{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OQZUVMBWKUWCNEY2SH7PBVWQJV","short_pith_number":"pith:OQZUVMBW","schema_version":"1.0","canonical_sha256":"74334ab036552c26931a91fef0d6d04d451fb556433ceab9f272d374ab9a7410","source":{"kind":"arxiv","id":"2505.19235","version":1},"attestation_state":"computed","paper":{"title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Hancheng Ye, Jianyi Zhang, Martin Kuo, Mingyuan Ma, Ming-Yu Chung, Qinsi Wang, Yiran Chen, Yudong Liu, Yueqian Lin","submitted_at":"2025-05-25T17:16:34Z","abstract_excerpt":"Vision-Language Models (VLMs) excel across diverse tasks but suffer from high inference costs in time and memory. Token sparsity mitigates inefficiencies in token usage, while neuron sparsity reduces high-dimensional computations, both offering promising solutions to enhance efficiency. Recently, these two sparsity paradigms have evolved largely in parallel, fostering the prevailing assumption that they function independently. However, a fundamental yet underexplored question remains: Do they truly operate in isolation, or is there a deeper underlying interplay that has yet to be uncovered? In"},"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":"2505.19235","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-25T17:16:34Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"42411a48c9d5450b5ce2372e50f251f12ce1147d01ee4889ae2e97e8eaa1e1bc","abstract_canon_sha256":"6154e3dbc593be2bc5a7ac03a5c70c2e1b64fe7dc0a98e528653966e88147c2d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:26.933868Z","signature_b64":"siPdI5f4xyYY2e6iZ8OYJyxy9t/XFnCtNWjCi/oZWXCEMntOgFZ8bEiHqfMixIePk2iSjtXJEPk3V4BCAIAHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74334ab036552c26931a91fef0d6d04d451fb556433ceab9f272d374ab9a7410","last_reissued_at":"2026-07-05T11:09:26.933366Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:26.933366Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Hancheng Ye, Jianyi Zhang, Martin Kuo, Mingyuan Ma, Ming-Yu Chung, Qinsi Wang, Yiran Chen, Yudong Liu, Yueqian Lin","submitted_at":"2025-05-25T17:16:34Z","abstract_excerpt":"Vision-Language Models (VLMs) excel across diverse tasks but suffer from high inference costs in time and memory. Token sparsity mitigates inefficiencies in token usage, while neuron sparsity reduces high-dimensional computations, both offering promising solutions to enhance efficiency. Recently, these two sparsity paradigms have evolved largely in parallel, fostering the prevailing assumption that they function independently. However, a fundamental yet underexplored question remains: Do they truly operate in isolation, or is there a deeper underlying interplay that has yet to be uncovered? In"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19235","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/2505.19235/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":"2505.19235","created_at":"2026-07-05T11:09:26.933427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19235v1","created_at":"2026-07-05T11:09:26.933427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19235","created_at":"2026-07-05T11:09:26.933427+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQZUVMBWKUWC","created_at":"2026-07-05T11:09:26.933427+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQZUVMBWKUWCNEY2","created_at":"2026-07-05T11:09:26.933427+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQZUVMBW","created_at":"2026-07-05T11:09:26.933427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24165","citing_title":"Spectral Evolution-Guided Token Pruning in Multimodal Large Language Models","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24156","citing_title":"Accelerating Multimodal Large Language Models with Prior-Corrected Token Reduction","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQZUVMBWKUWCNEY2SH7PBVWQJV","json":"https://pith.science/pith/OQZUVMBWKUWCNEY2SH7PBVWQJV.json","graph_json":"https://pith.science/api/pith-number/OQZUVMBWKUWCNEY2SH7PBVWQJV/graph.json","events_json":"https://pith.science/api/pith-number/OQZUVMBWKUWCNEY2SH7PBVWQJV/events.json","paper":"https://pith.science/paper/OQZUVMBW"},"agent_actions":{"view_html":"https://pith.science/pith/OQZUVMBWKUWCNEY2SH7PBVWQJV","download_json":"https://pith.science/pith/OQZUVMBWKUWCNEY2SH7PBVWQJV.json","view_paper":"https://pith.science/paper/OQZUVMBW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19235&json=true","fetch_graph":"https://pith.science/api/pith-number/OQZUVMBWKUWCNEY2SH7PBVWQJV/graph.json","fetch_events":"https://pith.science/api/pith-number/OQZUVMBWKUWCNEY2SH7PBVWQJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQZUVMBWKUWCNEY2SH7PBVWQJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQZUVMBWKUWCNEY2SH7PBVWQJV/action/storage_attestation","attest_author":"https://pith.science/pith/OQZUVMBWKUWCNEY2SH7PBVWQJV/action/author_attestation","sign_citation":"https://pith.science/pith/OQZUVMBWKUWCNEY2SH7PBVWQJV/action/citation_signature","submit_replication":"https://pith.science/pith/OQZUVMBWKUWCNEY2SH7PBVWQJV/action/replication_record"}},"created_at":"2026-07-05T11:09:26.933427+00:00","updated_at":"2026-07-05T11:09:26.933427+00:00"}