{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3VPCIIW3CYZ3ENZD7RZAPWBJYS","short_pith_number":"pith:3VPCIIW3","schema_version":"1.0","canonical_sha256":"dd5e2422db1633b23723fc7207d829c4881a2424bf6ddbf1ee4ee5ca2e8a506e","source":{"kind":"arxiv","id":"2503.06119","version":1},"attestation_state":"computed","paper":{"title":"Unlocking Pretrained LLMs for Motion-Related Multimodal Generation: A Fine-Tuning Approach to Unify Diffusion and Next-Token Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jun Ohya, Shinichi Tanaka, Yoichi Kato, Zhao Wang","submitted_at":"2025-03-08T08:16:16Z","abstract_excerpt":"In this paper, we propose a unified framework that leverages a single pretrained LLM for Motion-related Multimodal Generation, referred to as MoMug. MoMug integrates diffusion-based continuous motion generation with the model's inherent autoregressive discrete text prediction capabilities by fine-tuning a pretrained LLM. This enables seamless switching between continuous motion output and discrete text token prediction within a single model architecture, effectively combining the strengths of both diffusion- and LLM-based approaches. Experimental results show that, compared to the most recent "},"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":"2503.06119","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-08T08:16:16Z","cross_cats_sorted":[],"title_canon_sha256":"d1e3816baa6b510e60737bc8add286531d9c1b6befa98dc3ce490550461e8d9e","abstract_canon_sha256":"a8c4faa8404aaffb0320579edb0f2cb0ca62908d53050cf3be392e26e1502d58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:54.601232Z","signature_b64":"ekOO07XtBxU9lI39E4xTkmv5nypcLPEBrfV3UuYCTW3VkzNewuKk9EqoQiTpkPtqfGN4/lhGyhropR5FPJweDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd5e2422db1633b23723fc7207d829c4881a2424bf6ddbf1ee4ee5ca2e8a506e","last_reissued_at":"2026-07-05T10:26:54.600776Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:54.600776Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlocking Pretrained LLMs for Motion-Related Multimodal Generation: A Fine-Tuning Approach to Unify Diffusion and Next-Token Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jun Ohya, Shinichi Tanaka, Yoichi Kato, Zhao Wang","submitted_at":"2025-03-08T08:16:16Z","abstract_excerpt":"In this paper, we propose a unified framework that leverages a single pretrained LLM for Motion-related Multimodal Generation, referred to as MoMug. MoMug integrates diffusion-based continuous motion generation with the model's inherent autoregressive discrete text prediction capabilities by fine-tuning a pretrained LLM. This enables seamless switching between continuous motion output and discrete text token prediction within a single model architecture, effectively combining the strengths of both diffusion- and LLM-based approaches. Experimental results show that, compared to the most recent "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06119","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/2503.06119/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":"2503.06119","created_at":"2026-07-05T10:26:54.600846+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06119v1","created_at":"2026-07-05T10:26:54.600846+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06119","created_at":"2026-07-05T10:26:54.600846+00:00"},{"alias_kind":"pith_short_12","alias_value":"3VPCIIW3CYZ3","created_at":"2026-07-05T10:26:54.600846+00:00"},{"alias_kind":"pith_short_16","alias_value":"3VPCIIW3CYZ3ENZD","created_at":"2026-07-05T10:26:54.600846+00:00"},{"alias_kind":"pith_short_8","alias_value":"3VPCIIW3","created_at":"2026-07-05T10:26:54.600846+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/3VPCIIW3CYZ3ENZD7RZAPWBJYS","json":"https://pith.science/pith/3VPCIIW3CYZ3ENZD7RZAPWBJYS.json","graph_json":"https://pith.science/api/pith-number/3VPCIIW3CYZ3ENZD7RZAPWBJYS/graph.json","events_json":"https://pith.science/api/pith-number/3VPCIIW3CYZ3ENZD7RZAPWBJYS/events.json","paper":"https://pith.science/paper/3VPCIIW3"},"agent_actions":{"view_html":"https://pith.science/pith/3VPCIIW3CYZ3ENZD7RZAPWBJYS","download_json":"https://pith.science/pith/3VPCIIW3CYZ3ENZD7RZAPWBJYS.json","view_paper":"https://pith.science/paper/3VPCIIW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06119&json=true","fetch_graph":"https://pith.science/api/pith-number/3VPCIIW3CYZ3ENZD7RZAPWBJYS/graph.json","fetch_events":"https://pith.science/api/pith-number/3VPCIIW3CYZ3ENZD7RZAPWBJYS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3VPCIIW3CYZ3ENZD7RZAPWBJYS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3VPCIIW3CYZ3ENZD7RZAPWBJYS/action/storage_attestation","attest_author":"https://pith.science/pith/3VPCIIW3CYZ3ENZD7RZAPWBJYS/action/author_attestation","sign_citation":"https://pith.science/pith/3VPCIIW3CYZ3ENZD7RZAPWBJYS/action/citation_signature","submit_replication":"https://pith.science/pith/3VPCIIW3CYZ3ENZD7RZAPWBJYS/action/replication_record"}},"created_at":"2026-07-05T10:26:54.600846+00:00","updated_at":"2026-07-05T10:26:54.600846+00:00"}