{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DOFPGUK7VYF3IGXNK2SCIVNV24","short_pith_number":"pith:DOFPGUK7","schema_version":"1.0","canonical_sha256":"1b8af3515fae0bb41aed56a42455b5d715a7b16f51b8b63ee579750d58984a0d","source":{"kind":"arxiv","id":"2504.20690","version":3},"attestation_state":"computed","paper":{"title":"In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Large Diffusion Transformers perform precise instructional image editing via in-context generation without major retraining.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ji Xie, Yi Yang, Yu Lu, Zechuan Zhang, Zongxin Yang","submitted_at":"2025-04-29T12:14:47Z","abstract_excerpt":"Instruction-based image editing enables precise modifications via natural language prompts, but existing methods face a precision-efficiency tradeoff: fine-tuning demands massive datasets (>10M) and computational resources, while training-free approaches suffer from weak instruction comprehension. We address this by proposing ICEdit, which leverages the inherent comprehension and generation abilities of large-scale Diffusion Transformers (DiTs) through three key innovations: (1) An in-context editing paradigm without architectural modifications; (2) Minimal parameter-efficient fine-tuning for "},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2504.20690","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-29T12:14:47Z","cross_cats_sorted":[],"title_canon_sha256":"b09eff2550cbfc815651eabd97454b4c5a2dcb6fefbfffce677bfa8d2eea2896","abstract_canon_sha256":"27f135510bace5cb08e2ba0a9e557b96faf6fe276a8db9d900404f50a20aae43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:47.349279Z","signature_b64":"RXPP073Ltu9/+s7/+Xz5VEBuZk2GVwYAsd0N58aporuHInlasDw8xbEyQhZ7ucWdZ0lrIPlFpt2M3Bm8tOJhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b8af3515fae0bb41aed56a42455b5d715a7b16f51b8b63ee579750d58984a0d","last_reissued_at":"2026-05-17T23:38:47.348564Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:47.348564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Large Diffusion Transformers perform precise instructional image editing via in-context generation without major retraining.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ji Xie, Yi Yang, Yu Lu, Zechuan Zhang, Zongxin Yang","submitted_at":"2025-04-29T12:14:47Z","abstract_excerpt":"Instruction-based image editing enables precise modifications via natural language prompts, but existing methods face a precision-efficiency tradeoff: fine-tuning demands massive datasets (>10M) and computational resources, while training-free approaches suffer from weak instruction comprehension. We address this by proposing ICEdit, which leverages the inherent comprehension and generation abilities of large-scale Diffusion Transformers (DiTs) through three key innovations: (1) An in-context editing paradigm without architectural modifications; (2) Minimal parameter-efficient fine-tuning for "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"ICEdit achieves state-of-the-art editing performance with only 0.1% of the training data and 1% trainable parameters compared to previous methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the inherent comprehension and generation abilities of large-scale Diffusion Transformers can be effectively leveraged for precise instructional editing through an in-context paradigm without any architectural modifications.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ICEdit achieves state-of-the-art instructional image editing in Diffusion Transformers via in-context generation, requiring only 0.1% of prior training data and 1% trainable parameters.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Large Diffusion Transformers perform precise instructional image editing via in-context generation without major retraining.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a30c54734c9e7ab2952e1db28f3caff75a0a24a0b731dd6cdb0869296cde5e7a"},"source":{"id":"2504.20690","kind":"arxiv","version":3},"verdict":{"id":"1e73ec36-2161-4fe0-b2f0-207517cbbcb5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T16:04:06.609653Z","strongest_claim":"ICEdit achieves state-of-the-art editing performance with only 0.1% of the training data and 1% trainable parameters compared to previous methods.","one_line_summary":"ICEdit achieves state-of-the-art instructional image editing in Diffusion Transformers via in-context generation, requiring only 0.1% of prior training data and 1% trainable parameters.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the inherent comprehension and generation abilities of large-scale Diffusion Transformers can be effectively leveraged for precise instructional editing through an in-context paradigm without any architectural modifications.","pith_extraction_headline":"Large Diffusion Transformers perform precise instructional image editing via in-context generation without major retraining."