{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N23LRJVU7VCXMHY2TVZFE2XGSA","short_pith_number":"pith:N23LRJVU","schema_version":"1.0","canonical_sha256":"6eb6b8a6b4fd45761f1a9d72526ae69022bb5be5d87e62a554ab0d40c456cbb5","source":{"kind":"arxiv","id":"2503.16492","version":3},"attestation_state":"computed","paper":{"title":"FAM-HRI: Foundation-Model Assisted Multi-Modal Human-Robot Interaction Combining Gaze and Speech","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.HC","authors_text":"Andreas Zell, Benjamin Kiefer, Boya Zhang, Peizheng Li, Shenghai Yuan, Tianchen Deng, Yuzhi Lai","submitted_at":"2025-03-11T02:30:15Z","abstract_excerpt":"ffective Human-Robot Interaction (HRI) is crucial for enhancing accessibility and usability in real-world robotics applications. However, existing solutions often rely on gesture- only or language-only commands, making interaction inefficient and ambiguous, particularly for users with physical impairments. In this paper, we introduce FAM-HRI, an efficient multimodal framework for HRI that integrates language and gaze inputs via foundation models. By leveraging lightweight Meta ARIA glasses, our system captures real-time multimodal signals and utilizes large language models (LLMs) to fuse user "},"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":"2503.16492","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.HC","submitted_at":"2025-03-11T02:30:15Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"d86472266b7d551eb13e436f548a673c811bb4cd929b7c8246d2bd81d5fd8879","abstract_canon_sha256":"716c614b41c3e5724e678de778acf8b50cefd97037c51874355b41ef72394957"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:27.838456Z","signature_b64":"rDHeYt5HUmSGd2UdzS0yJU7mL385lXvpulWY4VC4ojc7EXN2MHrFmIaSRV8gqpFmzqiCOlmUMKbZ6HUtasxbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6eb6b8a6b4fd45761f1a9d72526ae69022bb5be5d87e62a554ab0d40c456cbb5","last_reissued_at":"2026-05-20T00:05:27.837644Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:27.837644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FAM-HRI: Foundation-Model Assisted Multi-Modal Human-Robot Interaction Combining Gaze and Speech","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.HC","authors_text":"Andreas Zell, Benjamin Kiefer, Boya Zhang, Peizheng Li, Shenghai Yuan, Tianchen Deng, Yuzhi Lai","submitted_at":"2025-03-11T02:30:15Z","abstract_excerpt":"ffective Human-Robot Interaction (HRI) is crucial for enhancing accessibility and usability in real-world robotics applications. However, existing solutions often rely on gesture- only or language-only commands, making interaction inefficient and ambiguous, particularly for users with physical impairments. In this paper, we introduce FAM-HRI, an efficient multimodal framework for HRI that integrates language and gaze inputs via foundation models. By leveraging lightweight Meta ARIA glasses, our system captures real-time multimodal signals and utilizes large language models (LLMs) to fuse user "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16492","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/2503.16492/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":"2503.16492","created_at":"2026-05-20T00:05:27.837772+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16492v3","created_at":"2026-05-20T00:05:27.837772+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16492","created_at":"2026-05-20T00:05:27.837772+00:00"},{"alias_kind":"pith_short_12","alias_value":"N23LRJVU7VCX","created_at":"2026-05-20T00:05:27.837772+00:00"},{"alias_kind":"pith_short_16","alias_value":"N23LRJVU7VCXMHY2","created_at":"2026-05-20T00:05:27.837772+00:00"},{"alias_kind":"pith_short_8","alias_value":"N23LRJVU","created_at":"2026-05-20T00:05:27.837772+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.10719","citing_title":"SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N23LRJVU7VCXMHY2TVZFE2XGSA","json":"https://pith.science/pith/N23LRJVU7VCXMHY2TVZFE2XGSA.json","graph_json":"https://pith.science/api/pith-number/N23LRJVU7VCXMHY2TVZFE2XGSA/graph.json","events_json":"https://pith.science/api/pith-number/N23LRJVU7VCXMHY2TVZFE2XGSA/events.json","paper":"https://pith.science/paper/N23LRJVU"},"agent_actions":{"view_html":"https://pith.science/pith/N23LRJVU7VCXMHY2TVZFE2XGSA","download_json":"https://pith.science/pith/N23LRJVU7VCXMHY2TVZFE2XGSA.json","view_paper":"https://pith.science/paper/N23LRJVU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16492&json=true","fetch_graph":"https://pith.science/api/pith-number/N23LRJVU7VCXMHY2TVZFE2XGSA/graph.json","fetch_events":"https://pith.science/api/pith-number/N23LRJVU7VCXMHY2TVZFE2XGSA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N23LRJVU7VCXMHY2TVZFE2XGSA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N23LRJVU7VCXMHY2TVZFE2XGSA/action/storage_attestation","attest_author":"https://pith.science/pith/N23LRJVU7VCXMHY2TVZFE2XGSA/action/author_attestation","sign_citation":"https://pith.science/pith/N23LRJVU7VCXMHY2TVZFE2XGSA/action/citation_signature","submit_replication":"https://pith.science/pith/N23LRJVU7VCXMHY2TVZFE2XGSA/action/replication_record"}},"created_at":"2026-05-20T00:05:27.837772+00:00","updated_at":"2026-05-20T00:05:27.837772+00:00"}