{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7NLFFWOBUFPWWKQRD4NXRATHGW","short_pith_number":"pith:7NLFFWOB","canonical_record":{"source":{"id":"2409.12514","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-19T07:10:18Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"29fb64fb48e6a5eb3ad63b2ee904bee527a38ffc0b152de0baa1808b18c63dc6","abstract_canon_sha256":"4b8dc1f54b57add6d3130db258de0181fe6b46834717ccd6fdea4538564fde06"},"schema_version":"1.0"},"canonical_sha256":"fb5652d9c1a15f6b2a111f1b788267358946b746507846aac867f099aa1f0551","source":{"kind":"arxiv","id":"2409.12514","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12514","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12514v5","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12514","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"7NLFFWOBUFPW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"7NLFFWOBUFPWWKQR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"7NLFFWOB","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7NLFFWOBUFPWWKQRD4NXRATHGW","target":"record","payload":{"canonical_record":{"source":{"id":"2409.12514","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-19T07:10:18Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"29fb64fb48e6a5eb3ad63b2ee904bee527a38ffc0b152de0baa1808b18c63dc6","abstract_canon_sha256":"4b8dc1f54b57add6d3130db258de0181fe6b46834717ccd6fdea4538564fde06"},"schema_version":"1.0"},"canonical_sha256":"fb5652d9c1a15f6b2a111f1b788267358946b746507846aac867f099aa1f0551","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:13.622548Z","signature_b64":"7jpM5vjfNW6XtMEbWjAbSBYApo2J1+Ukq+ogol73XJA37+FJthyG4WkMnamjn7GGIxSfbGql3Wv5dvnDIesiBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb5652d9c1a15f6b2a111f1b788267358946b746507846aac867f099aa1f0551","last_reissued_at":"2026-05-17T23:38:13.621854Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:13.621854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.12514","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Dfzz4fUg25EmgmBgZG3oBcYKwgfeQUKMm0R81gLr1TZ9+uAJJDA1+5bw1xwgdYbIN5hPFHuK4HfDVHGr0scCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T15:23:43.717859Z"},"content_sha256":"0a5122520c67968898e92d92fe87ceee4ce1885132f7cdede4081761a2a30852","schema_version":"1.0","event_id":"sha256:0a5122520c67968898e92d92fe87ceee4ce1885132f7cdede4081761a2a30852"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7NLFFWOBUFPWWKQRD4NXRATHGW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"TinyVLA reaches OpenVLA-level performance on robot tasks by initializing from fast multimodal models and adding a diffusion action decoder, removing the pre-training stage entirely.","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chaomin Shen, Feifei Feng, Jian Tang, Jinming Li, Junjie Wen, Kun Wu, Minjie Zhu, Ning Liu, Ran Cheng, Yaxin Peng, Yichen Zhu, Zhiyuan Xu","submitted_at":"2024-09-19T07:10:18Z","abstract_excerpt":"Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor control and instruction comprehension through end-to-end learning processes. However, current VLA models face significant challenges: they are slow during inference and require extensive pre-training on large amounts of robotic data, making real-world deployment difficult. In this paper, we introduce a new family of compact vision-language-action models, called TinyVLA, which offers two key advantages over existing VLA models: (1) faster inference speeds, and (2) improved data efficiency, eliminating the need for"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our approach significantly outperforms the state-of-the-art VLA model, OpenVLA, in terms of speed and data efficiency, while delivering comparable or superior performance.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That initializing the policy backbone with existing high-speed multimodal models plus a diffusion decoder during fine-tuning is sufficient to eliminate the pre-training stage while preserving or improving task performance and generalization.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"TinyVLA achieves faster inference and higher data efficiency than OpenVLA on robotic manipulation tasks by initializing from high-speed multimodal models and adding a diffusion policy decoder, without any pre-training phase.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"TinyVLA reaches OpenVLA-level performance on robot tasks by initializing from fast multimodal models and adding a diffusion action decoder, removing the pre-training stage entirely.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d2290bf4b1530764ac0538952466e4728758aebbbdb0d343407da3c0cedc10b3"},"source":{"id":"2409.12514","kind":"arxiv","version":5},"verdict":{"id":"b4940e26-1ddf-4bd7-8052-f922074b9249","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T16:07:08.380660Z","strongest_claim":"Our approach significantly outperforms the state-of-the-art VLA model, OpenVLA, in terms of speed and data efficiency, while delivering comparable or superior performance.","one_line_summary":"TinyVLA achieves faster inference and higher data efficiency than OpenVLA on robotic manipulation tasks by initializing from high-speed multimodal models and adding a diffusion policy decoder, without any pre-training phase.