{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XULYDNKJNAPSHBPRYVYLU6TIQY","short_pith_number":"pith:XULYDNKJ","schema_version":"1.0","canonical_sha256":"bd1781b549681f2385f1c570ba7a68863e899fa6ea94a9309c2b1484db630c25","source":{"kind":"arxiv","id":"2411.18995","version":1},"attestation_state":"computed","paper":{"title":"MVFormer: Diversifying Feature Normalization and Token Mixing for Efficient Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ha Young Kim, Jongseong Bae, Minsu Cho, Susang Kim","submitted_at":"2024-11-28T08:49:11Z","abstract_excerpt":"Active research is currently underway to enhance the efficiency of vision transformers (ViTs). Most studies have focused solely on effective token mixers, overlooking the potential relationship with normalization. To boost diverse feature learning, we propose two components: a normalization module called multi-view normalization (MVN) and a token mixer called multi-view token mixer (MVTM). The MVN integrates three differently normalized features via batch, layer, and instance normalization using a learnable weighted sum. Each normalization method outputs a different distribution, generating di"},"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":"2411.18995","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-28T08:49:11Z","cross_cats_sorted":[],"title_canon_sha256":"83a572652935488a181b61dd96c2a5ffb465b09d0125d7b0e8f6b10342418ea0","abstract_canon_sha256":"bbc7c734bb19784d1d1a31565c4c665f33da8eee250f1b3c99014eb2748bbc19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:55.577439Z","signature_b64":"wBHJakd2ugcE99H2KmpJElGws3iEbWdCjSYOgjlhnOlTuoNujVBqm0XCI1ftb6ydM4c5+y+BPU5QZgVdR9B7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd1781b549681f2385f1c570ba7a68863e899fa6ea94a9309c2b1484db630c25","last_reissued_at":"2026-07-05T09:41:55.576922Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:55.576922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MVFormer: Diversifying Feature Normalization and Token Mixing for Efficient Vision Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ha Young Kim, Jongseong Bae, Minsu Cho, Susang Kim","submitted_at":"2024-11-28T08:49:11Z","abstract_excerpt":"Active research is currently underway to enhance the efficiency of vision transformers (ViTs). Most studies have focused solely on effective token mixers, overlooking the potential relationship with normalization. To boost diverse feature learning, we propose two components: a normalization module called multi-view normalization (MVN) and a token mixer called multi-view token mixer (MVTM). The MVN integrates three differently normalized features via batch, layer, and instance normalization using a learnable weighted sum. Each normalization method outputs a different distribution, generating di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18995","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/2411.18995/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":"2411.18995","created_at":"2026-07-05T09:41:55.576983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18995v1","created_at":"2026-07-05T09:41:55.576983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18995","created_at":"2026-07-05T09:41:55.576983+00:00"},{"alias_kind":"pith_short_12","alias_value":"XULYDNKJNAPS","created_at":"2026-07-05T09:41:55.576983+00:00"},{"alias_kind":"pith_short_16","alias_value":"XULYDNKJNAPSHBPR","created_at":"2026-07-05T09:41:55.576983+00:00"},{"alias_kind":"pith_short_8","alias_value":"XULYDNKJ","created_at":"2026-07-05T09:41:55.576983+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/XULYDNKJNAPSHBPRYVYLU6TIQY","json":"https://pith.science/pith/XULYDNKJNAPSHBPRYVYLU6TIQY.json","graph_json":"https://pith.science/api/pith-number/XULYDNKJNAPSHBPRYVYLU6TIQY/graph.json","events_json":"https://pith.science/api/pith-number/XULYDNKJNAPSHBPRYVYLU6TIQY/events.json","paper":"https://pith.science/paper/XULYDNKJ"},"agent_actions":{"view_html":"https://pith.science/pith/XULYDNKJNAPSHBPRYVYLU6TIQY","download_json":"https://pith.science/pith/XULYDNKJNAPSHBPRYVYLU6TIQY.json","view_paper":"https://pith.science/paper/XULYDNKJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18995&json=true","fetch_graph":"https://pith.science/api/pith-number/XULYDNKJNAPSHBPRYVYLU6TIQY/graph.json","fetch_events":"https://pith.science/api/pith-number/XULYDNKJNAPSHBPRYVYLU6TIQY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XULYDNKJNAPSHBPRYVYLU6TIQY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XULYDNKJNAPSHBPRYVYLU6TIQY/action/storage_attestation","attest_author":"https://pith.science/pith/XULYDNKJNAPSHBPRYVYLU6TIQY/action/author_attestation","sign_citation":"https://pith.science/pith/XULYDNKJNAPSHBPRYVYLU6TIQY/action/citation_signature","submit_replication":"https://pith.science/pith/XULYDNKJNAPSHBPRYVYLU6TIQY/action/replication_record"}},"created_at":"2026-07-05T09:41:55.576983+00:00","updated_at":"2026-07-05T09:41:55.576983+00:00"}