{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MTQYB5LS27E5SR6WW4HW74HSBV","short_pith_number":"pith:MTQYB5LS","schema_version":"1.0","canonical_sha256":"64e180f572d7c9d947d6b70f6ff0f20d59bfa4272b774e76d13ea9dc2a863885","source":{"kind":"arxiv","id":"2607.27205","version":1},"attestation_state":"computed","paper":{"title":"TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Chenfei Yao, Dingkang Liang, Di Xu, Han Ding, Hengyi Xie, Xiang Bai, Xianjin Wu, Xuanyang Xi, Yingying Zhu, Yiping Tang","submitted_at":"2026-07-29T17:59:58Z","abstract_excerpt":"Vision-language-action (VLA) models commonly adopt an LLM-centric $V \\to L \\to A$ pathway, where visual observations are projected into the representation space of a large language model before being decoded into robot actions. Although effective, this design incurs substantial computation and memory overhead at every policy invocation. In this work, we introduce TurboVLA, a new VLA paradigm that reformulates the conventional $V \\to L \\to A$ pathway as a direct $V + L \\to A$ mapping. Instead of using a large language model as the central interface between perception and action, TurboVLA indepe"},"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":"2607.27205","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-29T17:59:58Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"20c776d73483fd1b6ba645f871cad7bcd0bebce251b33489012d1da65f0a8c1e","abstract_canon_sha256":"d65d08c62322007732a58b3f71e6aa6afb28a96f7a9420602056f13fcc554d2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64e180f572d7c9d947d6b70f6ff0f20d59bfa4272b774e76d13ea9dc2a863885","last_reissued_at":"2026-07-30T01:24:08.613158Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:24:08.613158Z"},"graph_snapshot":{"paper":{"title":"TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Chenfei Yao, Dingkang Liang, Di Xu, Han Ding, Hengyi Xie, Xiang Bai, Xianjin Wu, Xuanyang Xi, Yingying Zhu, Yiping Tang","submitted_at":"2026-07-29T17:59:58Z","abstract_excerpt":"Vision-language-action (VLA) models commonly adopt an LLM-centric $V \\to L \\to A$ pathway, where visual observations are projected into the representation space of a large language model before being decoded into robot actions. Although effective, this design incurs substantial computation and memory overhead at every policy invocation. In this work, we introduce TurboVLA, a new VLA paradigm that reformulates the conventional $V \\to L \\to A$ pathway as a direct $V + L \\to A$ mapping. Instead of using a large language model as the central interface between perception and action, TurboVLA indepe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.27205","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/2607.27205/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":"2607.27205","created_at":"2026-07-30T01:24:08.618179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.27205v1","created_at":"2026-07-30T01:24:08.618179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.27205","created_at":"2026-07-30T01:24:08.618179+00:00"},{"alias_kind":"pith_short_12","alias_value":"MTQYB5LS27E5","created_at":"2026-07-30T01:24:08.618179+00:00"},{"alias_kind":"pith_short_16","alias_value":"MTQYB5LS27E5SR6W","created_at":"2026-07-30T01:24:08.618179+00:00"},{"alias_kind":"pith_short_8","alias_value":"MTQYB5LS","created_at":"2026-07-30T01:24:08.618179+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MTQYB5LS27E5SR6WW4HW74HSBV","json":"https://pith.science/pith/MTQYB5LS27E5SR6WW4HW74HSBV.json","graph_json":"https://pith.science/api/pith-number/MTQYB5LS27E5SR6WW4HW74HSBV/graph.json","events_json":"https://pith.science/api/pith-number/MTQYB5LS27E5SR6WW4HW74HSBV/events.json","paper":"https://pith.science/paper/MTQYB5LS"},"agent_actions":{"view_html":"https://pith.science/pith/MTQYB5LS27E5SR6WW4HW74HSBV","download_json":"https://pith.science/pith/MTQYB5LS27E5SR6WW4HW74HSBV.json","view_paper":"https://pith.science/paper/MTQYB5LS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.27205&json=true","fetch_graph":"https://pith.science/api/pith-number/MTQYB5LS27E5SR6WW4HW74HSBV/graph.json","fetch_events":"https://pith.science/api/pith-number/MTQYB5LS27E5SR6WW4HW74HSBV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MTQYB5LS27E5SR6WW4HW74HSBV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MTQYB5LS27E5SR6WW4HW74HSBV/action/storage_attestation","attest_author":"https://pith.science/pith/MTQYB5LS27E5SR6WW4HW74HSBV/action/author_attestation","sign_citation":"https://pith.science/pith/MTQYB5LS27E5SR6WW4HW74HSBV/action/citation_signature","submit_replication":"https://pith.science/pith/MTQYB5LS27E5SR6WW4HW74HSBV/action/replication_record"}},"created_at":"2026-07-30T01:24:08.618179+00:00","updated_at":"2026-07-30T01:24:08.618179+00:00"}