{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TIXFN4PYCPAVDJ5NOCHMKRQQB7","short_pith_number":"pith:TIXFN4PY","schema_version":"1.0","canonical_sha256":"9a2e56f1f813c151a7ad708ec546100fce25d89bd51f399c9b238616c1253b25","source":{"kind":"arxiv","id":"2410.15027","version":1},"attestation_state":"computed","paper":{"title":"Group Diffusion Transformers are Unsupervised Multitask Learners","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Liang, Huanzhang Dou, Jingren Zhou, Lianghua Huang, Wei Wang, Yu Liu, Yupeng Shi, Yutong Feng, Zhi-Fan Wu","submitted_at":"2024-10-19T07:53:15Z","abstract_excerpt":"While large language models (LLMs) have revolutionized natural language processing with their task-agnostic capabilities, visual generation tasks such as image translation, style transfer, and character customization still rely heavily on supervised, task-specific datasets. In this work, we introduce Group Diffusion Transformers (GDTs), a novel framework that unifies diverse visual generation tasks by redefining them as a group generation problem. In this approach, a set of related images is generated simultaneously, optionally conditioned on a subset of the group. GDTs build upon diffusion tr"},"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":"2410.15027","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-19T07:53:15Z","cross_cats_sorted":[],"title_canon_sha256":"8364279b4714cca3e5b57cb34d02015dd6b30f7e228aaba6f061feedf5068ffb","abstract_canon_sha256":"145a21425146eb5696a312c22d6065cc7d4386e46ae07234ba8973f9dea21a82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:49.036121Z","signature_b64":"GuRSA7tFd6RC/KFFTlcNsKWeWVroejRqKyRRrt3wnHoooMU+qx9uQQtJD4oSWxwqP/nJtH9Bx+QT4nz+QWYQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a2e56f1f813c151a7ad708ec546100fce25d89bd51f399c9b238616c1253b25","last_reissued_at":"2026-07-05T09:22:49.035530Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:49.035530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Group Diffusion Transformers are Unsupervised Multitask Learners","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Liang, Huanzhang Dou, Jingren Zhou, Lianghua Huang, Wei Wang, Yu Liu, Yupeng Shi, Yutong Feng, Zhi-Fan Wu","submitted_at":"2024-10-19T07:53:15Z","abstract_excerpt":"While large language models (LLMs) have revolutionized natural language processing with their task-agnostic capabilities, visual generation tasks such as image translation, style transfer, and character customization still rely heavily on supervised, task-specific datasets. In this work, we introduce Group Diffusion Transformers (GDTs), a novel framework that unifies diverse visual generation tasks by redefining them as a group generation problem. In this approach, a set of related images is generated simultaneously, optionally conditioned on a subset of the group. GDTs build upon diffusion tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15027","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/2410.15027/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":"2410.15027","created_at":"2026-07-05T09:22:49.035594+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.15027v1","created_at":"2026-07-05T09:22:49.035594+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15027","created_at":"2026-07-05T09:22:49.035594+00:00"},{"alias_kind":"pith_short_12","alias_value":"TIXFN4PYCPAV","created_at":"2026-07-05T09:22:49.035594+00:00"},{"alias_kind":"pith_short_16","alias_value":"TIXFN4PYCPAVDJ5N","created_at":"2026-07-05T09:22:49.035594+00:00"},{"alias_kind":"pith_short_8","alias_value":"TIXFN4PY","created_at":"2026-07-05T09:22:49.035594+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.20690","citing_title":"In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TIXFN4PYCPAVDJ5NOCHMKRQQB7","json":"https://pith.science/pith/TIXFN4PYCPAVDJ5NOCHMKRQQB7.json","graph_json":"https://pith.science/api/pith-number/TIXFN4PYCPAVDJ5NOCHMKRQQB7/graph.json","events_json":"https://pith.science/api/pith-number/TIXFN4PYCPAVDJ5NOCHMKRQQB7/events.json","paper":"https://pith.science/paper/TIXFN4PY"},"agent_actions":{"view_html":"https://pith.science/pith/TIXFN4PYCPAVDJ5NOCHMKRQQB7","download_json":"https://pith.science/pith/TIXFN4PYCPAVDJ5NOCHMKRQQB7.json","view_paper":"https://pith.science/paper/TIXFN4PY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.15027&json=true","fetch_graph":"https://pith.science/api/pith-number/TIXFN4PYCPAVDJ5NOCHMKRQQB7/graph.json","fetch_events":"https://pith.science/api/pith-number/TIXFN4PYCPAVDJ5NOCHMKRQQB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TIXFN4PYCPAVDJ5NOCHMKRQQB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TIXFN4PYCPAVDJ5NOCHMKRQQB7/action/storage_attestation","attest_author":"https://pith.science/pith/TIXFN4PYCPAVDJ5NOCHMKRQQB7/action/author_attestation","sign_citation":"https://pith.science/pith/TIXFN4PYCPAVDJ5NOCHMKRQQB7/action/citation_signature","submit_replication":"https://pith.science/pith/TIXFN4PYCPAVDJ5NOCHMKRQQB7/action/replication_record"}},"created_at":"2026-07-05T09:22:49.035594+00:00","updated_at":"2026-07-05T09:22:49.035594+00:00"}