{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N34MAQ6UFFAHZQV6LQB2JQFRYF","short_pith_number":"pith:N34MAQ6U","schema_version":"1.0","canonical_sha256":"6ef8c043d429407cc2be5c03a4c0b1c1628fb1366be54cc9784f8e91f0f15747","source":{"kind":"arxiv","id":"2406.09399","version":1},"attestation_state":"computed","paper":{"title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binyue Peng, Junke Wang, Yi Jiang, Yu-Gang Jiang, Zehuan Yuan, Zuxuan Wu","submitted_at":"2024-06-13T17:59:26Z","abstract_excerpt":"Tokenizer, serving as a translator to map the intricate visual data into a compact latent space, lies at the core of visual generative models. Based on the finding that existing tokenizers are tailored to image or video inputs, this paper presents OmniTokenizer, a transformer-based tokenizer for joint image and video tokenization. OmniTokenizer is designed with a spatial-temporal decoupled architecture, which integrates window and causal attention for spatial and temporal modeling. To exploit the complementary nature of image and video data, we further propose a progressive training strategy, "},"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":"2406.09399","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T17:59:26Z","cross_cats_sorted":[],"title_canon_sha256":"85ed6b8b174de2ed70cc47831dcd3da4ff4bd517fa3572a78271d4ad73a9501b","abstract_canon_sha256":"695366520e789a2eebb984fb5d15d901053d7712e863b69d5d1c4f867bd2cc36"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:32.515753Z","signature_b64":"qQgW2/NSWhQp0DZbZGwvf0UFEYzOIJnTC64ZIZLUVrOSduZfNtgFJm3Wf5ezjekGrDWFKBOV5HzgYgetH81CBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ef8c043d429407cc2be5c03a4c0b1c1628fb1366be54cc9784f8e91f0f15747","last_reissued_at":"2026-07-05T08:31:32.515197Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:32.515197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binyue Peng, Junke Wang, Yi Jiang, Yu-Gang Jiang, Zehuan Yuan, Zuxuan Wu","submitted_at":"2024-06-13T17:59:26Z","abstract_excerpt":"Tokenizer, serving as a translator to map the intricate visual data into a compact latent space, lies at the core of visual generative models. Based on the finding that existing tokenizers are tailored to image or video inputs, this paper presents OmniTokenizer, a transformer-based tokenizer for joint image and video tokenization. OmniTokenizer is designed with a spatial-temporal decoupled architecture, which integrates window and causal attention for spatial and temporal modeling. To exploit the complementary nature of image and video data, we further propose a progressive training strategy, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09399","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/2406.09399/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":"2406.09399","created_at":"2026-07-05T08:31:32.515269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09399v1","created_at":"2026-07-05T08:31:32.515269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09399","created_at":"2026-07-05T08:31:32.515269+00:00"},{"alias_kind":"pith_short_12","alias_value":"N34MAQ6UFFAH","created_at":"2026-07-05T08:31:32.515269+00:00"},{"alias_kind":"pith_short_16","alias_value":"N34MAQ6UFFAHZQV6","created_at":"2026-07-05T08:31:32.515269+00:00"},{"alias_kind":"pith_short_8","alias_value":"N34MAQ6U","created_at":"2026-07-05T08:31:32.515269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02631","citing_title":"Wavelet as Tokenizer: Preliminary Results on a Shared Wavelet Token Schema for Natural Signals","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30904","citing_title":"MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2503.19325","citing_title":"Long-Context Autoregressive Video Modeling with Next-Frame Prediction","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06481","citing_title":"OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2501.03575","citing_title":"Cosmos World Foundation Model Platform for Physical AI","ref_index":203,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N34MAQ6UFFAHZQV6LQB2JQFRYF","json":"https://pith.science/pith/N34MAQ6UFFAHZQV6LQB2JQFRYF.json","graph_json":"https://pith.science/api/pith-number/N34MAQ6UFFAHZQV6LQB2JQFRYF/graph.json","events_json":"https://pith.science/api/pith-number/N34MAQ6UFFAHZQV6LQB2JQFRYF/events.json","paper":"https://pith.science/paper/N34MAQ6U"},"agent_actions":{"view_html":"https://pith.science/pith/N34MAQ6UFFAHZQV6LQB2JQFRYF","download_json":"https://pith.science/pith/N34MAQ6UFFAHZQV6LQB2JQFRYF.json","view_paper":"https://pith.science/paper/N34MAQ6U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09399&json=true","fetch_graph":"https://pith.science/api/pith-number/N34MAQ6UFFAHZQV6LQB2JQFRYF/graph.json","fetch_events":"https://pith.science/api/pith-number/N34MAQ6UFFAHZQV6LQB2JQFRYF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N34MAQ6UFFAHZQV6LQB2JQFRYF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N34MAQ6UFFAHZQV6LQB2JQFRYF/action/storage_attestation","attest_author":"https://pith.science/pith/N34MAQ6UFFAHZQV6LQB2JQFRYF/action/author_attestation","sign_citation":"https://pith.science/pith/N34MAQ6UFFAHZQV6LQB2JQFRYF/action/citation_signature","submit_replication":"https://pith.science/pith/N34MAQ6UFFAHZQV6LQB2JQFRYF/action/replication_record"}},"created_at":"2026-07-05T08:31:32.515269+00:00","updated_at":"2026-07-05T08:31:32.515269+00:00"}