{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YEZ5FF6DOYMGEPGHSSEC73PQKX","short_pith_number":"pith:YEZ5FF6D","schema_version":"1.0","canonical_sha256":"c133d297c37618623cc794882fedf055e8f3989e7512d398b397c78ff1c20d8c","source":{"kind":"arxiv","id":"2410.20927","version":3},"attestation_state":"computed","paper":{"title":"VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Guanyan Chen, Haizhou Li, Haoyang Lu, Meiling Wang, Mengxiao Hu, Te Cui, Tianxing Zhou, Yao Mu, Yi Yang, Yuan Li, Yufeng Yue, Zicai Peng","submitted_at":"2024-10-28T11:12:00Z","abstract_excerpt":"Visual imitation learning (VIL) provides an efficient and intuitive strategy for robotic systems to acquire novel skills. Recent advancements in Vision Language Models (VLMs) have demonstrated remarkable performance in vision and language reasoning capabilities for VIL tasks. Despite the progress, current VIL methods naively employ VLMs to learn high-level plans from human videos, relying on pre-defined motion primitives for executing physical interactions, which remains a major bottleneck. In this work, we present VLMimic, a novel paradigm that harnesses VLMs to directly learn even fine-grain"},"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":"2410.20927","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-10-28T11:12:00Z","cross_cats_sorted":[],"title_canon_sha256":"542b99d6fcbe4dac428a21ab3bc23c7b635c84db745ca0c3aaf36b5850388403","abstract_canon_sha256":"7876db71161c5fb64b7dea7fbf487616a05ee10ec8dd07e94be2c775052ed995"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:57.008365Z","signature_b64":"y6MNYQZau9pmHTrt1jm2ObueM0foenXJ25Q4iWm5TvhGX5bgJtF3OEvjsjM5WWHEPZVrQEbmTwK/R1NxVVveAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c133d297c37618623cc794882fedf055e8f3989e7512d398b397c78ff1c20d8c","last_reissued_at":"2026-07-05T09:28:57.007828Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:57.007828Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Guanyan Chen, Haizhou Li, Haoyang Lu, Meiling Wang, Mengxiao Hu, Te Cui, Tianxing Zhou, Yao Mu, Yi Yang, Yuan Li, Yufeng Yue, Zicai Peng","submitted_at":"2024-10-28T11:12:00Z","abstract_excerpt":"Visual imitation learning (VIL) provides an efficient and intuitive strategy for robotic systems to acquire novel skills. Recent advancements in Vision Language Models (VLMs) have demonstrated remarkable performance in vision and language reasoning capabilities for VIL tasks. Despite the progress, current VIL methods naively employ VLMs to learn high-level plans from human videos, relying on pre-defined motion primitives for executing physical interactions, which remains a major bottleneck. In this work, we present VLMimic, a novel paradigm that harnesses VLMs to directly learn even fine-grain"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20927","kind":"arxiv","version":3},"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/2410.20927/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":"2410.20927","created_at":"2026-07-05T09:28:57.007891+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20927v3","created_at":"2026-07-05T09:28:57.007891+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20927","created_at":"2026-07-05T09:28:57.007891+00:00"},{"alias_kind":"pith_short_12","alias_value":"YEZ5FF6DOYMG","created_at":"2026-07-05T09:28:57.007891+00:00"},{"alias_kind":"pith_short_16","alias_value":"YEZ5FF6DOYMGEPGH","created_at":"2026-07-05T09:28:57.007891+00:00"},{"alias_kind":"pith_short_8","alias_value":"YEZ5FF6D","created_at":"2026-07-05T09:28:57.007891+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21030","citing_title":"STEP Planner: Constructing cross-hierarchical subgoal tree as an embodied long-horizon task planner","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YEZ5FF6DOYMGEPGHSSEC73PQKX","json":"https://pith.science/pith/YEZ5FF6DOYMGEPGHSSEC73PQKX.json","graph_json":"https://pith.science/api/pith-number/YEZ5FF6DOYMGEPGHSSEC73PQKX/graph.json","events_json":"https://pith.science/api/pith-number/YEZ5FF6DOYMGEPGHSSEC73PQKX/events.json","paper":"https://pith.science/paper/YEZ5FF6D"},"agent_actions":{"view_html":"https://pith.science/pith/YEZ5FF6DOYMGEPGHSSEC73PQKX","download_json":"https://pith.science/pith/YEZ5FF6DOYMGEPGHSSEC73PQKX.json","view_paper":"https://pith.science/paper/YEZ5FF6D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20927&json=true","fetch_graph":"https://pith.science/api/pith-number/YEZ5FF6DOYMGEPGHSSEC73PQKX/graph.json","fetch_events":"https://pith.science/api/pith-number/YEZ5FF6DOYMGEPGHSSEC73PQKX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YEZ5FF6DOYMGEPGHSSEC73PQKX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YEZ5FF6DOYMGEPGHSSEC73PQKX/action/storage_attestation","attest_author":"https://pith.science/pith/YEZ5FF6DOYMGEPGHSSEC73PQKX/action/author_attestation","sign_citation":"https://pith.science/pith/YEZ5FF6DOYMGEPGHSSEC73PQKX/action/citation_signature","submit_replication":"https://pith.science/pith/YEZ5FF6DOYMGEPGHSSEC73PQKX/action/replication_record"}},"created_at":"2026-07-05T09:28:57.007891+00:00","updated_at":"2026-07-05T09:28:57.007891+00:00"}