{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:A4NLSGG3CJJDGVNKWZA4HMDUQV","short_pith_number":"pith:A4NLSGG3","schema_version":"1.0","canonical_sha256":"071ab918db12523355aab641c3b074855510b6977f2508257528742f46cf4b9f","source":{"kind":"arxiv","id":"2409.16280","version":1},"attestation_state":"computed","paper":{"title":"MonoFormer: One Transformer for Both Diffusion and Autoregression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuyang Zhao, Errui Ding, Haocheng Feng, Jingdong Wang, Wenhao Wang, Xinyan Xiao, Yifan Sun, Yuxing Song","submitted_at":"2024-09-24T17:51:04Z","abstract_excerpt":"Most existing multimodality methods use separate backbones for autoregression-based discrete text generation and diffusion-based continuous visual generation, or the same backbone by discretizing the visual data to use autoregression for both text and visual generation. In this paper, we propose to study a simple idea: share one transformer for both autoregression and diffusion. The feasibility comes from two main aspects: (i) Transformer is successfully applied to diffusion for visual generation, and (ii) transformer training for autoregression and diffusion is very similar, and the differenc"},"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":"2409.16280","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-24T17:51:04Z","cross_cats_sorted":[],"title_canon_sha256":"f37ca8f7e51b60ff605751c4a4e2ae48e6994f9e3895f2899d0a6684d3b77caa","abstract_canon_sha256":"5a3f4775bfd8815ff410a257b1bbe1270add412a49c732ac0f1f69f8c0ca855b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:18.378588Z","signature_b64":"BBJJ0nn9GWZFZf5e3gPg39l0hsUpN1E04TR0SFNCj1MMhsBY47rCy4sWPEdEAYZd1h2epIiN6xN5kl2FVVN5Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"071ab918db12523355aab641c3b074855510b6977f2508257528742f46cf4b9f","last_reissued_at":"2026-07-05T09:11:18.378056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:18.378056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MonoFormer: One Transformer for Both Diffusion and Autoregression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuyang Zhao, Errui Ding, Haocheng Feng, Jingdong Wang, Wenhao Wang, Xinyan Xiao, Yifan Sun, Yuxing Song","submitted_at":"2024-09-24T17:51:04Z","abstract_excerpt":"Most existing multimodality methods use separate backbones for autoregression-based discrete text generation and diffusion-based continuous visual generation, or the same backbone by discretizing the visual data to use autoregression for both text and visual generation. In this paper, we propose to study a simple idea: share one transformer for both autoregression and diffusion. The feasibility comes from two main aspects: (i) Transformer is successfully applied to diffusion for visual generation, and (ii) transformer training for autoregression and diffusion is very similar, and the differenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16280","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/2409.16280/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":"2409.16280","created_at":"2026-07-05T09:11:18.378120+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.16280v1","created_at":"2026-07-05T09:11:18.378120+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16280","created_at":"2026-07-05T09:11:18.378120+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4NLSGG3CJJD","created_at":"2026-07-05T09:11:18.378120+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4NLSGG3CJJDGVNK","created_at":"2026-07-05T09:11:18.378120+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4NLSGG3","created_at":"2026-07-05T09:11:18.378120+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25328","citing_title":"DIVA: Harnessing the Representation Divergence in Unified Multimodal Models for Mutual Reinforcement","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21272","citing_title":"MONET: A Massive, Open, Non-redundant and Enriched Text-to-image dataset","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2505.23606","citing_title":"Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2511.08416","citing_title":"Generative AI Meets 6G and Beyond: Diffusion Models for Semantic Communications","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2602.12370","citing_title":"LLaMo: Scaling Pretrained Language Models for Unified Motion Understanding and Generation with Continuous Autoregressive Tokens","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2503.10631","citing_title":"HybridVLA: Collaborative Diffusion and Autoregression in a Unified Vision-Language-Action Model","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15564","citing_title":"Show-o2: Improved Native Unified Multimodal Models","ref_index":146,"is_internal_anchor":false},{"citing_arxiv_id":"2501.17811","citing_title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A4NLSGG3CJJDGVNKWZA4HMDUQV","json":"https://pith.science/pith/A4NLSGG3CJJDGVNKWZA4HMDUQV.json","graph_json":"https://pith.science/api/pith-number/A4NLSGG3CJJDGVNKWZA4HMDUQV/graph.json","events_json":"https://pith.science/api/pith-number/A4NLSGG3CJJDGVNKWZA4HMDUQV/events.json","paper":"https://pith.science/paper/A4NLSGG3"},"agent_actions":{"view_html":"https://pith.science/pith/A4NLSGG3CJJDGVNKWZA4HMDUQV","download_json":"https://pith.science/pith/A4NLSGG3CJJDGVNKWZA4HMDUQV.json","view_paper":"https://pith.science/paper/A4NLSGG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.16280&json=true","fetch_graph":"https://pith.science/api/pith-number/A4NLSGG3CJJDGVNKWZA4HMDUQV/graph.json","fetch_events":"https://pith.science/api/pith-number/A4NLSGG3CJJDGVNKWZA4HMDUQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4NLSGG3CJJDGVNKWZA4HMDUQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4NLSGG3CJJDGVNKWZA4HMDUQV/action/storage_attestation","attest_author":"https://pith.science/pith/A4NLSGG3CJJDGVNKWZA4HMDUQV/action/author_attestation","sign_citation":"https://pith.science/pith/A4NLSGG3CJJDGVNKWZA4HMDUQV/action/citation_signature","submit_replication":"https://pith.science/pith/A4NLSGG3CJJDGVNKWZA4HMDUQV/action/replication_record"}},"created_at":"2026-07-05T09:11:18.378120+00:00","updated_at":"2026-07-05T09:11:18.378120+00:00"}