{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JIAELROSEXFBHRJDWNMWKW4SP6","short_pith_number":"pith:JIAELROS","schema_version":"1.0","canonical_sha256":"4a0045c5d225ca13c523b359655b927f950ebf2bbe654e66f7688610b636ebee","source":{"kind":"arxiv","id":"2507.14049","version":1},"attestation_state":"computed","paper":{"title":"EdgeVLA: Efficient Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.RO","authors_text":"Aaron Xie, Benjamin Bolte, Jingxiang Mo, Matthew Freed, Pawe{\\l} Budzianowski, Tomasz M{\\l}oduchowski, Viraj Tipnis, Wesley Maa, Winston Hsiao","submitted_at":"2025-07-18T16:15:09Z","abstract_excerpt":"Vision-Language Models (VLMs) have emerged as a promising approach to address the data scarcity challenge in robotics, enabling the development of generalizable visuomotor control policies. While models like OpenVLA showcase the potential of this paradigm, deploying large-scale VLMs on resource-constrained mobile manipulation systems remains a significant hurdle. This paper introduces Edge VLA (EVLA), a novel approach designed to significantly enhance the inference speed of Vision-Language-Action (VLA) models. EVLA maintains the representational power of these models while enabling real-time p"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2507.14049","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-07-18T16:15:09Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"02dafba123afd638db8a84ff0c2e91958b6af02f722d7b8bdf7e15170ba91b85","abstract_canon_sha256":"bfcab59b1615a98732deac0e06b354d4254376f004fa47b1d152aecef43f61cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:27.838966Z","signature_b64":"pySFrBHt7r91Fcerdgpqm9+ph0faITJK+8/YkF7Pkp0yQhGsVsi6yqSzk83XJiFI5OH0UKbv1FRanUWQof96DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a0045c5d225ca13c523b359655b927f950ebf2bbe654e66f7688610b636ebee","last_reissued_at":"2026-07-05T11:39:27.838407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:27.838407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EdgeVLA: Efficient Vision-Language-Action Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.RO","authors_text":"Aaron Xie, Benjamin Bolte, Jingxiang Mo, Matthew Freed, Pawe{\\l} Budzianowski, Tomasz M{\\l}oduchowski, Viraj Tipnis, Wesley Maa, Winston Hsiao","submitted_at":"2025-07-18T16:15:09Z","abstract_excerpt":"Vision-Language Models (VLMs) have emerged as a promising approach to address the data scarcity challenge in robotics, enabling the development of generalizable visuomotor control policies. While models like OpenVLA showcase the potential of this paradigm, deploying large-scale VLMs on resource-constrained mobile manipulation systems remains a significant hurdle. This paper introduces Edge VLA (EVLA), a novel approach designed to significantly enhance the inference speed of Vision-Language-Action (VLA) models. EVLA maintains the representational power of these models while enabling real-time p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14049","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2507.14049/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.14049","created_at":"2026-07-05T11:39:27.838478+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.14049v1","created_at":"2026-07-05T11:39:27.838478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14049","created_at":"2026-07-05T11:39:27.838478+00:00"},{"alias_kind":"pith_short_12","alias_value":"JIAELROSEXFB","created_at":"2026-07-05T11:39:27.838478+00:00"},{"alias_kind":"pith_short_16","alias_value":"JIAELROSEXFBHRJD","created_at":"2026-07-05T11:39:27.838478+00:00"},{"alias_kind":"pith_short_8","alias_value":"JIAELROS","created_at":"2026-07-05T11:39:27.838478+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22540","citing_title":"PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19199","citing_title":"FASTER: Rethinking Real-Time Flow VLAs","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2511.18082","citing_title":"ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2603.01581","citing_title":"KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2603.17573","citing_title":"HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19199","citing_title":"FASTER: Rethinking Real-Time Flow VLAs","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05672","citing_title":"A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JIAELROSEXFBHRJDWNMWKW4SP6","json":"https://pith.science/pith/JIAELROSEXFBHRJDWNMWKW4SP6.json","graph_json":"https://pith.science/api/pith-number/JIAELROSEXFBHRJDWNMWKW4SP6/graph.json","events_json":"https://pith.science/api/pith-number/JIAELROSEXFBHRJDWNMWKW4SP6/events.json","paper":"https://pith.science/paper/JIAELROS"},"agent_actions":{"view_html":"https://pith.science/pith/JIAELROSEXFBHRJDWNMWKW4SP6","download_json":"https://pith.science/pith/JIAELROSEXFBHRJDWNMWKW4SP6.json","view_paper":"https://pith.science/paper/JIAELROS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.14049&json=true","fetch_graph":"https://pith.science/api/pith-number/JIAELROSEXFBHRJDWNMWKW4SP6/graph.json","fetch_events":"https://pith.science/api/pith-number/JIAELROSEXFBHRJDWNMWKW4SP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JIAELROSEXFBHRJDWNMWKW4SP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JIAELROSEXFBHRJDWNMWKW4SP6/action/storage_attestation","attest_author":"https://pith.science/pith/JIAELROSEXFBHRJDWNMWKW4SP6/action/author_attestation","sign_citation":"https://pith.science/pith/JIAELROSEXFBHRJDWNMWKW4SP6/action/citation_signature","submit_replication":"https://pith.science/pith/JIAELROSEXFBHRJDWNMWKW4SP6/action/replication_record"}},"created_at":"2026-07-05T11:39:27.838478+00:00","updated_at":"2026-07-05T11:39:27.838478+00:00"}