{"id":"https://openalex.org/W7167608087","doi":"https://doi.org/10.48550/arxiv.2607.03748","title":"Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Process","display_name":"Bridging Interleaved Multi-Modal Reasoning as a Unified Decision Process","publication_year":2026,"publication_date":"2026-07-04","ids":{"openalex":"https://openalex.org/W7167608087","doi":"https://doi.org/10.48550/arxiv.2607.03748"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.03748","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.03748","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2607.03748","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039055022","display_name":"Zican Hu","orcid":"https://orcid.org/0000-0002-6369-5730"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Zican","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136106652","display_name":"Xuyang Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Xuyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140221963","display_name":"Yiming Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yiming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115731913","display_name":"Zuwei Long","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Long, Zuwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140166326","display_name":"Wei Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120862643","display_name":"Yunzhuo Hao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao, Yunzhuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140209857","display_name":"Jiawei Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Jiawei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140184227","display_name":"Linjie Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Linjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140192008","display_name":"Yu Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140191876","display_name":"Zhenhong Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Zhenhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037284650","display_name":"Weibo Gu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gu, Weibo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140179585","display_name":"Xing Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Xing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5140176882","display_name":"Zhi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhi","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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9843000173568726,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9843000173568726,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0035000001080334187,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0019000000320374966,"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/markov-decision-process","display_name":"Markov decision process","score":0.5995000004768372},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5270000100135803},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4699000120162964},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.44999998807907104},{"id":"https://openalex.org/keywords/unified-model","display_name":"Unified Model","score":0.40689998865127563},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3903000056743622},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.33820000290870667},{"id":"https://openalex.org/keywords/braid","display_name":"Braid","score":0.3321000039577484}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7272999882698059},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5995000004768372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5701000094413757},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5270000100135803},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4699000120162964},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.40689998865127563},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.33820000290870667},{"id":"https://openalex.org/C124194741","wikidata":"https://www.wikidata.org/wiki/Q320809","display_name":"Braid","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3239000141620636},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2912999987602234},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.275299996137619},{"id":"https://openalex.org/C151051286","wikidata":"https://www.wikidata.org/wiki/Q3258398","display_name":"Unified Process","level":4,"score":0.2660999894142151},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.03748","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.03748","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.2607.03748","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.03748","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[{"display_name":"Peace, Justice and strong institutions","score":0.8045676350593567,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Unified":[0],"multi-modal":[1,193],"models":[2],"(UMMs)":[3],"have":[4],"shown":[5],"promising":[6],"interleaved":[7,47],"text-image":[8],"reasoning":[9,71,84,152,168],"capabilities,":[10],"yet":[11],"effectively":[12],"optimizing":[13],"such":[14],"multi-turn":[15,82],"generation":[16,35,99],"via":[17,100],"reinforcement":[18],"learning":[19,160],"(RL)":[20],"remains":[21],"an":[22],"open":[23],"challenge.":[24],"Existing":[25],"approaches":[26],"apply":[27],"RL":[28,57,104],"exclusively":[29],"to":[30,36,158],"text":[31,118],"steps,":[32],"relegating":[33],"image":[34,121,149],"supervised":[37],"surrogates,":[38],"preventing":[39],"policy":[40,129],"gradients":[41],"from":[42],"propagating":[43],"through":[44,126],"the":[45,54,63],"full":[46],"trajectory":[48],"across":[49],"heterogeneous":[50],"modalities.":[51],"This":[52],"leaves":[53],"potential":[55],"of":[56,95],"for":[58,191],"UMMs":[59],"largely":[60],"untapped.":[61],"In":[62],"paper,":[64],"we":[65],"introduce":[66],"\\textbf{BRAID}":[67],"(\\textbf{B}ridging":[68],"inte\\textbf{R}le\\textbf{A}ved":[69],"mult\\textbf{I}-modal":[70],"as":[72,85],"a":[73,77,86,101,108,140,182],"unified":[74,87,183],"\\textbf{D}ecision":[75],"process),":[76],"simple":[78],"framework":[79],"that":[80,145,174,181],"casts":[81],"text-image-text":[83],"Markov":[88],"decision":[89],"process":[90],"(MDP),":[91],"enabling":[92],"joint":[93],"optimization":[94],"textual":[96],"and":[97,112,120,169],"visual":[98,163,170],"single,":[102],"principled":[103],"objective.":[105],"BRAID":[106,138,175],"computes":[107],"shared":[109],"trajectory-level":[110],"advantage":[111],"propagates":[113],"it":[114],"coherently":[115],"into":[116],"both":[117],"tokens":[119],"denoising":[122],"paths,":[123],"each":[124,147],"optimized":[125],"its":[127,151],"modality-native":[128],"gradient":[130],"mechanism.":[131],"To":[132],"further":[133],"address":[134],"long-horizon":[135],"credit":[136],"assignment,":[137],"employs":[139],"vision-language":[141],"model":[142],"(VLM)":[143],"judge":[144],"scores":[146],"intermediate":[148],"on":[150,166],"utility,":[153],"supplying":[154],"dense":[155],"turn-level":[156],"feedback":[157],"sharpen":[159],"at":[161],"critical":[162],"branches.":[164],"Experiments":[165],"spatial":[167],"perception":[171],"benchmarks":[172],"show":[173],"consistently":[176],"outperforms":[177],"various":[178],"baselines,":[179],"confirming":[180],"MDP":[184],"formulation":[185],"with":[186],"vision-thinking":[187],"guidance":[188],"is":[189],"essential":[190],"effective":[192],"reasoning.":[194]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-08T00:00:00"}