{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QNCXYW4SENEMAFDG5QMTPAAXED","short_pith_number":"pith:QNCXYW4S","schema_version":"1.0","canonical_sha256":"83457c5b922348c01466ec1937801720c42653efe84dfde8543f01838283054b","source":{"kind":"arxiv","id":"2410.10356","version":2},"attestation_state":"computed","paper":{"title":"FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingfeng Yao, Wang Cheng, Wenyu Liu, Xinggang Wang","submitted_at":"2024-10-14T10:17:24Z","abstract_excerpt":"Diffusion Transformers (DiT) have attracted significant attention in research. However, they suffer from a slow convergence rate. In this paper, we aim to accelerate DiT training without any architectural modification. We identify the following issues in the training process: firstly, certain training strategies do not consistently perform well across different data. Secondly, the effectiveness of supervision at specific timesteps is limited. In response, we propose the following contributions: (1) We introduce a new perspective for interpreting the failure of the strategies. Specifically, we "},"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":"2410.10356","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T10:17:24Z","cross_cats_sorted":[],"title_canon_sha256":"d98f5e7d0554a857531befde0e535f1eda4fe32f8964253350aa61b6f0564f9c","abstract_canon_sha256":"b2810c61ffff178e4cdffe2293b0d68ec189fac08cf5b83768ee5403460efb00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:56.086125Z","signature_b64":"giGgmtCn+2idgBFBebbhU9bC4yGUqdxviJ0q8Ka2udClopQfqYtdusMQLkvhiSGLQGWc/bWQZIq0Sl9o3lurDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83457c5b922348c01466ec1937801720c42653efe84dfde8543f01838283054b","last_reissued_at":"2026-07-05T09:28:56.085622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:56.085622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jingfeng Yao, Wang Cheng, Wenyu Liu, Xinggang Wang","submitted_at":"2024-10-14T10:17:24Z","abstract_excerpt":"Diffusion Transformers (DiT) have attracted significant attention in research. However, they suffer from a slow convergence rate. In this paper, we aim to accelerate DiT training without any architectural modification. We identify the following issues in the training process: firstly, certain training strategies do not consistently perform well across different data. Secondly, the effectiveness of supervision at specific timesteps is limited. In response, we propose the following contributions: (1) We introduce a new perspective for interpreting the failure of the strategies. Specifically, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10356","kind":"arxiv","version":2},"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/2410.10356/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":"2410.10356","created_at":"2026-07-05T09:28:56.085681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10356v2","created_at":"2026-07-05T09:28:56.085681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10356","created_at":"2026-07-05T09:28:56.085681+00:00"},{"alias_kind":"pith_short_12","alias_value":"QNCXYW4SENEM","created_at":"2026-07-05T09:28:56.085681+00:00"},{"alias_kind":"pith_short_16","alias_value":"QNCXYW4SENEMAFDG","created_at":"2026-07-05T09:28:56.085681+00:00"},{"alias_kind":"pith_short_8","alias_value":"QNCXYW4S","created_at":"2026-07-05T09:28:56.085681+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24888","citing_title":"DiffusionBench: On Holistic Evaluation of Diffusion Transformers","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11096","citing_title":"IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10790","citing_title":"Elucidating Representation Degradation Problem in Diffusion Model Training","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QNCXYW4SENEMAFDG5QMTPAAXED","json":"https://pith.science/pith/QNCXYW4SENEMAFDG5QMTPAAXED.json","graph_json":"https://pith.science/api/pith-number/QNCXYW4SENEMAFDG5QMTPAAXED/graph.json","events_json":"https://pith.science/api/pith-number/QNCXYW4SENEMAFDG5QMTPAAXED/events.json","paper":"https://pith.science/paper/QNCXYW4S"},"agent_actions":{"view_html":"https://pith.science/pith/QNCXYW4SENEMAFDG5QMTPAAXED","download_json":"https://pith.science/pith/QNCXYW4SENEMAFDG5QMTPAAXED.json","view_paper":"https://pith.science/paper/QNCXYW4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10356&json=true","fetch_graph":"https://pith.science/api/pith-number/QNCXYW4SENEMAFDG5QMTPAAXED/graph.json","fetch_events":"https://pith.science/api/pith-number/QNCXYW4SENEMAFDG5QMTPAAXED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QNCXYW4SENEMAFDG5QMTPAAXED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QNCXYW4SENEMAFDG5QMTPAAXED/action/storage_attestation","attest_author":"https://pith.science/pith/QNCXYW4SENEMAFDG5QMTPAAXED/action/author_attestation","sign_citation":"https://pith.science/pith/QNCXYW4SENEMAFDG5QMTPAAXED/action/citation_signature","submit_replication":"https://pith.science/pith/QNCXYW4SENEMAFDG5QMTPAAXED/action/replication_record"}},"created_at":"2026-07-05T09:28:56.085681+00:00","updated_at":"2026-07-05T09:28:56.085681+00:00"}