{"id":"https://openalex.org/W7215719352","doi":"https://doi.org/10.48550/arxiv.2610.00524","title":"Same Scene, Different Task: Skill Alignment for Compositional Generalization in VLAs","display_name":"Same Scene, Different Task: Skill Alignment for Compositional Generalization in VLAs","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7215719352","doi":"https://doi.org/10.48550/arxiv.2610.00524"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.00524","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00524","pdf_url":"https://arxiv.org/pdf/2610.00524","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.00524","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111749329","display_name":"T. Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yang, Taegeun","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5155468175","display_name":"Youngju Na","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Na, Youngju","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057188848","display_name":"Yoonki Cho","orcid":"https://orcid.org/0000-0002-8231-5633","observed_orcids":["https://orcid.org/0000-0002-8231-5633"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Cho, Yoonki","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5155436807","display_name":"Sung-Eui Yoon","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoon, Sung-Eui","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology (KAIST)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology (KAIST)","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.5800999999046326,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.5800999999046326,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.40549999475479126,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.004600000102072954,"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/vision-language-action-models","display_name":"vision-language-action models","score":0.9890000224113464},{"id":"https://openalex.org/keywords/compositional-generalization","display_name":"compositional generalization","score":0.9879999756813049},{"id":"https://openalex.org/keywords/skill-representation","display_name":"skill representation","score":0.5019999742507935},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.44200000166893005},{"id":"https://openalex.org/keywords/robot-learning-from-demonstration","display_name":"robot learning from demonstration","score":0.3569999933242798}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.8672999739646912},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7642999887466431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6448000073432922},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5443000197410583},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.5088000297546387},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.508400022983551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4629000127315521},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3767000138759613},{"id":"https://openalex.org/C132758656","wikidata":"https://www.wikidata.org/wiki/Q5307365","display_name":"Dreyfus model of skill acquisition","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2549999952316284},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.00524","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00524","pdf_url":"https://arxiv.org/pdf/2610.00524","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.00524","doi":"https://doi.org/10.48550/arxiv.2610.00524","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.00524","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,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.00524","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00524","pdf_url":"https://arxiv.org/pdf/2610.00524","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7215719352.pdf","grobid_xml":"https://content.openalex.org/works/W7215719352.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W3039055967","https://openalex.org/W3168867926","https://openalex.org/W4224912544","https://openalex.org/W4303647933","https://openalex.org/W4399695759","https://openalex.org/W4402354111","https://openalex.org/W4414051084","https://openalex.org/W4414079054","https://openalex.org/W4414674749","https://openalex.org/W4414901575","https://openalex.org/W4414991724","https://openalex.org/W4415193753","https://openalex.org/W4416045178","https://openalex.org/W4416105445","https://openalex.org/W4416258814","https://openalex.org/W4417151837","https://openalex.org/W6948104436","https://openalex.org/W7115597726","https://openalex.org/W7125414767","https://openalex.org/W7130730707","https://openalex.org/W7139047685","https://openalex.org/W7160948833","https://openalex.org/W7164198096","https://openalex.org/W7167013799"],"related_works":["https://openalex.org/W7215112566","https://openalex.org/W7167013799","https://openalex.org/W7215055859","https://openalex.org/W7213406894","https://openalex.org/W7169809643","https://openalex.org/W4415955379","https://openalex.org/W7197018774","https://openalex.org/W7130730707","https://openalex.org/W7106678340","https://openalex.org/W4417309052"],"abstract_inverted_index":{"Vision-language-action":[0],"(VLA)":[1],"models":[2,153],"often":[3],"struggle":[4],"to":[5,7,79,134],"generalize":[6],"skill":[8,19,96,114,133,138],"combinations":[9,163],"absent":[10],"from":[11,103,127],"their":[12],"fine-tuning":[13],"demonstrations,":[14],"even":[15],"when":[16],"every":[17],"constituent":[18],"has":[20,97],"been":[21,99],"demonstrated.":[22],"We":[23,121],"focus":[24],"on":[25,161,168,176],"a":[26,40,46,50,71,177],"vision":[27],"shortcut":[28],"as":[29,39,108],"one":[30],"failure":[31],"mode:":[32],"during":[33],"fine-tuning,":[34],"visual":[35],"observations":[36,56],"can":[37,115,141],"serve":[38,107],"proxy":[41],"for":[42],"the":[43,59,77,93,112,131,147],"instruction,":[44],"so":[45],"policy":[47],"may":[48],"execute":[49],"demonstrated":[51,89,128,169],"combination":[52],"associated":[53],"with":[54,65],"similar":[55],"rather":[57],"than":[58],"instructed":[60],"combination.":[61,83],"This":[62],"motivates":[63],"training":[64],"counterfactual":[66,135],"pairs":[67,136],"formed":[68],"by":[69],"holding":[70],"demonstration":[72],"observation":[73],"fixed":[74],"while":[75,164],"changing":[76],"instruction":[78],"specify":[80],"an":[81],"undemonstrated":[82,162],"These":[84],"pairs,":[85],"however,":[86],"lack":[87],"corresponding":[88],"action":[90],"targets.":[91],"Crucially,":[92],"currently":[94],"required":[95,132],"already":[98],"demonstrated,":[100],"but":[101],"actions":[102,118],"those":[104],"executions":[105,129,145],"cannot":[106],"direct":[109],"targets":[110],"because":[111],"same":[113,148],"require":[116],"different":[117],"across":[119,144],"observations.":[120],"propose":[122],"CRAFT,":[123],"which":[124],"transfers":[125],"supervision":[126],"of":[130,146],"using":[137],"representations":[139],"that":[140],"be":[142],"reused":[143],"skill.":[149],"Across":[150],"three":[151],"VLA":[152],"and":[154],"two":[155],"simulation":[156],"benchmarks,":[157],"CRAFT":[158],"improves":[159,173],"success":[160,167],"maintaining":[165],"high":[166],"ones;":[170],"it":[171],"also":[172],"compositional":[174],"generalization":[175],"real":[178],"robot.":[179],"Project":[180],"website:":[181],"https://taegeunyang.github.io/craft/":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-03T00:00:00"}