{"id":"https://openalex.org/W7163517716","doi":"https://doi.org/10.1109/lra.2026.3700379","title":"RLRC: Reinforcement Learning-Based Recovery for Compressed Vision-Language-Action Models","display_name":"RLRC: Reinforcement Learning-Based Recovery for Compressed Vision-Language-Action Models","publication_year":2026,"publication_date":"2026-06-04","ids":{"openalex":"https://openalex.org/W7163517716","doi":"https://doi.org/10.1109/lra.2026.3700379"},"language":null,"primary_location":{"id":"doi:10.1109/lra.2026.3700379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3700379","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.17639","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137844181","display_name":"Yuxuan Chen","orcid":null},"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":"Yuxuan Chen","raw_affiliation_strings":["State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0005-9418-1686","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085565570","display_name":"Yixin Han","orcid":null},"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":"Yixin Han","raw_affiliation_strings":["State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0006-9771-3489","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121194169","display_name":"Yize Huang","orcid":null},"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":"Yize Huang","raw_affiliation_strings":["State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-6179-9053","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041607266","display_name":"Li X","orcid":"https://orcid.org/0000-0002-5981-2762"},"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":"Xiao Li","raw_affiliation_strings":["State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2565-9883","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":4.7596,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.95882293,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"11","issue":"7","first_page":"8864","last_page":"8871"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7024000287055969,"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":0.7024000287055969,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.08389999717473984,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.05220000073313713,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.357699990272522},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.3375000059604645},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.2815999984741211},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2815999984741211},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.2606000006198883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4578000009059906},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.357699990272522},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2815999984741211},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2815999984741211},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2574999928474426},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2476000040769577},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24639999866485596},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24469999969005585}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lra.2026.3700379","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lra.2026.3700379","pdf_url":null,"source":{"id":"https://openalex.org/S4210169774","display_name":"IEEE Robotics and Automation Letters","issn_l":"2377-3766","issn":["2377-3766","2377-3774"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Robotics and Automation Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2506.17639","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2506.17639","pdf_url":"https://arxiv.org/pdf/2506.17639","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.17639","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2506.17639","pdf_url":"https://arxiv.org/pdf/2506.17639","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3305530808","display_name":null,"funder_award_id":"MSVZD202608","funder_id":"https://openalex.org/F4320327024","funder_display_name":"State Key Laboratory of Mechanical System and Vibration"},{"id":"https://openalex.org/G6244767003","display_name":null,"funder_award_id":"24511103400","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"},{"id":"https://openalex.org/G676121582","display_name":null,"funder_award_id":"52405029","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"},{"id":"https://openalex.org/F4320327024","display_name":"State Key Laboratory of Mechanical System and Vibration","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7163517716.pdf","grobid_xml":"https://content.openalex.org/works/W7163517716.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language-Action":[0],"models":[1],"(VLA)":[2],"have":[3],"demonstrated":[4],"remarkable":[5],"capabilities":[6],"and":[7,19,53,64,66,77,84,96],"strong":[8],"potential":[9],"in":[10],"complex":[11],"robotic":[12],"manipulation.":[13],"However,":[14],"their":[15],"large":[16],"parameter":[17],"sizes":[18],"high":[20],"inference":[21,98],"latency":[22],"hinder":[23],"real-world":[24],"deployment,":[25],"especially":[26],"on":[27,45],"resource-constrained":[28],"platforms.":[29],"To":[30],"address":[31],"this,":[32],"we":[33,48],"conduct":[34],"a":[35,50,73],"systematic":[36],"empirical":[37],"study":[38],"of":[39,57],"model":[40],"compression":[41,52,119],"for":[42,124],"VLAs.":[43],"Building":[44],"these":[46],"insights,":[47],"presentRLRC,":[49],"three-stage":[51],"recovery":[54,61],"pipeline":[55],"consisting":[56],"structured":[58],"pruning,":[59],"performance":[60],"via":[62],"SFT":[63],"RL,":[65],"subsequent":[67],"quantization.":[68],"The":[69],"RL":[70],"stage":[71],"incorporates":[72],"critic":[74],"warm-up":[75],"strategy":[76],"BC":[78],"loss":[79],"regularization":[80],"to":[81,91],"stabilize":[82],"training":[83],"preserve":[85],"policy":[86],"behavior.":[87],"RLRC":[88,115],"achieves":[89],"up":[90],"an":[92],"8\u00d7":[93],"memory":[94],"reduction":[95],"2.3\u00d7":[97],"speedup":[99],"while":[100],"maintaining":[101],"the":[102],"original":[103],"task":[104],"success":[105],"rate.":[106],"Extensive":[107],"experiments":[108],"across":[109],"multiple":[110],"VLA":[111],"backbones":[112],"show":[113],"that":[114],"consistently":[116],"outperforms":[117],"existing":[118],"baselines,":[120],"highlighting":[121],"its":[122],"effectiveness":[123],"on-device":[125],"deployment.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2026-06-05T00:00:00"}