{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ES4NHBDICVH72CV7PV2STQANHK","short_pith_number":"pith:ES4NHBDI","schema_version":"1.0","canonical_sha256":"24b8d38468154ffd0abf7d7529c00d3aafcf6b60e58d194d2aff0ffddbdd653a","source":{"kind":"arxiv","id":"2507.20454","version":1},"attestation_state":"computed","paper":{"title":"Frequency-Aware Autoregressive Modeling for Efficient High-Resolution Image Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bohan Zhuang, Jugang Fan, Mingkui Tan, Zhuokun Chen, Zhuowei Yu","submitted_at":"2025-07-28T01:13:24Z","abstract_excerpt":"Visual autoregressive modeling, based on the next-scale prediction paradigm, exhibits notable advantages in image quality and model scalability over traditional autoregressive and diffusion models. It generates images by progressively refining resolution across multiple stages. However, the computational overhead in high-resolution stages remains a critical challenge due to the substantial number of tokens involved. In this paper, we introduce SparseVAR, a plug-and-play acceleration framework for next-scale prediction that dynamically excludes low-frequency tokens during inference without requ"},"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":"2507.20454","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-28T01:13:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0b5413d3333ae610d5cde679e00cc01c2d9c42dbc4f5ce14a10ed03e263276cb","abstract_canon_sha256":"ec7af5264a7d788e9b4f15ea41ef13f3280a58674a996323bcebf40dac7b9da8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:19.588989Z","signature_b64":"mbpoF0bNyU6M5ruL3c5vyduk/XJvB7VWIQAci+XN9gP84heJkdo/oh12eNc16oXEG6O5YRwBW4sVjQ43iZJrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24b8d38468154ffd0abf7d7529c00d3aafcf6b60e58d194d2aff0ffddbdd653a","last_reissued_at":"2026-07-05T11:44:19.588569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:19.588569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Frequency-Aware Autoregressive Modeling for Efficient High-Resolution Image Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bohan Zhuang, Jugang Fan, Mingkui Tan, Zhuokun Chen, Zhuowei Yu","submitted_at":"2025-07-28T01:13:24Z","abstract_excerpt":"Visual autoregressive modeling, based on the next-scale prediction paradigm, exhibits notable advantages in image quality and model scalability over traditional autoregressive and diffusion models. It generates images by progressively refining resolution across multiple stages. However, the computational overhead in high-resolution stages remains a critical challenge due to the substantial number of tokens involved. In this paper, we introduce SparseVAR, a plug-and-play acceleration framework for next-scale prediction that dynamically excludes low-frequency tokens during inference without requ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.20454","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/2507.20454/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":"2507.20454","created_at":"2026-07-05T11:44:19.588625+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.20454v1","created_at":"2026-07-05T11:44:19.588625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.20454","created_at":"2026-07-05T11:44:19.588625+00:00"},{"alias_kind":"pith_short_12","alias_value":"ES4NHBDICVH7","created_at":"2026-07-05T11:44:19.588625+00:00"},{"alias_kind":"pith_short_16","alias_value":"ES4NHBDICVH72CV7","created_at":"2026-07-05T11:44:19.588625+00:00"},{"alias_kind":"pith_short_8","alias_value":"ES4NHBDI","created_at":"2026-07-05T11:44:19.588625+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ES4NHBDICVH72CV7PV2STQANHK","json":"https://pith.science/pith/ES4NHBDICVH72CV7PV2STQANHK.json","graph_json":"https://pith.science/api/pith-number/ES4NHBDICVH72CV7PV2STQANHK/graph.json","events_json":"https://pith.science/api/pith-number/ES4NHBDICVH72CV7PV2STQANHK/events.json","paper":"https://pith.science/paper/ES4NHBDI"},"agent_actions":{"view_html":"https://pith.science/pith/ES4NHBDICVH72CV7PV2STQANHK","download_json":"https://pith.science/pith/ES4NHBDICVH72CV7PV2STQANHK.json","view_paper":"https://pith.science/paper/ES4NHBDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.20454&json=true","fetch_graph":"https://pith.science/api/pith-number/ES4NHBDICVH72CV7PV2STQANHK/graph.json","fetch_events":"https://pith.science/api/pith-number/ES4NHBDICVH72CV7PV2STQANHK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ES4NHBDICVH72CV7PV2STQANHK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ES4NHBDICVH72CV7PV2STQANHK/action/storage_attestation","attest_author":"https://pith.science/pith/ES4NHBDICVH72CV7PV2STQANHK/action/author_attestation","sign_citation":"https://pith.science/pith/ES4NHBDICVH72CV7PV2STQANHK/action/citation_signature","submit_replication":"https://pith.science/pith/ES4NHBDICVH72CV7PV2STQANHK/action/replication_record"}},"created_at":"2026-07-05T11:44:19.588625+00:00","updated_at":"2026-07-05T11:44:19.588625+00:00"}