{"id":"https://openalex.org/W7114896704","doi":"https://doi.org/10.48550/arxiv.2512.09928","title":"HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models","display_name":"HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models","publication_year":2025,"publication_date":"2025-12-10","ids":{"openalex":"https://openalex.org/W7114896704","doi":"https://doi.org/10.48550/arxiv.2512.09928"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2512.09928","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.09928","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.2512.09928","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Lin, Minghui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Minghui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Ding, Pengxiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Pengxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Shu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Shu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhuang, Zifeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang, Zifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Tong, Xinyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong, Xinyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Song, Wenxuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Wenxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lyu, Shangke","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyu, Shangke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Huang, Siteng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Siteng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Wang, Donglin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Donglin","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":0.9824000000953674,"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":0.9824000000953674,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.0019000000320374966,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.001500000013038516,"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/hindsight-bias","display_name":"Hindsight bias","score":0.734499990940094},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6437000036239624},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.6370000243186951},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6154999732971191},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5989999771118164},{"id":"https://openalex.org/keywords/futures-studies","display_name":"Futures studies","score":0.59170001745224},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.40689998865127563}],"concepts":[{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.734499990940094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6489999890327454},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6437000036239624},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.6370000243186951},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6180999875068665},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6154999732971191},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5989999771118164},{"id":"https://openalex.org/C64848388","wikidata":"https://www.wikidata.org/wiki/Q188867","display_name":"Futures studies","level":2,"score":0.59170001745224},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.40689998865127563},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.32760000228881836},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.3199999928474426},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.3190999925136566},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3156999945640564},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3059999942779541},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.25760000944137573}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2512.09928","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.09928","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.2512.09928","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.09928","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language-Action":[0],"(VLA)":[1],"models":[2],"have":[3],"recently":[4],"enabled":[5],"robotic":[6,178],"manipulation":[7,170],"by":[8],"grounding":[9],"visual":[10],"and":[11,29,49,55,100,127,152],"linguistic":[12],"cues":[13],"into":[14],"actions.":[15],"However,":[16],"most":[17],"VLAs":[18],"assume":[19],"the":[20,26,76],"Markov":[21],"property,":[22],"relying":[23],"only":[24],"on":[25,92,150],"current":[27],"observation":[28],"thus":[30],"suffering":[31],"from":[32],"temporal":[33,53,83,112],"myopia":[34],"that":[35,107],"degrades":[36],"long-horizon":[37,141,169],"coherence.":[38],"In":[39],"this":[40,67,93],"work,":[41],"we":[42,95],"view":[43],"motion":[44,109,123],"as":[45],"a":[46,71,104,131,137,144],"more":[47],"compact":[48],"informative":[50],"representation":[51],"of":[52],"context":[54],"world":[56,73],"dynamics,":[57],"capturing":[58],"inter-state":[59],"changes":[60],"while":[61,156],"filtering":[62],"static":[63],"pixel-level":[64],"noise.":[65],"From":[66],"perspective,":[68],"HiF-VLA":[69,97,114,146,163],"equips":[70],"motion-centric":[72],"model":[74],"for":[75,85,102,110,140],"VLA,":[77],"enabling":[78],"agents":[79],"to":[80,135],"reason":[81],"about":[82],"dynamics":[84,117],"future":[86,122],"evolution":[87],"during":[88],"action":[89],"generation.":[90],"Building":[91],"idea,":[94],"propose":[96],"(Hindsight,":[98],"Insight,":[99],"Foresight":[101],"VLAs),":[103],"unified":[105],"framework":[106],"leverages":[108],"bidirectional":[111],"reasoning.":[113],"encodes":[115],"past":[116],"through":[118,130],"hindsight":[119],"priors,":[120],"anticipates":[121],"via":[124],"foresight":[125],"reasoning,":[126],"integrates":[128],"both":[129],"hindsight-modulated":[132],"joint":[133],"expert":[134],"enable":[136],"''think-while-acting''":[138],"paradigm":[139],"manipulation.":[142],"As":[143],"result,":[145],"surpasses":[147],"strong":[148],"baselines":[149],"LIBERO-Long":[151],"CALVIN":[153],"ABC-D":[154],"benchmarks,":[155],"incurring":[157],"negligible":[158],"additional":[159],"inference":[160],"latency.":[161],"Furthermore,":[162],"achieves":[164],"substantial":[165],"improvements":[166],"in":[167,176],"real-world":[168],"tasks,":[171],"demonstrating":[172],"its":[173],"broad":[174],"effectiveness":[175],"practical":[177],"settings.":[179]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-12-12T00:00:00"}