{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VNFUHXCLJAPFGIGBHHUNERJ47Y","short_pith_number":"pith:VNFUHXCL","schema_version":"1.0","canonical_sha256":"ab4b43dc4b481e5320c139e8d2453cfe073be42803dbf4c2e4b9c684cad8d1ea","source":{"kind":"arxiv","id":"2605.14877","version":1},"attestation_state":"computed","paper":{"title":"HeatKV: Head-tuned KV-cache Compression for Visual Autoregressive Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Head-specific attention ranking doubles KV-cache compression in visual autoregressive image models while preserving quality.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Axel Berg, Chuteng Zhou, Durmus Alp Emre Acar, Jonathan Cederlund, Pontus Giselsson","submitted_at":"2026-05-14T14:22:34Z","abstract_excerpt":"Visual Autoregressive (VAR) models have recently demonstrated impressive image generation quality while maintaining low latency. However, they suffer from severe KV-cache memory constraints, often requiring gigabytes of memory per generated image. We introduce HeatKV, a novel compression method that adapts cache allocation in each head based on its attention to previously generated scales. Using a small offline calibration set, the attention heads are ranked according to their attention scores over prior scales. Based on this ranking, we construct a static pruning schedule tailored to a given "},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.14877","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T14:22:34Z","cross_cats_sorted":[],"title_canon_sha256":"4b56ae184d7afff6d28f203935951a47bae3d761028d3320a9f5096242185147","abstract_canon_sha256":"1ef38dabdc5d4752e11d311d9445b475b24b4c6ac345155aa2f530c37a22414c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:56.082506Z","signature_b64":"TjdIM4m7hPbQc41BQbHDJSuvBKztPZI0N3Kd9c+JjqNkQIaySmoSj/pzlYnmKWjIvsbIj2D4a52TLGdbIZq0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab4b43dc4b481e5320c139e8d2453cfe073be42803dbf4c2e4b9c684cad8d1ea","last_reissued_at":"2026-05-17T23:38:56.081842Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:56.081842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HeatKV: Head-tuned KV-cache Compression for Visual Autoregressive Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Head-specific attention ranking doubles KV-cache compression in visual autoregressive image models while preserving quality.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Axel Berg, Chuteng Zhou, Durmus Alp Emre Acar, Jonathan Cederlund, Pontus Giselsson","submitted_at":"2026-05-14T14:22:34Z","abstract_excerpt":"Visual Autoregressive (VAR) models have recently demonstrated impressive image generation quality while maintaining low latency. However, they suffer from severe KV-cache memory constraints, often requiring gigabytes of memory per generated image. We introduce HeatKV, a novel compression method that adapts cache allocation in each head based on its attention to previously generated scales. Using a small offline calibration set, the attention heads are ranked according to their attention scores over prior scales. Based on this ranking, we construct a static pruning schedule tailored to a given "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Applied to the Infinity-2B model, HeatKV achieves 2× higher compression ratio in memory allocation for KV cache compared to existing methods, while maintaining similar or better image fidelity, prompt alignment and human perception score.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a static pruning schedule derived from attention scores on a small offline calibration set will generalize to arbitrary prompts and generation lengths without measurable quality loss.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"HeatKV ranks attention heads by their focus on prior scales using offline calibration data and applies a static per-head pruning schedule, delivering 2x higher KV-cache compression than prior methods on the Infinity-2B model with comparable image fidelity.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Head-specific attention ranking doubles KV-cache compression in visual autoregressive image models while preserving quality.