{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IAV6G2YDH3T4EJ7CEVYSCSLATN","short_pith_number":"pith:IAV6G2YD","schema_version":"1.0","canonical_sha256":"402be36b033ee7c227e225712149609b698ef952a4197737bf52a4ac25f5ad17","source":{"kind":"arxiv","id":"2605.18359","version":1},"attestation_state":"computed","paper":{"title":"RAVE: Re-Allocating Visual Attention in Large Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zhang, Guanjun Jiang, Xiaoying Tang, Xi Leng, Xinhong Ma, Yang Yang, Ziqiang Dong","submitted_at":"2026-05-18T13:12:50Z","abstract_excerpt":"Large multimodal models (LMMs) inherit the self-attention mechanism of pretrained language backbones, yet standard attention can exhibit suboptimal allocation, including cross-modal misallocation between textual and visual evidence and intra-visual imbalance among visual tokens. We propose RAVE (Re-Allocating Visual Attention), a lightweight pair-gating mechanism that adds a learned query--key bias to pre-softmax attention scores over visual keys, derived from pre-RoPE query and key features. RAVE requires no architectural modification to the backbone and can be trained end-to-end with the res"},"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":"2605.18359","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-18T13:12:50Z","cross_cats_sorted":[],"title_canon_sha256":"972a85dd5697e2acd03050f1944f51aee8ff1e8520d301d995baee358cc6d247","abstract_canon_sha256":"395011c5e02147d5d375607c403201e2822f812aa96bc103a0f17e9a20166450"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:56.984850Z","signature_b64":"1lf2z713ckTfG1pP2NmMceGCKXWpMan5B/UdcuL0txGEU+TkNLHVpzrwTZ0/+Hu0+Cel2hT42ODK9F2+47M4Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"402be36b033ee7c227e225712149609b698ef952a4197737bf52a4ac25f5ad17","last_reissued_at":"2026-05-20T00:05:56.984077Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:56.984077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAVE: Re-Allocating Visual Attention in Large Multimodal Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zhang, Guanjun Jiang, Xiaoying Tang, Xi Leng, Xinhong Ma, Yang Yang, Ziqiang Dong","submitted_at":"2026-05-18T13:12:50Z","abstract_excerpt":"Large multimodal models (LMMs) inherit the self-attention mechanism of pretrained language backbones, yet standard attention can exhibit suboptimal allocation, including cross-modal misallocation between textual and visual evidence and intra-visual imbalance among visual tokens. We propose RAVE (Re-Allocating Visual Attention), a lightweight pair-gating mechanism that adds a learned query--key bias to pre-softmax attention scores over visual keys, derived from pre-RoPE query and key features. RAVE requires no architectural modification to the backbone and can be trained end-to-end with the res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18359","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/2605.18359/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:30.714805Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"external_links","ran_at":"2026-05-19T23:31:52.366466Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T23:21:58.795121Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"04e48ff8d77638bb98e8574f93c6245d41fbd8931889ace5f3f3167df82d2869"},"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":"2605.18359","created_at":"2026-05-20T00:05:56.984223+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18359v1","created_at":"2026-05-20T00:05:56.984223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18359","created_at":"2026-05-20T00:05:56.984223+00:00"},{"alias_kind":"pith_short_12","alias_value":"IAV6G2YDH3T4","created_at":"2026-05-20T00:05:56.984223+00:00"},{"alias_kind":"pith_short_16","alias_value":"IAV6G2YDH3T4EJ7C","created_at":"2026-05-20T00:05:56.984223+00:00"},{"alias_kind":"pith_short_8","alias_value":"IAV6G2YD","created_at":"2026-05-20T00:05:56.984223+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/IAV6G2YDH3T4EJ7CEVYSCSLATN","json":"https://pith.science/pith/IAV6G2YDH3T4EJ7CEVYSCSLATN.json","graph_json":"https://pith.science/api/pith-number/IAV6G2YDH3T4EJ7CEVYSCSLATN/graph.json","events_json":"https://pith.science/api/pith-number/IAV6G2YDH3T4EJ7CEVYSCSLATN/events.json","paper":"https://pith.science/paper/IAV6G2YD"},"agent_actions":{"view_html":"https://pith.science/pith/IAV6G2YDH3T4EJ7CEVYSCSLATN","download_json":"https://pith.science/pith/IAV6G2YDH3T4EJ7CEVYSCSLATN.json","view_paper":"https://pith.science/paper/IAV6G2YD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18359&json=true","fetch_graph":"https://pith.science/api/pith-number/IAV6G2YDH3T4EJ7CEVYSCSLATN/graph.json","fetch_events":"https://pith.science/api/pith-number/IAV6G2YDH3T4EJ7CEVYSCSLATN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IAV6G2YDH3T4EJ7CEVYSCSLATN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IAV6G2YDH3T4EJ7CEVYSCSLATN/action/storage_attestation","attest_author":"https://pith.science/pith/IAV6G2YDH3T4EJ7CEVYSCSLATN/action/author_attestation","sign_citation":"https://pith.science/pith/IAV6G2YDH3T4EJ7CEVYSCSLATN/action/citation_signature","submit_replication":"https://pith.science/pith/IAV6G2YDH3T4EJ7CEVYSCSLATN/action/replication_record"}},"created_at":"2026-05-20T00:05:56.984223+00:00","updated_at":"2026-05-20T00:05:56.984223+00:00"}