{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IYVGRVEC4E4JST2F2O27BWD6P2","short_pith_number":"pith:IYVGRVEC","schema_version":"1.0","canonical_sha256":"462a68d482e138994f45d3b5f0d87e7eae975a186a873c9270071e9d56973ad4","source":{"kind":"arxiv","id":"2606.07383","version":1},"attestation_state":"computed","paper":{"title":"RhinoVLA Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Chenyang Zhou, Guanghui He, Guanglei Ding, Haibin Gao, Huixi Intelligence: Chen Zhang, Jiajia Chen, Jianyong Zhang, Lianyi Yu, Ningyi Xu, Ping Xu, Qingchen Li, Yijia Zhang, Yingjun Hu, Yuxi Liu","submitted_at":"2026-06-05T15:21:41Z","abstract_excerpt":"Vision-Language-Action (VLA) models have shown strong potential for robotic manipulation, but real-time deployment on edge hardware remains challenging. In this work, we identify VLM visual and context tokens as a major source of deployment latency: for GEMM-dominated projection operators, computation grows linearly with the number of input tokens when model dimensions are fixed. Motivated by this observation, we propose RhinoVLA, a deployment-oriented VLA model co-designed with the Huixi R1 edge SoC. RhinoVLA adopts a token-efficient Qwen3-VL backbone and a continuous Action Expert, reducing "},"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":"2606.07383","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-05T15:21:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6816877cde1a630b2911049af7f8a3faedfacf92c92e44829735f30216a49c18","abstract_canon_sha256":"2c9980557d69915f8dfd725f345a0c43e525d30fa2d4c15161a913988248f8c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:05:23.788058Z","signature_b64":"Gu5/XXUmgRhN1LiVgPT+Nnlup2+LawUcBFp7jwFia/gXSxsFTxbMAAxkPOBz2oM3M3w4jlISwSDWq1LkVKKPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"462a68d482e138994f45d3b5f0d87e7eae975a186a873c9270071e9d56973ad4","last_reissued_at":"2026-06-08T01:05:23.787301Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:05:23.787301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RhinoVLA Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Chenyang Zhou, Guanghui He, Guanglei Ding, Haibin Gao, Huixi Intelligence: Chen Zhang, Jiajia Chen, Jianyong Zhang, Lianyi Yu, Ningyi Xu, Ping Xu, Qingchen Li, Yijia Zhang, Yingjun Hu, Yuxi Liu","submitted_at":"2026-06-05T15:21:41Z","abstract_excerpt":"Vision-Language-Action (VLA) models have shown strong potential for robotic manipulation, but real-time deployment on edge hardware remains challenging. In this work, we identify VLM visual and context tokens as a major source of deployment latency: for GEMM-dominated projection operators, computation grows linearly with the number of input tokens when model dimensions are fixed. Motivated by this observation, we propose RhinoVLA, a deployment-oriented VLA model co-designed with the Huixi R1 edge SoC. RhinoVLA adopts a token-efficient Qwen3-VL backbone and a continuous Action Expert, reducing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07383","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/2606.07383/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":"2606.07383","created_at":"2026-06-08T01:05:23.787441+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07383v1","created_at":"2026-06-08T01:05:23.787441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07383","created_at":"2026-06-08T01:05:23.787441+00:00"},{"alias_kind":"pith_short_12","alias_value":"IYVGRVEC4E4J","created_at":"2026-06-08T01:05:23.787441+00:00"},{"alias_kind":"pith_short_16","alias_value":"IYVGRVEC4E4JST2F","created_at":"2026-06-08T01:05:23.787441+00:00"},{"alias_kind":"pith_short_8","alias_value":"IYVGRVEC","created_at":"2026-06-08T01:05:23.787441+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/IYVGRVEC4E4JST2F2O27BWD6P2","json":"https://pith.science/pith/IYVGRVEC4E4JST2F2O27BWD6P2.json","graph_json":"https://pith.science/api/pith-number/IYVGRVEC4E4JST2F2O27BWD6P2/graph.json","events_json":"https://pith.science/api/pith-number/IYVGRVEC4E4JST2F2O27BWD6P2/events.json","paper":"https://pith.science/paper/IYVGRVEC"},"agent_actions":{"view_html":"https://pith.science/pith/IYVGRVEC4E4JST2F2O27BWD6P2","download_json":"https://pith.science/pith/IYVGRVEC4E4JST2F2O27BWD6P2.json","view_paper":"https://pith.science/paper/IYVGRVEC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07383&json=true","fetch_graph":"https://pith.science/api/pith-number/IYVGRVEC4E4JST2F2O27BWD6P2/graph.json","fetch_events":"https://pith.science/api/pith-number/IYVGRVEC4E4JST2F2O27BWD6P2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IYVGRVEC4E4JST2F2O27BWD6P2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IYVGRVEC4E4JST2F2O27BWD6P2/action/storage_attestation","attest_author":"https://pith.science/pith/IYVGRVEC4E4JST2F2O27BWD6P2/action/author_attestation","sign_citation":"https://pith.science/pith/IYVGRVEC4E4JST2F2O27BWD6P2/action/citation_signature","submit_replication":"https://pith.science/pith/IYVGRVEC4E4JST2F2O27BWD6P2/action/replication_record"}},"created_at":"2026-06-08T01:05:23.787441+00:00","updated_at":"2026-06-08T01:05:23.787441+00:00"}