{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HXHSEMVRTM6S57EBUNLSY222L7","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":"9d3c9c0425d0d1be97de821c29782d31974c217cd2ad1d65390a6f33f8bd592a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T14:35:32Z","title_canon_sha256":"bd55663b2cc6ca72bfc21c8d8f810908610655392a1be0a7220bd48692b47fac"},"schema_version":"1.0","source":{"id":"2403.06764","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.06764","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"arxiv_version","alias_value":"2403.06764v3","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.06764","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"pith_short_12","alias_value":"HXHSEMVRTM6S","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"pith_short_16","alias_value":"HXHSEMVRTM6S57EB","created_at":"2026-07-05T09:01:30Z"},{"alias_kind":"pith_short_8","alias_value":"HXHSEMVR","created_at":"2026-07-05T09:01:30Z"}],"graph_snapshots":[{"event_id":"sha256:0cdee14a2a7f45b8c3a57e8bfa26f35c575a4e81cb83093c7cad3278add56537","target":"graph","created_at":"2026-07-05T09:01:30Z","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/2403.06764/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we identify the inefficient attention phenomena in Large Vision-Language Models (LVLMs), notably within prominent models like LLaVA-1.5, QwenVL-Chat and Video-LLaVA. We find out that the attention computation over visual tokens is of extreme inefficiency in the deep layers of popular LVLMs, suggesting a need for a sparser approach compared to textual data handling. To this end, we introduce FastV, a versatile plug-and-play method designed to optimize computational efficiency by learning adaptive attention patterns in early layers and pruning visual tokens in subsequent ones. Our","authors_text":"Baobao Chang, Chang Zhou, Haozhe Zhao, Junyang Lin, Liang Chen, Shuai Bai, Tianyu Liu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T14:35:32Z","title":"An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.06764","kind":"arxiv","version":3},"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":"sha256:90f369047ee50b1edd3325238fff2f7227c75689a1b05b9da3c5c2f287d09d8f","target":"record","created_at":"2026-07-05T09:01:30Z","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":"9d3c9c0425d0d1be97de821c29782d31974c217cd2ad1d65390a6f33f8bd592a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-11T14:35:32Z","title_canon_sha256":"bd55663b2cc6ca72bfc21c8d8f810908610655392a1be0a7220bd48692b47fac"},"schema_version":"1.0","source":{"id":"2403.06764","kind":"arxiv","version":3}},"canonical_sha256":"3dcf2232b19b3d2efc81a3572c6b5a5fd1446d2f321232ca24b5f0929c1e78ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3dcf2232b19b3d2efc81a3572c6b5a5fd1446d2f321232ca24b5f0929c1e78ca","first_computed_at":"2026-07-05T09:01:30.928892Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:01:30.928892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HdQQpXMRA4AS2hjhfwhxl4C91CGffM4u8lyZiq+0Zjhddf+ggEa2ZyXW3Z9CgEb9U2fNtF9ZMzZ35RM0G+DYCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:01:30.929409Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.06764","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90f369047ee50b1edd3325238fff2f7227c75689a1b05b9da3c5c2f287d09d8f","sha256:0cdee14a2a7f45b8c3a57e8bfa26f35c575a4e81cb83093c7cad3278add56537"],"state_sha256":"d7dba9ec1b530e1f32db4e5172e289810376d29b577e700b470576f60d488655"}