{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:227FCLNVM3HISWDDJUCIAS2YAB","short_pith_number":"pith:227FCLNV","schema_version":"1.0","canonical_sha256":"d6be512db566ce8958634d04804b58005abb22d13d5b631eb5f6e53e2650666e","source":{"kind":"arxiv","id":"2312.16240","version":1},"attestation_state":"computed","paper":{"title":"Merging Vision Transformers from Different Tasks and Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenyu Huang, Mingzhu Shen, Peng Ye, Tao Chen, Wanli Ouyang, Yongqi Huang, Yuning Zhang","submitted_at":"2023-12-25T09:32:28Z","abstract_excerpt":"This work targets to merge various Vision Transformers (ViTs) trained on different tasks (i.e., datasets with different object categories) or domains (i.e., datasets with the same categories but different environments) into one unified model, yielding still good performance on each task or domain. Previous model merging works focus on either CNNs or NLP models, leaving the ViTs merging research untouched. To fill this gap, we first explore and find that existing model merging methods cannot well handle the merging of the whole ViT models and still have improvement space. To enable the merging "},"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":"2312.16240","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-25T09:32:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"434b197a1315ce90ce7aaf256250e46041ed76f3a0da96f907e5bdaeac7d40ed","abstract_canon_sha256":"ca695180782789bce4c84c4aa5b40c8432923680dd9358af0d666a2d53350b76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:14.900065Z","signature_b64":"v8djF3rCOsgR1uSHcBQuagSA4w2KAMUw/KCVEgS+lvFTqwfpgjV3bbBUw7WkCMDNhnMgelE56r0fsIulwX9UAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6be512db566ce8958634d04804b58005abb22d13d5b631eb5f6e53e2650666e","last_reissued_at":"2026-07-05T07:28:14.899678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:14.899678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Merging Vision Transformers from Different Tasks and Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenyu Huang, Mingzhu Shen, Peng Ye, Tao Chen, Wanli Ouyang, Yongqi Huang, Yuning Zhang","submitted_at":"2023-12-25T09:32:28Z","abstract_excerpt":"This work targets to merge various Vision Transformers (ViTs) trained on different tasks (i.e., datasets with different object categories) or domains (i.e., datasets with the same categories but different environments) into one unified model, yielding still good performance on each task or domain. Previous model merging works focus on either CNNs or NLP models, leaving the ViTs merging research untouched. To fill this gap, we first explore and find that existing model merging methods cannot well handle the merging of the whole ViT models and still have improvement space. To enable the merging "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.16240","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/2312.16240/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":"2312.16240","created_at":"2026-07-05T07:28:14.899733+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.16240v1","created_at":"2026-07-05T07:28:14.899733+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.16240","created_at":"2026-07-05T07:28:14.899733+00:00"},{"alias_kind":"pith_short_12","alias_value":"227FCLNVM3HI","created_at":"2026-07-05T07:28:14.899733+00:00"},{"alias_kind":"pith_short_16","alias_value":"227FCLNVM3HISWDD","created_at":"2026-07-05T07:28:14.899733+00:00"},{"alias_kind":"pith_short_8","alias_value":"227FCLNV","created_at":"2026-07-05T07:28:14.899733+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.07666","citing_title":"Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities","ref_index":276,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/227FCLNVM3HISWDDJUCIAS2YAB","json":"https://pith.science/pith/227FCLNVM3HISWDDJUCIAS2YAB.json","graph_json":"https://pith.science/api/pith-number/227FCLNVM3HISWDDJUCIAS2YAB/graph.json","events_json":"https://pith.science/api/pith-number/227FCLNVM3HISWDDJUCIAS2YAB/events.json","paper":"https://pith.science/paper/227FCLNV"},"agent_actions":{"view_html":"https://pith.science/pith/227FCLNVM3HISWDDJUCIAS2YAB","download_json":"https://pith.science/pith/227FCLNVM3HISWDDJUCIAS2YAB.json","view_paper":"https://pith.science/paper/227FCLNV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.16240&json=true","fetch_graph":"https://pith.science/api/pith-number/227FCLNVM3HISWDDJUCIAS2YAB/graph.json","fetch_events":"https://pith.science/api/pith-number/227FCLNVM3HISWDDJUCIAS2YAB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/227FCLNVM3HISWDDJUCIAS2YAB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/227FCLNVM3HISWDDJUCIAS2YAB/action/storage_attestation","attest_author":"https://pith.science/pith/227FCLNVM3HISWDDJUCIAS2YAB/action/author_attestation","sign_citation":"https://pith.science/pith/227FCLNVM3HISWDDJUCIAS2YAB/action/citation_signature","submit_replication":"https://pith.science/pith/227FCLNVM3HISWDDJUCIAS2YAB/action/replication_record"}},"created_at":"2026-07-05T07:28:14.899733+00:00","updated_at":"2026-07-05T07:28:14.899733+00:00"}