{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NDDQLT2KUDYI5ZBUIFBYHVSAEM","short_pith_number":"pith:NDDQLT2K","schema_version":"1.0","canonical_sha256":"68c705cf4aa0f08ee434414383d640232acb229356a5ac0c3b254c37a680fa64","source":{"kind":"arxiv","id":"2505.16335","version":1},"attestation_state":"computed","paper":{"title":"FPQVAR: Floating Point Quantization for Visual Autoregressive Model with FPGA Hardware Co-design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Meng Li, Qingyu Guo, Renjie Wei, Songqiang Xu","submitted_at":"2025-05-22T07:47:51Z","abstract_excerpt":"Visual autoregressive (VAR) modeling has marked a paradigm shift in image generation from next-token prediction to next-scale prediction. VAR predicts a set of tokens at each step from coarse to fine scale, leading to better image quality and faster inference speed compared to existing diffusion models. However, the large parameter size and computation cost hinder its deployment on edge devices. To reduce the memory and computation cost, we propose FPQVAR, an efficient post-training floating-point (FP) quantization framework for VAR featuring algorithm and hardware co-design. At the algorithm "},"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":"2505.16335","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T07:47:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"864e7225c475f709dab1dd51815c0406934ac9903de1e770e8eeb2e0a3ea0af4","abstract_canon_sha256":"4d70aecc9e087c20e91bb70bcc4a9db2a621a2dfdb4cdd0b220e9d596c13ce60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:33.873181Z","signature_b64":"wRbiGJSpAoAuF7+xBDbrmjSWY/9I6P++ObuYRRe+XBh/K4m7c7mBUNetm6EMs1EGUL6u+8xdRP/iShRGBLM2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68c705cf4aa0f08ee434414383d640232acb229356a5ac0c3b254c37a680fa64","last_reissued_at":"2026-07-05T11:07:33.872705Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:33.872705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FPQVAR: Floating Point Quantization for Visual Autoregressive Model with FPGA Hardware Co-design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Meng Li, Qingyu Guo, Renjie Wei, Songqiang Xu","submitted_at":"2025-05-22T07:47:51Z","abstract_excerpt":"Visual autoregressive (VAR) modeling has marked a paradigm shift in image generation from next-token prediction to next-scale prediction. VAR predicts a set of tokens at each step from coarse to fine scale, leading to better image quality and faster inference speed compared to existing diffusion models. However, the large parameter size and computation cost hinder its deployment on edge devices. To reduce the memory and computation cost, we propose FPQVAR, an efficient post-training floating-point (FP) quantization framework for VAR featuring algorithm and hardware co-design. At the algorithm "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16335","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/2505.16335/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":"2505.16335","created_at":"2026-07-05T11:07:33.872763+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16335v1","created_at":"2026-07-05T11:07:33.872763+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16335","created_at":"2026-07-05T11:07:33.872763+00:00"},{"alias_kind":"pith_short_12","alias_value":"NDDQLT2KUDYI","created_at":"2026-07-05T11:07:33.872763+00:00"},{"alias_kind":"pith_short_16","alias_value":"NDDQLT2KUDYI5ZBU","created_at":"2026-07-05T11:07:33.872763+00:00"},{"alias_kind":"pith_short_8","alias_value":"NDDQLT2K","created_at":"2026-07-05T11:07:33.872763+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/NDDQLT2KUDYI5ZBUIFBYHVSAEM","json":"https://pith.science/pith/NDDQLT2KUDYI5ZBUIFBYHVSAEM.json","graph_json":"https://pith.science/api/pith-number/NDDQLT2KUDYI5ZBUIFBYHVSAEM/graph.json","events_json":"https://pith.science/api/pith-number/NDDQLT2KUDYI5ZBUIFBYHVSAEM/events.json","paper":"https://pith.science/paper/NDDQLT2K"},"agent_actions":{"view_html":"https://pith.science/pith/NDDQLT2KUDYI5ZBUIFBYHVSAEM","download_json":"https://pith.science/pith/NDDQLT2KUDYI5ZBUIFBYHVSAEM.json","view_paper":"https://pith.science/paper/NDDQLT2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16335&json=true","fetch_graph":"https://pith.science/api/pith-number/NDDQLT2KUDYI5ZBUIFBYHVSAEM/graph.json","fetch_events":"https://pith.science/api/pith-number/NDDQLT2KUDYI5ZBUIFBYHVSAEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NDDQLT2KUDYI5ZBUIFBYHVSAEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NDDQLT2KUDYI5ZBUIFBYHVSAEM/action/storage_attestation","attest_author":"https://pith.science/pith/NDDQLT2KUDYI5ZBUIFBYHVSAEM/action/author_attestation","sign_citation":"https://pith.science/pith/NDDQLT2KUDYI5ZBUIFBYHVSAEM/action/citation_signature","submit_replication":"https://pith.science/pith/NDDQLT2KUDYI5ZBUIFBYHVSAEM/action/replication_record"}},"created_at":"2026-07-05T11:07:33.872763+00:00","updated_at":"2026-07-05T11:07:33.872763+00:00"}