{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6LSVVAHAOJ6TBDDSZL36GTX535","short_pith_number":"pith:6LSVVAHA","schema_version":"1.0","canonical_sha256":"f2e55a80e0727d308c72caf7e34efddf6b5337833d3a786c0c5ca0682ae77daf","source":{"kind":"arxiv","id":"2406.01159","version":1},"attestation_state":"computed","paper":{"title":"Dimba: Transformer-Mamba Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changqian Yu, Debang Li, Junshi Huang, Mingyuan Fan, Youqiang Zhang, Zhengcong Fei","submitted_at":"2024-06-03T09:51:59Z","abstract_excerpt":"This paper unveils Dimba, a new text-to-image diffusion model that employs a distinctive hybrid architecture combining Transformer and Mamba elements. Specifically, Dimba sequentially stacked blocks alternate between Transformer and Mamba layers, and integrate conditional information through the cross-attention layer, thus capitalizing on the advantages of both architectural paradigms. We investigate several optimization strategies, including quality tuning, resolution adaption, and identify critical configurations necessary for large-scale image generation. The model's flexible design support"},"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":"2406.01159","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T09:51:59Z","cross_cats_sorted":[],"title_canon_sha256":"bb63426f022fb952bfb6e768999ed1dffd547f21d5582ffe76fbaef4175efd5d","abstract_canon_sha256":"25216c4f0653441dd80dabc3ced2149fe6fb6b24c151c0ea8ee7a43f031f849a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:36.235471Z","signature_b64":"8j8dRzQeTU8+n4n/y4cF2BVFfc9ilRagU4QG0rWWpJ7s559NcvN6LHeuRJB+a90+x26aESA8zo0wXEyrGykPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f2e55a80e0727d308c72caf7e34efddf6b5337833d3a786c0c5ca0682ae77daf","last_reissued_at":"2026-07-05T08:26:36.235003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:36.235003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dimba: Transformer-Mamba Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changqian Yu, Debang Li, Junshi Huang, Mingyuan Fan, Youqiang Zhang, Zhengcong Fei","submitted_at":"2024-06-03T09:51:59Z","abstract_excerpt":"This paper unveils Dimba, a new text-to-image diffusion model that employs a distinctive hybrid architecture combining Transformer and Mamba elements. Specifically, Dimba sequentially stacked blocks alternate between Transformer and Mamba layers, and integrate conditional information through the cross-attention layer, thus capitalizing on the advantages of both architectural paradigms. We investigate several optimization strategies, including quality tuning, resolution adaption, and identify critical configurations necessary for large-scale image generation. The model's flexible design support"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01159","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/2406.01159/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":"2406.01159","created_at":"2026-07-05T08:26:36.235060+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01159v1","created_at":"2026-07-05T08:26:36.235060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01159","created_at":"2026-07-05T08:26:36.235060+00:00"},{"alias_kind":"pith_short_12","alias_value":"6LSVVAHAOJ6T","created_at":"2026-07-05T08:26:36.235060+00:00"},{"alias_kind":"pith_short_16","alias_value":"6LSVVAHAOJ6TBDDS","created_at":"2026-07-05T08:26:36.235060+00:00"},{"alias_kind":"pith_short_8","alias_value":"6LSVVAHA","created_at":"2026-07-05T08:26:36.235060+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28615","citing_title":"Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2509.01986","citing_title":"Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6LSVVAHAOJ6TBDDSZL36GTX535","json":"https://pith.science/pith/6LSVVAHAOJ6TBDDSZL36GTX535.json","graph_json":"https://pith.science/api/pith-number/6LSVVAHAOJ6TBDDSZL36GTX535/graph.json","events_json":"https://pith.science/api/pith-number/6LSVVAHAOJ6TBDDSZL36GTX535/events.json","paper":"https://pith.science/paper/6LSVVAHA"},"agent_actions":{"view_html":"https://pith.science/pith/6LSVVAHAOJ6TBDDSZL36GTX535","download_json":"https://pith.science/pith/6LSVVAHAOJ6TBDDSZL36GTX535.json","view_paper":"https://pith.science/paper/6LSVVAHA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01159&json=true","fetch_graph":"https://pith.science/api/pith-number/6LSVVAHAOJ6TBDDSZL36GTX535/graph.json","fetch_events":"https://pith.science/api/pith-number/6LSVVAHAOJ6TBDDSZL36GTX535/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6LSVVAHAOJ6TBDDSZL36GTX535/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6LSVVAHAOJ6TBDDSZL36GTX535/action/storage_attestation","attest_author":"https://pith.science/pith/6LSVVAHAOJ6TBDDSZL36GTX535/action/author_attestation","sign_citation":"https://pith.science/pith/6LSVVAHAOJ6TBDDSZL36GTX535/action/citation_signature","submit_replication":"https://pith.science/pith/6LSVVAHAOJ6TBDDSZL36GTX535/action/replication_record"}},"created_at":"2026-07-05T08:26:36.235060+00:00","updated_at":"2026-07-05T08:26:36.235060+00:00"}