],"textual":[51,90],"chains":[53],"with":[54,92],"drafts,":[57],"overlaid":[58],"on":[59],"input":[60],"images,":[61],"significantly":[62],"outperforms":[63],"conventional":[64],"approaches,":[65],"offering":[66],"new":[67],"insights":[68],"into":[69,96],"evolving":[73],"environments.To":[74],"generalize":[75],"capability,":[77],"propose":[79],"D2R":[80,101],"(Dynamic":[81],"Draft-Augmented":[82],"Reasoning),":[83],"training-free":[85],"framework":[86],"seamlessly":[88],"integrates":[89],"CoT":[91],"corresponding":[93],"drafts":[95],"MLLMs.Extensive":[97],"evaluations":[98],"demonstrate":[99],"consistently":[102],"enhances":[103],"performance":[104],"across":[105],"diverse":[106],"tasks,":[107],"establishing":[108],"robust":[110],"baseline":[111],"for":[112],"without":[116],"requiring":[117],"model":[118],"fine-tuning.Project":[119],"is":[120],"open":[121],"at":[122],"https://github.com/Cratileo/":[123],"D2R.":[124]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}