{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XLMUT3UJRA4NW74L6ILZWM47Z2","short_pith_number":"pith:XLMUT3UJ","schema_version":"1.0","canonical_sha256":"bad949ee898838db7f8bf2179b339fceb6b0809c8883ffb59838abe81b908e48","source":{"kind":"arxiv","id":"2604.24763","version":2},"attestation_state":"computed","paper":{"title":"Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Tuna-2 shows that simple pixel patch embeddings can replace pretrained vision encoders for unified multimodal understanding and generation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Belinda Zeng, Jonas Schult, Luke Zettlemoyer, Mengzhao Chen, Ping Luo, Sen He, Shoufa Chen, Tao Xiang, Tianhong Li, Weiming Ren, Wenhu Chen, Xiaoke Huang, Yatai Ji, Yuren Cong, Zhiheng Liu","submitted_at":"2026-04-27T17:59:56Z","abstract_excerpt":"Unified multimodal models typically rely on pretrained vision encoders and use separate visual representations for understanding and generation, creating misalignment between the two tasks and preventing fully end-to-end optimization from raw pixels. We introduce Tuna-2, a native unified multimodal model that performs visual understanding and generation directly based on pixel embeddings. Tuna-2 drastically simplifies the model architecture by employing simple patch embedding layers to encode visual input, completely discarding the modular vision encoder designs such as the VAE or the represen"},"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":"2604.24763","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-04-27T17:59:56Z","cross_cats_sorted":[],"title_canon_sha256":"fcd3d766fa645fb882bbaf1a54ecfdd2df1a45fc353c92e79193608fca6e7dc7","abstract_canon_sha256":"6da0401ac5d63b909a123cde4a092dd4683b560b4692dc78f5060d4c533dfc94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:32.948674Z","signature_b64":"JPMCX/LgRJuGEDhEOLS78VC/igbClh+2pLJuiHONPsWApuFQj2owpafYlCYPbMwpHzV8yQ5pDHiRVVF/o2qkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bad949ee898838db7f8bf2179b339fceb6b0809c8883ffb59838abe81b908e48","last_reissued_at":"2026-05-20T00:04:32.947791Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:32.947791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Tuna-2 shows that simple pixel patch embeddings can replace pretrained vision encoders for unified multimodal understanding and generation.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Belinda Zeng, Jonas Schult, Luke Zettlemoyer, Mengzhao Chen, Ping Luo, Sen He, Shoufa Chen, Tao Xiang, Tianhong Li, Weiming Ren, Wenhu Chen, Xiaoke Huang, Yatai Ji, Yuren Cong, Zhiheng Liu","submitted_at":"2026-04-27T17:59:56Z","abstract_excerpt":"Unified multimodal models typically rely on pretrained vision encoders and use separate visual representations for understanding and generation, creating misalignment between the two tasks and preventing fully end-to-end optimization from raw pixels. We introduce Tuna-2, a native unified multimodal model that performs visual understanding and generation directly based on pixel embeddings. Tuna-2 drastically simplifies the model architecture by employing simple patch embedding layers to encode visual input, completely discarding the modular vision encoder designs such as the VAE or the represen"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Tuna-2 achieves state-of-the-art performance in multimodal benchmarks, demonstrating that unified pixel-space modelling can fully compete with latent-space approaches for high-quality image generation. Moreover, while the encoder-based variant converges faster in early pretraining, Tuna-2's encoder-free design achieves stronger multimodal understanding at scale, particularly on tasks requiring fine-grained visual perception.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That simple patch embedding layers applied directly to pixels can extract sufficient visual features for both high-quality generation and fine-grained understanding without the inductive biases or pretraining provided by dedicated vision encoders.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Tuna-2 shows pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive or superior results on understanding and generation benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Tuna-2 shows that simple pixel patch embeddings can replace pretrained vision encoders for unified multimodal understanding and generation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"0d852a7d6154f4060b4655365e59ed1af7074e4b6ca131d8bfbdf770df1f3477"},"source":{"id":"2604.24763","kind":"arxiv","version":2},"verdict":{"id":"c5793468-ad57-400e-91e7-1d7890d12b31","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T04:27:47.732435Z","strongest_claim":"Tuna-2 achieves state-of-the-art performance in multimodal benchmarks, demonstrating that unified pixel-space modelling can fully compete with latent-space approaches for high-quality image generation. Moreover, while the encoder-based variant converges faster in early pretraining, Tuna-2's encoder-free design achieves stronger multimodal understanding at scale, particularly on tasks requiring fine-grained visual perception.","one_line_summary":"Tuna-2 shows pixel embeddings can replace vision encoders in unified multimodal models, achieving competitive or superior results on understanding and generation benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That simple patch embedding layers applied directly to pixels can extract sufficient visual features for both high-quality generation and fine-grained understanding without the inductive biases or pretraining provided by dedicated vision encoders.","pith_extraction_headline":"Tuna-2 shows that simple pixel patch embeddings can replace pretrained vision encoders for unified multimodal understanding and generation."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.24763/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T21:44:27.612842Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"fd1d77f395f8cfc7b6286c0bd81ecda604b883af1c59a7bd11bba05c71223451"},"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":"2604.24763","created_at":"2026-05-20T00:04:32.947930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.24763v2","created_at":"2026-05-20T00:04:32.947930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.24763","created_at":"2026-05-20T00:04:32.947930+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLMUT3UJRA4N","created_at":"2026-05-20T00:04:32.947930+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLMUT3UJRA4NW74L","created_at":"2026-05-20T00:04:32.947930+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLMUT3UJ","created_at":"2026-05-20T00:04:32.947930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"2605.18678","citing_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","ref_index":79,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18678","citing_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12271","citing_title":"Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12500","citing_title":"SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture","ref_index":85,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08029","citing_title":"STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XLMUT3UJRA4NW74L6ILZWM47Z2","json":"https://pith.science/pith/XLMUT3UJRA4NW74L6ILZWM47Z2.json","graph_json":"https://pith.science/api/pith-number/XLMUT3UJRA4NW74L6ILZWM47Z2/graph.json","events_json":"https://pith.science/api/pith-number/XLMUT3UJRA4NW74L6ILZWM47Z2/events.json","paper":"https://pith.science/paper/XLMUT3UJ"},"agent_actions":{"view_html":"https://pith.science/pith/XLMUT3UJRA4NW74L6ILZWM47Z2","download_json":"https://pith.science/pith/XLMUT3UJRA4NW74L6ILZWM47Z2.json","view_paper":"https://pith.science/paper/XLMUT3UJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.24763&json=true","fetch_graph":"https://pith.science/api/pith-number/XLMUT3UJRA4NW74L6ILZWM47Z2/graph.json","fetch_events":"https://pith.science/api/pith-number/XLMUT3UJRA4NW74L6ILZWM47Z2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLMUT3UJRA4NW74L6ILZWM47Z2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLMUT3UJRA4NW74L6ILZWM47Z2/action/storage_attestation","attest_author":"https://pith.science/pith/XLMUT3UJRA4NW74L6ILZWM47Z2/action/author_attestation","sign_citation":"https://pith.science/pith/XLMUT3UJRA4NW74L6ILZWM47Z2/action/citation_signature","submit_replication":"https://pith.science/pith/XLMUT3UJRA4NW74L6ILZWM47Z2/action/replication_record"}},"created_at":"2026-05-20T00:04:32.947930+00:00","updated_at":"2026-05-20T00:04:32.947930+00:00"}