{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DKEMUPZYWALML2IGBTQLHIRNFE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6861b26a531462cc33ff579448735f21f98ffd10b088e1564fe78663a9dcd0cf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-17T10:22:29Z","title_canon_sha256":"12acc562f2d745dbb846a14570b8e6d03dacdcd5773af0be4d88babd362a59c7"},"schema_version":"1.0","source":{"id":"2505.11945","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11945","created_at":"2026-07-05T11:07:24Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11945v2","created_at":"2026-07-05T11:07:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11945","created_at":"2026-07-05T11:07:24Z"},{"alias_kind":"pith_short_12","alias_value":"DKEMUPZYWALM","created_at":"2026-07-05T11:07:24Z"},{"alias_kind":"pith_short_16","alias_value":"DKEMUPZYWALML2IG","created_at":"2026-07-05T11:07:24Z"},{"alias_kind":"pith_short_8","alias_value":"DKEMUPZY","created_at":"2026-07-05T11:07:24Z"}],"graph_snapshots":[{"event_id":"sha256:9d368e706129954896bffc2053b84b49a34c348e019d30e73bd25ecff4befdd5","target":"graph","created_at":"2026-07-05T11:07:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.11945/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual instruction tuning aims to enable large language models to comprehend the visual world, with a pivotal challenge lying in establishing an effective vision-to-language projection. However, existing methods often grapple with the intractable trade-off between accuracy and efficiency. In this paper, we present LLaVA-Meteor, a novel approach designed to break this deadlock, equipped with a novel Top-Down Compression paradigm that strategically compresses visual tokens without compromising core information. Specifically, we construct a trainable Flash Global Fusion module based on efficient ","authors_text":"Bonan Li, Songhua Liu, Weihao Yu, Xinchao Wang, Zicheng Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-17T10:22:29Z","title":"Top-Down Compression: Revisit Efficient Vision Token Projection for Visual Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11945","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1cb63d89e727a8f860d8249d5e9c25fc05ea1a4eefd7c4c415a43786c3d54ba8","target":"record","created_at":"2026-07-05T11:07:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6861b26a531462cc33ff579448735f21f98ffd10b088e1564fe78663a9dcd0cf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-17T10:22:29Z","title_canon_sha256":"12acc562f2d745dbb846a14570b8e6d03dacdcd5773af0be4d88babd362a59c7"},"schema_version":"1.0","source":{"id":"2505.11945","kind":"arxiv","version":2}},"canonical_sha256":"1a88ca3f38b016c5e9060ce0b3a22d292b00fc438a2040120f2ec7cfadb495a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a88ca3f38b016c5e9060ce0b3a22d292b00fc438a2040120f2ec7cfadb495a8","first_computed_at":"2026-07-05T11:07:24.770230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:24.770230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vTGqQg4b1M+42QKudELruGUZTY223WnznL1AOuXLi3Aoxlsuxa7m/BODyHiMoKrflc2al4b7lRbUH0rWVvBmAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:24.770731Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11945","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cb63d89e727a8f860d8249d5e9c25fc05ea1a4eefd7c4c415a43786c3d54ba8","sha256:9d368e706129954896bffc2053b84b49a34c348e019d30e73bd25ecff4befdd5"],"state_sha256":"a07aae358cbd3e64188c2f6fbf92c28a18db2abbd70affcaf459fdbafdeba8ca"}