{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NGFGFV7DJYX62W2AE5S25VEDXO","short_pith_number":"pith:NGFGFV7D","schema_version":"1.0","canonical_sha256":"698a62d7e34e2fed5b402765aed483bbaacfed88aefed48b73253347d8428f81","source":{"kind":"arxiv","id":"2606.02161","version":1},"attestation_state":"computed","paper":{"title":"InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Lei Xie, Sanglu Lu, Shiwei Gan, Xiao Liu, Xinxin Liu, Yafeng Yin","submitted_at":"2026-06-01T12:24:24Z","abstract_excerpt":"Video Large Language Models (Video-LLMs) achieve strong performance in video understanding, but their excessive visual tokens bring substantial computational overhead. Existing training-free compression methods improve inference efficiency by reducing visual tokens, yet they often rely on local adjacent-frame similarity for temporal redundancy estimation or allocate token budgets mainly according to segment length. Such designs are sensitive to frame-level noise and fail to capture the non-uniform information distribution of real-world videos. To address these challenges, we propose InfoMerge,"},"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":"2606.02161","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T12:24:24Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a32e63430bc92f023ac7037872d06cba42a7282c05e5e2dff325b3920347374c","abstract_canon_sha256":"24b964178d275a86a1f0cddf134759edb43ea40bdc716f5241c2b7af07ebf4f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:05:08.149227Z","signature_b64":"wp7d5lWnJeTAIG/OWnYEjdRwfvdOXAkmGHF/f7suCaZof1Dm+kExt/L++4zY3aDWyT8vFQMMeDeIFgZpSxwTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"698a62d7e34e2fed5b402765aed483bbaacfed88aefed48b73253347d8428f81","last_reissued_at":"2026-06-02T02:05:08.148824Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:05:08.148824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InfoMerge: Information-aware Token Compression for Efficient Video Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Lei Xie, Sanglu Lu, Shiwei Gan, Xiao Liu, Xinxin Liu, Yafeng Yin","submitted_at":"2026-06-01T12:24:24Z","abstract_excerpt":"Video Large Language Models (Video-LLMs) achieve strong performance in video understanding, but their excessive visual tokens bring substantial computational overhead. Existing training-free compression methods improve inference efficiency by reducing visual tokens, yet they often rely on local adjacent-frame similarity for temporal redundancy estimation or allocate token budgets mainly according to segment length. Such designs are sensitive to frame-level noise and fail to capture the non-uniform information distribution of real-world videos. To address these challenges, we propose InfoMerge,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02161","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/2606.02161/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":"2606.02161","created_at":"2026-06-02T02:05:08.148881+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02161v1","created_at":"2026-06-02T02:05:08.148881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02161","created_at":"2026-06-02T02:05:08.148881+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGFGFV7DJYX6","created_at":"2026-06-02T02:05:08.148881+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGFGFV7DJYX62W2A","created_at":"2026-06-02T02:05:08.148881+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGFGFV7D","created_at":"2026-06-02T02:05:08.148881+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/NGFGFV7DJYX62W2AE5S25VEDXO","json":"https://pith.science/pith/NGFGFV7DJYX62W2AE5S25VEDXO.json","graph_json":"https://pith.science/api/pith-number/NGFGFV7DJYX62W2AE5S25VEDXO/graph.json","events_json":"https://pith.science/api/pith-number/NGFGFV7DJYX62W2AE5S25VEDXO/events.json","paper":"https://pith.science/paper/NGFGFV7D"},"agent_actions":{"view_html":"https://pith.science/pith/NGFGFV7DJYX62W2AE5S25VEDXO","download_json":"https://pith.science/pith/NGFGFV7DJYX62W2AE5S25VEDXO.json","view_paper":"https://pith.science/paper/NGFGFV7D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02161&json=true","fetch_graph":"https://pith.science/api/pith-number/NGFGFV7DJYX62W2AE5S25VEDXO/graph.json","fetch_events":"https://pith.science/api/pith-number/NGFGFV7DJYX62W2AE5S25VEDXO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGFGFV7DJYX62W2AE5S25VEDXO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGFGFV7DJYX62W2AE5S25VEDXO/action/storage_attestation","attest_author":"https://pith.science/pith/NGFGFV7DJYX62W2AE5S25VEDXO/action/author_attestation","sign_citation":"https://pith.science/pith/NGFGFV7DJYX62W2AE5S25VEDXO/action/citation_signature","submit_replication":"https://pith.science/pith/NGFGFV7DJYX62W2AE5S25VEDXO/action/replication_record"}},"created_at":"2026-06-02T02:05:08.148881+00:00","updated_at":"2026-06-02T02:05:08.148881+00:00"}