{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VY5A7LIYUIVIO5TPR4THUKIE4S","short_pith_number":"pith:VY5A7LIY","schema_version":"1.0","canonical_sha256":"ae3a0fad18a22a87766f8f267a2904e4a71a3b9d3b046b749c23e84bcdd8094e","source":{"kind":"arxiv","id":"2412.04062","version":3},"attestation_state":"computed","paper":{"title":"ZipAR: Parallel Auto-regressive Image Generation through Spatial Locality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bohan Zhuang, Feng Chen, Hong Zhou, Kaipeng Zhang, Shaoxuan He, Yefei He, Yuanyu He","submitted_at":"2024-12-05T10:57:08Z","abstract_excerpt":"In this paper, we propose ZipAR, a training-free, plug-and-play parallel decoding framework for accelerating auto-regressive (AR) visual generation. The motivation stems from the observation that images exhibit local structures, and spatially distant regions tend to have minimal interdependence. Given a partially decoded set of visual tokens, in addition to the original next-token prediction scheme in the row dimension, the tokens corresponding to spatially adjacent regions in the column dimension can be decoded in parallel, enabling the ``next-set prediction'' paradigm. By decoding multiple t"},"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":"2412.04062","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-05T10:57:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3c58737ec084ff67e86bd7ab4db5334f666256e5da4c6e73df8be395bd7bc621","abstract_canon_sha256":"0309ad1a8fc30a709bb59e4e00c142d87574f06ed9d59eb4578b6cbe9dfff822"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:04.383067Z","signature_b64":"CDlr9mx1GQwUBGzG77aEUaPSvUECh022Dhv6yFJHiSSbYVGXQD8jucHcaCJ6TNaqBcK0adqlHi7MVgejTPLnBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae3a0fad18a22a87766f8f267a2904e4a71a3b9d3b046b749c23e84bcdd8094e","last_reissued_at":"2026-07-05T11:29:04.382526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:04.382526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZipAR: Parallel Auto-regressive Image Generation through Spatial Locality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bohan Zhuang, Feng Chen, Hong Zhou, Kaipeng Zhang, Shaoxuan He, Yefei He, Yuanyu He","submitted_at":"2024-12-05T10:57:08Z","abstract_excerpt":"In this paper, we propose ZipAR, a training-free, plug-and-play parallel decoding framework for accelerating auto-regressive (AR) visual generation. The motivation stems from the observation that images exhibit local structures, and spatially distant regions tend to have minimal interdependence. Given a partially decoded set of visual tokens, in addition to the original next-token prediction scheme in the row dimension, the tokens corresponding to spatially adjacent regions in the column dimension can be decoded in parallel, enabling the ``next-set prediction'' paradigm. By decoding multiple t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04062","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/2412.04062/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":"2412.04062","created_at":"2026-07-05T11:29:04.382596+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04062v3","created_at":"2026-07-05T11:29:04.382596+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04062","created_at":"2026-07-05T11:29:04.382596+00:00"},{"alias_kind":"pith_short_12","alias_value":"VY5A7LIYUIVI","created_at":"2026-07-05T11:29:04.382596+00:00"},{"alias_kind":"pith_short_16","alias_value":"VY5A7LIYUIVIO5TP","created_at":"2026-07-05T11:29:04.382596+00:00"},{"alias_kind":"pith_short_8","alias_value":"VY5A7LIY","created_at":"2026-07-05T11:29:04.382596+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06078","citing_title":"Knowledge Distillation for Visual Autoregressive Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05703","citing_title":"Parallel Jacobi Decoding for Fast Autoregressive Image Generation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11567","citing_title":"Dynamic Execution Commitment of Vision-Language-Action Models","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11567","citing_title":"Dynamic Execution Commitment of Vision-Language-Action Models","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2509.12052","citing_title":"FluentAvatar: Flicker-Free Talking-Head Animation via Phoneme-Guided Autoregressive Modeling","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11567","citing_title":"Dynamic Execution Commitment of Vision-Language-Action Models","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07230","citing_title":"CASCADE: Context-Aware Relaxation for Speculative Image Decoding","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VY5A7LIYUIVIO5TPR4THUKIE4S","json":"https://pith.science/pith/VY5A7LIYUIVIO5TPR4THUKIE4S.json","graph_json":"https://pith.science/api/pith-number/VY5A7LIYUIVIO5TPR4THUKIE4S/graph.json","events_json":"https://pith.science/api/pith-number/VY5A7LIYUIVIO5TPR4THUKIE4S/events.json","paper":"https://pith.science/paper/VY5A7LIY"},"agent_actions":{"view_html":"https://pith.science/pith/VY5A7LIYUIVIO5TPR4THUKIE4S","download_json":"https://pith.science/pith/VY5A7LIYUIVIO5TPR4THUKIE4S.json","view_paper":"https://pith.science/paper/VY5A7LIY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04062&json=true","fetch_graph":"https://pith.science/api/pith-number/VY5A7LIYUIVIO5TPR4THUKIE4S/graph.json","fetch_events":"https://pith.science/api/pith-number/VY5A7LIYUIVIO5TPR4THUKIE4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VY5A7LIYUIVIO5TPR4THUKIE4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VY5A7LIYUIVIO5TPR4THUKIE4S/action/storage_attestation","attest_author":"https://pith.science/pith/VY5A7LIYUIVIO5TPR4THUKIE4S/action/author_attestation","sign_citation":"https://pith.science/pith/VY5A7LIYUIVIO5TPR4THUKIE4S/action/citation_signature","submit_replication":"https://pith.science/pith/VY5A7LIYUIVIO5TPR4THUKIE4S/action/replication_record"}},"created_at":"2026-07-05T11:29:04.382596+00:00","updated_at":"2026-07-05T11:29:04.382596+00:00"}