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That initializing the policy backbone with existing high-speed multimodal models plus a diffusion decoder during fine-tuning is sufficient to eliminate the pre-training stage while preserving or improving task performance and generalization.","pith_extraction_headline":"TinyVLA reaches OpenVLA-level performance on robot tasks by initializing from fast multimodal models and adding a diffusion action decoder, removing the pre-training stage entirely."},"references":{"count":46,"sample":[{"doi":"","year":2024,"title":"Roboagent: Generalization and efficiency in robot manipulation via semantic augmentations and action chunking,","work_id":"ad2bd81c-bdcd-4b21-bc80-5819aaa4bea7","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Bridge data: Boosting generalization of robotic skills with cross-domain datasets,","work_id":"fdece732-d4e5-450c-8f75-6ca0dbdf84ac","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Diffusion policy: Visuomotor policy learning via action diffusion,","work_id":"eaca3997-9409-4ca0-a030-e58e1eae24f6","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"3d diffusion policy: Generalizable visuomo- tor policy learning via simple 3d representations,","work_id":"709db3be-7760-4bb5-bad0-1fc5c10cfd2f","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","ref_index":5,"cited_arxiv_id":"2307.09288","is_internal_anchor":true}],"resolved_work":46,"snapshot_sha256":"40a7bc759fc5fcf4399418d23e48a0662db7903bbb5d67e27a2eacbe096ef5bc","internal_anchors":11},"formal_canon":{"evidence_count":1,"snapshot_sha256":"03095fa8158cd570a3a929796d717e55d443cc61cc3ce48bb56e3987742f6747"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"b4940e26-1ddf-4bd7-8052-f922074b9249"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r8+aQC/6lgEBn6IWfJyPD0RN+5LXKyRsFeTADjV1E2XENdltP4XnpIU49ojlHblFUs6Y4jyDbzWmsVRN3O+nCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T15:23:43.718887Z"},"content_sha256":"847ae936055361d9731c1f01c687abacd8d2765d1e576b6e48c2a0cc7d6d8875","schema_version":"1.0","event_id":"sha256:847ae936055361d9731c1f01c687abacd8d2765d1e576b6e48c2a0cc7d6d8875"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7NLFFWOBUFPWWKQRD4NXRATHGW/bundle.json","state_url":"https://pith.science/pith/7NLFFWOBUFPWWKQRD4NXRATHGW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7NLFFWOBUFPWWKQRD4NXRATHGW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-10T15:23:43Z","links":{"resolver":"https://pith.science/pith/7NLFFWOBUFPWWKQRD4NXRATHGW","bundle":"https://pith.science/pith/7NLFFWOBUFPWWKQRD4NXRATHGW/bundle.json","state":"https://pith.science/pith/7NLFFWOBUFPWWKQRD4NXRATHGW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7NLFFWOBUFPWWKQRD4NXRATHGW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7NLFFWOBUFPWWKQRD4NXRATHGW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4b8dc1f54b57add6d3130db258de0181fe6b46834717ccd6fdea4538564fde06","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-19T07:10:18Z","title_canon_sha256":"29fb64fb48e6a5eb3ad63b2ee904bee527a38ffc0b152de0baa1808b18c63dc6"},"schema_version":"1.0","source":{"id":"2409.12514","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.12514","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"arxiv_version","alias_value":"2409.12514v5","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12514","created_at":"2026-05-17T23:38:13Z"},{"alias_kind":"pith_short_12","alias_value":"7NLFFWOBUFPW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"7NLFFWOBUFPWWKQR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"7NLFFWOB","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:847ae936055361d9731c1f01c687abacd8d2765d1e576b6e48c2a0cc7d6d8875","target":"graph","created_at":"2026-05-17T23:38:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our approach significantly outperforms the state-of-the-art VLA model, OpenVLA, in terms of speed and data efficiency, while delivering comparable or superior performance."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That initializing the policy backbone with existing high-speed multimodal models plus a diffusion decoder during fine-tuning is sufficient to eliminate the pre-training stage while preserving or improving task performance and generalization."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"TinyVLA achieves faster inference and higher data efficiency than OpenVLA on robotic manipulation tasks by initializing from high-speed multimodal models and adding a diffusion policy decoder, without any pre-training phase."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"TinyVLA reaches OpenVLA-level performance on robot tasks by initializing from fast multimodal models and adding a diffusion action decoder, removing the pre-training stage entirely."