{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PENECDHD36MV2AT4IECJJSOXZ3","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":"97b92615bccfbc075b49228e35e6161b0d0e4422990e703fda0b215f4f4b768e","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T11:24:23Z","title_canon_sha256":"369ecff8406ad1b805def7869ffd7a0e78537afe68d8a528b5ce1fbef90f084a"},"schema_version":"1.0","source":{"id":"2411.19628","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.19628","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"2411.19628v2","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19628","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"PENECDHD36MV","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"pith_short_16","alias_value":"PENECDHD36MV2AT4","created_at":"2026-07-05T11:43:08Z"},{"alias_kind":"pith_short_8","alias_value":"PENECDHD","created_at":"2026-07-05T11:43:08Z"}],"graph_snapshots":[{"event_id":"sha256:50f136fcd73ccc5c54e996a80900b4d50fb73d6bc9619ea262cf984d5394b249","target":"graph","created_at":"2026-07-05T11:43:08Z","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/2411.19628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The excessive use of visual tokens in existing Multimoal Large Language Models (MLLMs) often exhibits obvious redundancy and brings in prohibitively expensive computation. To gain insights into this problem, we first conduct extensive empirical studies on the attention behaviors of MLLMs, and summarize three main inference stages in MLLMs: (i) Early fusion between tokens is first accomplished quickly. (ii) Intra-modality modeling then comes to play. (iii) Multimodal reasoning} resumes and lasts until the end of inference. In particular, we reveal that visual tokens will stop contributing to re","authors_text":"Qiong Wu, Rongrong Ji, Weihao Ye, Wenhao Lin, Xiaoshuai Sun, Yiyi Zhou, Zhanpeng Zen","cross_cats":["cs.CL","cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T11:24:23Z","title":"Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19628","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:c3be70accc80cb9b675bd28e5a1f4ebf773bb9982ab62349fd76887f13c46d79","target":"record","created_at":"2026-07-05T11:43:08Z","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":"97b92615bccfbc075b49228e35e6161b0d0e4422990e703fda0b215f4f4b768e","cross_cats_sorted":["cs.CL","cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-29T11:24:23Z","title_canon_sha256":"369ecff8406ad1b805def7869ffd7a0e78537afe68d8a528b5ce1fbef90f084a"},"schema_version":"1.0","source":{"id":"2411.19628","kind":"arxiv","version":2}},"canonical_sha256":"791a410ce3df995d027c410494c9d7ced4ce7f16be2dc6d8c8327d63e23a90f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"791a410ce3df995d027c410494c9d7ced4ce7f16be2dc6d8c8327d63e23a90f3","first_computed_at":"2026-07-05T11:43:08.458826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:43:08.458826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N2KQQArN/UeFfL46crVaDNaF4UtcMk7/GvkgdIkiGvM0k3MmO66vlVp1BGC0rW7mUpqUAMuvn8JLXiyLJz7yCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:43:08.459257Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.19628","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c3be70accc80cb9b675bd28e5a1f4ebf773bb9982ab62349fd76887f13c46d79","sha256:50f136fcd73ccc5c54e996a80900b4d50fb73d6bc9619ea262cf984d5394b249"],"state_sha256":"abbb45d232c1fc4bdab58ebfb202c3cd516263e94db757439931fab24e105f79"}