{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ATFJD7V43TN26Z3TB5HNOKU4XV","short_pith_number":"pith:ATFJD7V4","schema_version":"1.0","canonical_sha256":"04ca91febcdcdbaf67730f4ed72a9cbd61e2db89584aea1c08e604f942cff0d1","source":{"kind":"arxiv","id":"2502.05415","version":2},"attestation_state":"computed","paper":{"title":"UniCMs: A Unified Consistency Model For Efficient Multimodal Generation and Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenkai Xu, TianQi Hou, Xu Wang, Yishun Li, Zhenyi Liao, Zhijie Deng","submitted_at":"2025-02-08T02:52:25Z","abstract_excerpt":"Consistency models (CMs) have shown promise in the efficient generation of both image and text. This raises the natural question of whether we can learn a unified CM for efficient multimodal generation (e.g., text-to-image) and understanding (e.g., image-to-text). Intuitively, such a model could be acquired by applying the consistency distillation (CD) to existing unified multimodal models. However, the key challenge is establishing a unified denoising perspective for both image and text generation, which is essential for establishing the consistency mapping. To tackle this, at the representat"},"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":"2502.05415","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-08T02:52:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2f7dfa7ddf40d611c7a4b87db98cfb3a71da6270d4eb1ded369ec88440d7fc71","abstract_canon_sha256":"c99e8cf7a6477847c031e7e9897b712d0169f08816c6c32e770e5a7d138014be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:45.347997Z","signature_b64":"FqXyDNvmIViEgmxpWkbbrnjDw+5X96jxJH+oAbApnTCR+/UG/r2TTsPnGi/NDwzCMfzlPZbNaCkQ2drT9Lr9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04ca91febcdcdbaf67730f4ed72a9cbd61e2db89584aea1c08e604f942cff0d1","last_reissued_at":"2026-07-05T11:04:45.347452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:45.347452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniCMs: A Unified Consistency Model For Efficient Multimodal Generation and Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenkai Xu, TianQi Hou, Xu Wang, Yishun Li, Zhenyi Liao, Zhijie Deng","submitted_at":"2025-02-08T02:52:25Z","abstract_excerpt":"Consistency models (CMs) have shown promise in the efficient generation of both image and text. This raises the natural question of whether we can learn a unified CM for efficient multimodal generation (e.g., text-to-image) and understanding (e.g., image-to-text). Intuitively, such a model could be acquired by applying the consistency distillation (CD) to existing unified multimodal models. However, the key challenge is establishing a unified denoising perspective for both image and text generation, which is essential for establishing the consistency mapping. To tackle this, at the representat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05415","kind":"arxiv","version":2},"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/2502.05415/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":"2502.05415","created_at":"2026-07-05T11:04:45.347514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05415v2","created_at":"2026-07-05T11:04:45.347514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05415","created_at":"2026-07-05T11:04:45.347514+00:00"},{"alias_kind":"pith_short_12","alias_value":"ATFJD7V43TN2","created_at":"2026-07-05T11:04:45.347514+00:00"},{"alias_kind":"pith_short_16","alias_value":"ATFJD7V43TN26Z3T","created_at":"2026-07-05T11:04:45.347514+00:00"},{"alias_kind":"pith_short_8","alias_value":"ATFJD7V4","created_at":"2026-07-05T11:04:45.347514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.20512","citing_title":"Adversarial Concept Distillation for One-Step Diffusion Personalization","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14362","citing_title":"DeepEyes: Incentivizing \"Thinking with Images\" via Reinforcement Learning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2502.09992","citing_title":"Large Language Diffusion Models","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ATFJD7V43TN26Z3TB5HNOKU4XV","json":"https://pith.science/pith/ATFJD7V43TN26Z3TB5HNOKU4XV.json","graph_json":"https://pith.science/api/pith-number/ATFJD7V43TN26Z3TB5HNOKU4XV/graph.json","events_json":"https://pith.science/api/pith-number/ATFJD7V43TN26Z3TB5HNOKU4XV/events.json","paper":"https://pith.science/paper/ATFJD7V4"},"agent_actions":{"view_html":"https://pith.science/pith/ATFJD7V43TN26Z3TB5HNOKU4XV","download_json":"https://pith.science/pith/ATFJD7V43TN26Z3TB5HNOKU4XV.json","view_paper":"https://pith.science/paper/ATFJD7V4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05415&json=true","fetch_graph":"https://pith.science/api/pith-number/ATFJD7V43TN26Z3TB5HNOKU4XV/graph.json","fetch_events":"https://pith.science/api/pith-number/ATFJD7V43TN26Z3TB5HNOKU4XV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ATFJD7V43TN26Z3TB5HNOKU4XV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ATFJD7V43TN26Z3TB5HNOKU4XV/action/storage_attestation","attest_author":"https://pith.science/pith/ATFJD7V43TN26Z3TB5HNOKU4XV/action/author_attestation","sign_citation":"https://pith.science/pith/ATFJD7V43TN26Z3TB5HNOKU4XV/action/citation_signature","submit_replication":"https://pith.science/pith/ATFJD7V43TN26Z3TB5HNOKU4XV/action/replication_record"}},"created_at":"2026-07-05T11:04:45.347514+00:00","updated_at":"2026-07-05T11:04:45.347514+00:00"}