{"paper":{"title":"Next-Scale Autoregressive Models for Text-to-Motion Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A next-scale autoregressive model generates text-to-motion sequences hierarchically from coarse to fine temporal resolutions.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lingjie Liu, Mingmin Zhao, Shibo Jin, Zhiwei Zheng","submitted_at":"2026-04-04T17:07:37Z","abstract_excerpt":"Autoregressive (AR) models offer stable and efficient training, but standard next-token prediction is not well aligned with the temporal structure required for text-conditioned motion generation. We introduce MoScale, a next-scale AR framework that generates motion hierarchically from coarse to fine temporal resolutions. By providing global semantics at the coarsest scale and refining them progressively, MoScale establishes a causal hierarchy better suited for long-range motion structure. To improve robustness under limited text-motion data, we further incorporate cross-scale hierarchical refi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"MoScale achieves SOTA text-to-motion performance with high training efficiency, scales effectively with model size, and generalizes zero-shot to diverse motion generation and editing tasks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that providing global semantics at the coarsest scale and refining progressively establishes a causal hierarchy better suited for long-range motion structure than standard next-token prediction.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MoScale introduces a hierarchical next-scale autoregressive framework for text-to-motion generation that achieves state-of-the-art performance by refining motions from coarse to fine temporal resolutions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A next-scale autoregressive model generates text-to-motion sequences hierarchically from coarse to fine temporal resolutions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"932dccec8ff54fd13f1a87f54763e3865992a9fb60aae87a5a965aab99e2e04c"},"source":{"id":"2604.03799","kind":"arxiv","version":2},"verdict":{"id":"20ab3674-782d-40cc-beb5-13d9ab28aee8","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T17:24:27.969157Z","strongest_claim":"MoScale achieves SOTA text-to-motion performance with high training efficiency, scales effectively with model size, and generalizes zero-shot to diverse motion generation and editing tasks.","one_line_summary":"MoScale introduces a hierarchical next-scale autoregressive framework for text-to-motion generation that achieves state-of-the-art performance by refining motions from coarse to fine temporal resolutions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that providing global semantics at the coarsest scale and refining progressively establishes a causal hierarchy better suited for long-range motion structure than standard next-token prediction.","pith_extraction_headline":"A next-scale autoregressive model generates text-to-motion sequences hierarchically from coarse to fine temporal resolutions."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.03799/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"}