{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:24KBJ3737TE4W4LTZT3WM2I5GG","short_pith_number":"pith:24KBJ373","schema_version":"1.0","canonical_sha256":"d71414effbfcc9cb7173ccf766691d3180a92f7c49750ee633ccf2ac8ea7f5c1","source":{"kind":"arxiv","id":"2503.15451","version":3},"attestation_state":"computed","paper":{"title":"MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huaijin Pi, Jingbo Wang, Ke Fan, Liang Pan, Lixing Xiao, Shunlin Lu, Sida Peng, Xiaowei Zhou, Yueer Zhou, Ziyong Feng","submitted_at":"2025-03-19T17:32:24Z","abstract_excerpt":"This paper addresses the challenge of text-conditioned streaming motion generation, which requires us to predict the next-step human pose based on variable-length historical motions and incoming texts. Existing methods struggle to achieve streaming motion generation, e.g., diffusion models are constrained by pre-defined motion lengths, while GPT-based methods suffer from delayed response and error accumulation problem due to discretized non-causal tokenization. To solve these problems, we propose MotionStreamer, a novel framework that incorporates a continuous causal latent space into a probab"},"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":"2503.15451","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-19T17:32:24Z","cross_cats_sorted":[],"title_canon_sha256":"91765b965a00ba46b0270104c5b5c0aa4b829492076ab479804d5ebc65fde946","abstract_canon_sha256":"99fd8b5a4592a651d374dcaf12f80d23100413bf7a167d3f69d475ad70784aac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:52.273887Z","signature_b64":"4K633+lSgoQVeQLoNLY3QWy8QVcbN41G/sSzq2kw6RnCy1iDrRby+A+XaSteelFP5v/eo0upgrPSimmBxybyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d71414effbfcc9cb7173ccf766691d3180a92f7c49750ee633ccf2ac8ea7f5c1","last_reissued_at":"2026-07-05T11:49:52.273402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:52.273402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huaijin Pi, Jingbo Wang, Ke Fan, Liang Pan, Lixing Xiao, Shunlin Lu, Sida Peng, Xiaowei Zhou, Yueer Zhou, Ziyong Feng","submitted_at":"2025-03-19T17:32:24Z","abstract_excerpt":"This paper addresses the challenge of text-conditioned streaming motion generation, which requires us to predict the next-step human pose based on variable-length historical motions and incoming texts. Existing methods struggle to achieve streaming motion generation, e.g., diffusion models are constrained by pre-defined motion lengths, while GPT-based methods suffer from delayed response and error accumulation problem due to discretized non-causal tokenization. To solve these problems, we propose MotionStreamer, a novel framework that incorporates a continuous causal latent space into a probab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15451","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/2503.15451/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":"2503.15451","created_at":"2026-07-05T11:49:52.273462+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.15451v3","created_at":"2026-07-05T11:49:52.273462+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15451","created_at":"2026-07-05T11:49:52.273462+00:00"},{"alias_kind":"pith_short_12","alias_value":"24KBJ3737TE4","created_at":"2026-07-05T11:49:52.273462+00:00"},{"alias_kind":"pith_short_16","alias_value":"24KBJ3737TE4W4LT","created_at":"2026-07-05T11:49:52.273462+00:00"},{"alias_kind":"pith_short_8","alias_value":"24KBJ373","created_at":"2026-07-05T11:49:52.273462+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.07880","citing_title":"GIRAF: Towards Generalizable Human Interactions with Articulated Objects","ref_index":70,"is_internal_anchor":true},{"citing_arxiv_id":"2607.08741","citing_title":"ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14935","citing_title":"Multi-scale Coarse-to-fine Modeling for Test-time Human Motion Control","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30362","citing_title":"ReactiveBFM: Reactive Closed-Loop Motion Planning Towards Universal Humanoid Whole-Body Control","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14417","citing_title":"Before the Body Moves: Learning Anticipatory Joint Intent for Language-Conditioned Humanoid Control","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2602.12370","citing_title":"LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14417","citing_title":"Before the Body Moves: Learning Anticipatory Joint Intent for Language-Conditioned Humanoid Control","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21926","citing_title":"Seeing Without Eyes: 4D Human-Scene Understanding from Wearable IMUs","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11792","citing_title":"LottieGPT: Tokenizing Vector Animation for Autoregressive Generation","ref_index":90,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/24KBJ3737TE4W4LTZT3WM2I5GG","json":"https://pith.science/pith/24KBJ3737TE4W4LTZT3WM2I5GG.json","graph_json":"https://pith.science/api/pith-number/24KBJ3737TE4W4LTZT3WM2I5GG/graph.json","events_json":"https://pith.science/api/pith-number/24KBJ3737TE4W4LTZT3WM2I5GG/events.json","paper":"https://pith.science/paper/24KBJ373"},"agent_actions":{"view_html":"https://pith.science/pith/24KBJ3737TE4W4LTZT3WM2I5GG","download_json":"https://pith.science/pith/24KBJ3737TE4W4LTZT3WM2I5GG.json","view_paper":"https://pith.science/paper/24KBJ373","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.15451&json=true","fetch_graph":"https://pith.science/api/pith-number/24KBJ3737TE4W4LTZT3WM2I5GG/graph.json","fetch_events":"https://pith.science/api/pith-number/24KBJ3737TE4W4LTZT3WM2I5GG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24KBJ3737TE4W4LTZT3WM2I5GG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24KBJ3737TE4W4LTZT3WM2I5GG/action/storage_attestation","attest_author":"https://pith.science/pith/24KBJ3737TE4W4LTZT3WM2I5GG/action/author_attestation","sign_citation":"https://pith.science/pith/24KBJ3737TE4W4LTZT3WM2I5GG/action/citation_signature","submit_replication":"https://pith.science/pith/24KBJ3737TE4W4LTZT3WM2I5GG/action/replication_record"}},"created_at":"2026-07-05T11:49:52.273462+00:00","updated_at":"2026-07-05T11:49:52.273462+00:00"}