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"65ba968a434d962722aa0603e36d76022c7c8a7be8960fab444d48979d528093"},"source":{"id":"2605.14877","kind":"arxiv","version":1},"verdict":{"id":"fb93b85d-6058-4875-89dc-c22b53b3a353","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T03:15:13.332676Z","strongest_claim":"Applied to the Infinity-2B model, HeatKV achieves 2× higher compression ratio in memory allocation for KV cache compared to existing methods, while maintaining similar or better image fidelity, prompt alignment and human perception score.","one_line_summary":"HeatKV ranks attention heads by their focus on prior scales using offline calibration data and applies a static per-head pruning schedule, delivering 2x higher KV-cache compression than prior methods on the Infinity-2B model with comparable image fidelity.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a static pruning schedule derived from attention scores on a small offline calibration set will generalize to arbitrary prompts and generation lengths without measurable quality loss.","pith_extraction_headline":"Head-specific attention ranking doubles KV-cache compression in visual autoregressive image models while preserving quality."},"references":{"count":40,"sample":[{"doi":"","year":2025,"title":"Infinity: Scaling bitwise autoregressive modeling for high-resolution image synthesis,","work_id":"977492f9-1add-4df5-aa71-c2e7f1a694b6","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y . Bengio, “Generative adversarial nets,”Advances in neural information processing systems, vol. 27, ","work_id":"4b8320ae-4a24-4686-85ca-93e608f3af08","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"A style-based generator architecture for generative adversarial networks,","work_id":"db3bde24-03b8-4609-98c5-e9672550b362","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Stylegan-xl: Scaling stylegan to large diverse datasets,","work_id":"f5a2bd2d-af70-447d-a377-f8717494b10f","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Diffusion models beat gans on image synthesis,","work_id":"35493ec7-8582-4e9b-a3dc-d835aca70a28","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":40,"snapshot_sha256":"bb5685a19cb18a9b4eee104188b34d8e9606abdd26d8b09aefd67fe8dfe4d354","internal_anchors":2},"formal_canon":{"evidence_count":2,"snapshot_sha256":"63aeb8692867d4ce5341a164139d63f584be7c504aea060e9cd9ca6f67647c72"},"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":"2605.14877","created_at":"2026-05-17T23:38:56.081952+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14877v1","created_at":"2026-05-17T23:38:56.081952+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14877","created_at":"2026-05-17T23:38:56.081952+00:00"},{"alias_kind":"pith_short_12","alias_value":"VNFUHXCLJAPF","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"VNFUHXCLJAPFGIGB","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"VNFUHXCL","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VNFUHXCLJAPFGIGBHHUNERJ47Y","json":"https://pith.science/pith/VNFUHXCLJAPFGIGBHHUNERJ47Y.json","graph_json":"https://pith.science/api/pith-number/VNFUHXCLJAPFGIGBHHUNERJ47Y/graph.json","events_json":"https://pith.science/api/pith-number/VNFUHXCLJAPFGIGBHHUNERJ47Y/events.json","paper":"https://pith.science/paper/VNFUHXCL"},"agent_actions":{"view_html":"https://pith.science/pith/VNFUHXCLJAPFGIGBHHUNERJ47Y","download_json":"https://pith.science/pith/VNFUHXCLJAPFGIGBHHUNERJ47Y.json","view_paper":"https://pith.science/paper/VNFUHXCL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14877&json=true","fetch_graph":"https://pith.science/api/pith-number/VNFUHXCLJAPFGIGBHHUNERJ47Y/graph.json","fetch_events":"https://pith.science/api/pith-number/VNFUHXCLJAPFGIGBHHUNERJ47Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VNFUHXCLJAPFGIGBHHUNERJ47Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VNFUHXCLJAPFGIGBHHUNERJ47Y/action/storage_attestation","attest_author":"https://pith.science/pith/VNFUHXCLJAPFGIGBHHUNERJ47Y/action/author_attestation","sign_citation":"https://pith.science/pith/VNFUHXCLJAPFGIGBHHUNERJ47Y/action/citation_signature","submit_replication":"https://pith.science/pith/VNFUHXCLJAPFGIGBHHUNERJ47Y/action/replication_record"}},"created_at":"2026-05-17T23:38:56.081952+00:00","updated_at":"2026-05-17T23:38:56.081952+00:00"}