{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TCGNBFMLN6LIVENMOEIZNNPCTJ","short_pith_number":"pith:TCGNBFML","schema_version":"1.0","canonical_sha256":"988cd0958b6f968a91ac711196b5e29a43a9ae00254cd0e2fecde16d64db6be2","source":{"kind":"arxiv","id":"2407.11717","version":1},"attestation_state":"computed","paper":{"title":"Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zheng, Chen Ju, Haicheng Wang, Haozhe Cheng, Jinsong Lan, Shuai Xiao, Weilin Huang, Xu Chen, Zhonghua Zhai","submitted_at":"2024-07-16T13:35:26Z","abstract_excerpt":"Vision-Language Large Models (VLMs) recently become primary backbone of AI, due to the impressive performance. However, their expensive computation costs, i.e., throughput and delay, impede potentials in the real-world scenarios. To achieve acceleration for VLMs, most existing methods focus on the model perspective: pruning, distillation, quantization, but completely overlook the data-perspective redundancy. To fill the overlook, this paper pioneers the severity of data redundancy, and designs one plug-and-play Turbo module guided by information degree to prune inefficient tokens from visual o"},"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":"2407.11717","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-16T13:35:26Z","cross_cats_sorted":[],"title_canon_sha256":"dbfeb224d92ea737f39603636a8162f06636a2314a58439d124ab7d5f6633c7d","abstract_canon_sha256":"f3464bf20c22735ee093648f531e9e8c2fd7685aaa3b92b2d2fbca175f1131b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:39.887551Z","signature_b64":"358XUdDZ/MZyj3VzWIkyLfJxYBftEiB391oWz1vi4JIMW/aogl0Bh7NC6uRyse5iJaRLQT5AXH1foF8CLlFRDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"988cd0958b6f968a91ac711196b5e29a43a9ae00254cd0e2fecde16d64db6be2","last_reissued_at":"2026-07-05T08:44:39.887024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:39.887024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Zheng, Chen Ju, Haicheng Wang, Haozhe Cheng, Jinsong Lan, Shuai Xiao, Weilin Huang, Xu Chen, Zhonghua Zhai","submitted_at":"2024-07-16T13:35:26Z","abstract_excerpt":"Vision-Language Large Models (VLMs) recently become primary backbone of AI, due to the impressive performance. However, their expensive computation costs, i.e., throughput and delay, impede potentials in the real-world scenarios. To achieve acceleration for VLMs, most existing methods focus on the model perspective: pruning, distillation, quantization, but completely overlook the data-perspective redundancy. To fill the overlook, this paper pioneers the severity of data redundancy, and designs one plug-and-play Turbo module guided by information degree to prune inefficient tokens from visual o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11717","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/2407.11717/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":"2407.11717","created_at":"2026-07-05T08:44:39.887082+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11717v1","created_at":"2026-07-05T08:44:39.887082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11717","created_at":"2026-07-05T08:44:39.887082+00:00"},{"alias_kind":"pith_short_12","alias_value":"TCGNBFMLN6LI","created_at":"2026-07-05T08:44:39.887082+00:00"},{"alias_kind":"pith_short_16","alias_value":"TCGNBFMLN6LIVENM","created_at":"2026-07-05T08:44:39.887082+00:00"},{"alias_kind":"pith_short_8","alias_value":"TCGNBFML","created_at":"2026-07-05T08:44:39.887082+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/TCGNBFMLN6LIVENMOEIZNNPCTJ","json":"https://pith.science/pith/TCGNBFMLN6LIVENMOEIZNNPCTJ.json","graph_json":"https://pith.science/api/pith-number/TCGNBFMLN6LIVENMOEIZNNPCTJ/graph.json","events_json":"https://pith.science/api/pith-number/TCGNBFMLN6LIVENMOEIZNNPCTJ/events.json","paper":"https://pith.science/paper/TCGNBFML"},"agent_actions":{"view_html":"https://pith.science/pith/TCGNBFMLN6LIVENMOEIZNNPCTJ","download_json":"https://pith.science/pith/TCGNBFMLN6LIVENMOEIZNNPCTJ.json","view_paper":"https://pith.science/paper/TCGNBFML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11717&json=true","fetch_graph":"https://pith.science/api/pith-number/TCGNBFMLN6LIVENMOEIZNNPCTJ/graph.json","fetch_events":"https://pith.science/api/pith-number/TCGNBFMLN6LIVENMOEIZNNPCTJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TCGNBFMLN6LIVENMOEIZNNPCTJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TCGNBFMLN6LIVENMOEIZNNPCTJ/action/storage_attestation","attest_author":"https://pith.science/pith/TCGNBFMLN6LIVENMOEIZNNPCTJ/action/author_attestation","sign_citation":"https://pith.science/pith/TCGNBFMLN6LIVENMOEIZNNPCTJ/action/citation_signature","submit_replication":"https://pith.science/pith/TCGNBFMLN6LIVENMOEIZNNPCTJ/action/replication_record"}},"created_at":"2026-07-05T08:44:39.887082+00:00","updated_at":"2026-07-05T08:44:39.887082+00:00"}