}],"snapshot_sha256":"d2290bf4b1530764ac0538952466e4728758aebbbdb0d343407da3c0cedc10b3"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"03095fa8158cd570a3a929796d717e55d443cc61cc3ce48bb56e3987742f6747"},"paper":{"abstract_excerpt":"Vision-Language-Action (VLA) models have shown remarkable potential in visuomotor control and instruction comprehension through end-to-end learning processes. However, current VLA models face significant challenges: they are slow during inference and require extensive pre-training on large amounts of robotic data, making real-world deployment difficult. In this paper, we introduce a new family of compact vision-language-action models, called TinyVLA, which offers two key advantages over existing VLA models: (1) faster inference speeds, and (2) improved data efficiency, eliminating the need for","authors_text":"Chaomin Shen, Feifei Feng, Jian Tang, Jinming Li, Junjie Wen, Kun Wu, Minjie Zhu, Ning Liu, Ran Cheng, Yaxin Peng, Yichen Zhu, Zhiyuan Xu","cross_cats":["cs.CV"],"headline":"TinyVLA reaches OpenVLA-level performance on robot tasks by initializing from fast multimodal models and adding a diffusion action decoder, removing the pre-training stage entirely.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-19T07:10:18Z","title":"TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation"},"references":{"count":46,"internal_anchors":11,"resolved_work":46,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Roboagent: Generalization and efficiency in robot manipulation via semantic augmentations and action chunking,","work_id":"ad2bd81c-bdcd-4b21-bc80-5819aaa4bea7","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Bridge data: Boosting generalization of robotic skills with cross-domain datasets,","work_id":"fdece732-d4e5-450c-8f75-6ca0dbdf84ac","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Diffusion policy: Visuomotor policy learning via action diffusion,","work_id":"eaca3997-9409-4ca0-a030-e58e1eae24f6","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"3d diffusion policy: Generalizable visuomo- tor policy learning via simple 3d representations,","work_id":"709db3be-7760-4bb5-bad0-1fc5c10cfd2f","year":2024},{"cited_arxiv_id":"2307.09288","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","year":2023}],"snapshot_sha256":"40a7bc759fc5fcf4399418d23e48a0662db7903bbb5d67e27a2eacbe096ef5bc"},"source":{"id":"2409.12514","kind":"arxiv","version":5},"verdict":{"created_at":"2026-05-17T16:07:08.380660Z","id":"b4940e26-1ddf-4bd7-8052-f922074b9249","model_set":{"reader":"grok-4.3"},"one_line_summary":"TinyVLA achieves faster inference and higher data efficiency than OpenVLA on robotic manipulation tasks by initializing from high-speed multimodal models and adding a diffusion policy decoder, without any pre-training phase.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"TinyVLA reaches OpenVLA-level performance on robot tasks by initializing from fast multimodal models and adding a diffusion action decoder, removing the pre-training stage entirely.","strongest_claim":"Our approach significantly outperforms the state-of-the-art VLA model, OpenVLA, in terms of speed and data efficiency, while delivering comparable or superior performance.","weakest_assumption":"That initializing the policy backbone with existing high-speed multimodal models plus a diffusion decoder during fine-tuning is sufficient to eliminate the pre-training stage while preserving or improving task performance and generalization."}},"verdict_id":"b4940e26-1ddf-4bd7-8052-f922074b9249"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0a5122520c67968898e92d92fe87ceee4ce1885132f7cdede4081761a2a30852","target":"record","created_at":"2026-05-17T23:38:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4b8dc1f54b57add6d3130db258de0181fe6b46834717ccd6fdea4538564fde06","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-09-19T07:10:18Z","title_canon_sha256":"29fb64fb48e6a5eb3ad63b2ee904bee527a38ffc0b152de0baa1808b18c63dc6"},"schema_version":"1.0","source":{"id":"2409.12514","kind":"arxiv","version":5}},"canonical_sha256":"fb5652d9c1a15f6b2a111f1b788267358946b746507846aac867f099aa1f0551","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb5652d9c1a15f6b2a111f1b788267358946b746507846aac867f099aa1f0551","first_computed_at":"2026-05-17T23:38:13.621854Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:13.621854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7jpM5vjfNW6XtMEbWjAbSBYApo2J1+Ukq+ogol73XJA37+FJthyG4WkMnamjn7GGIxSfbGql3Wv5dvnDIesiBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:13.622548Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.12514","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a5122520c67968898e92d92fe87ceee4ce1885132f7cdede4081761a2a30852","sha256:847ae936055361d9731c1f01c687abacd8d2765d1e576b6e48c2a0cc7d6d8875"],"state_sha256":"bcc59996cdb80a9ea22c15e5306c96530b0fa87bb0a034b14c3d072ab66f4b77"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"00QmicU9euU6HP3guWx3vsX/buNURNH9nc59iCsqrr13PQvR7hMrEci/KzE0sM2F0ulTCdZ6f9DfILNIm9swDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T15:23:43.723762Z","bundle_sha256":"07925f4e5a6bb8100534faf547f71a887b780d0d946dc32b385a95e66973632d"}}