},"references":{"count":60,"sample":[{"doi":"","year":2023,"title":"Instructpix2pix: Learning to follow image editing instructions","work_id":"fd7a4946-0389-427a-bb45-c75d5e7c48c3","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Magicbrush: A manually annotated dataset for instruction-guided image editing.Advances in Neural Information Processing Systems, 36, 2024","work_id":"da65b41a-11ec-470b-8042-e8459a3c6095","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Emu edit: Precise image editing via recognition and generation tasks","work_id":"041fd7a8-5b0e-41c8-9dd4-1750ebee5c81","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Ultraedit: Instruction-based fine-grained image editing at scale.Advances in Neural Information Processing Systems, 37:3058–3093, 2025","work_id":"63911165-3afc-4d06-8929-abf84f29ab58","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"arXiv preprint arXiv:2309.17102 (2023)","work_id":"2bb3b94c-6b63-43cc-8c25-25ed4a0de29c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":60,"snapshot_sha256":"8df2c86e799a633ea6a0b76f35c0d47ce4df2644664e872c963ef45ccd0c2e84","internal_anchors":13},"formal_canon":{"evidence_count":1,"snapshot_sha256":"76fb4d9e70ba5fd058da1aa94c524198b6a56a3e291d4193f52fbbaab528c58e"},"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":"2504.20690","created_at":"2026-05-17T23:38:47.348669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.20690v3","created_at":"2026-05-17T23:38:47.348669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20690","created_at":"2026-05-17T23:38:47.348669+00:00"},{"alias_kind":"pith_short_12","alias_value":"DOFPGUK7VYF3","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"DOFPGUK7VYF3IGXN","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"DOFPGUK7","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":23,"sample":[{"citing_arxiv_id":"2605.04128","citing_title":"JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation","ref_index":103,"is_internal_anchor":true},{"citing_arxiv_id":"2506.18871","citing_title":"OmniGen2: Towards Instruction-Aligned Multimodal Generation","ref_index":90,"is_internal_anchor":true},{"citing_arxiv_id":"2510.26583","citing_title":"Emu3.5: Native Multimodal Models are World Learners","ref_index":127,"is_internal_anchor":true},{"citing_arxiv_id":"2512.07469","citing_title":"VideoCoF: Unified Video Editing with Temporal Reasoner","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2512.21788","citing_title":"InstructMoLE: Instruction-Guided Mixture of Low-rank Experts for Multi-Conditional Image Generation","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2601.15507","citing_title":"A Unified and Controllable Framework for Layered Image Generation with Visual Effects","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2512.07584","citing_title":"LongCat-Image Technical Report","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2603.00918","citing_title":"Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards","ref_index":87,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13122","citing_title":"Early Semantic Grounding in Image Editing Models for Zero-Shot Referring Image Segmentation","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12500","citing_title":"SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture","ref_index":165,"is_internal_anchor":true},{"citing_arxiv_id":"2506.03147","citing_title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":90,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24625","citing_title":"Meta-CoT: Enhancing Granularity and Generalization in Image Editing","ref_index":82,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23763","citing_title":"Edit Where You Mean: Region-Aware Adapter Injection for Mask-Free Local Image Editing","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2511.22699","citing_title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer","ref_index":94,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10954","citing_title":"FineEdit: Fine-Grained Image Edit with Bounding Box Guidance","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2506.15742","citing_title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2505.14683","citing_title":"Emerging Properties in Unified Multimodal Pretraining","ref_index":101,"is_internal_anchor":true},{"citing_arxiv_id":"2508.02324","citing_title":"Qwen-Image Technical Report","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16114","citing_title":"Towards In-Context Tone Style Transfer with A Large-Scale Triplet Dataset","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":90,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21904","citing_title":"UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection","ref_index":73,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04128","citing_title":"JoyAI-Image: Awaking Spatial Intelligence in Unified Multimodal Understanding and Generation","ref_index":103,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DOFPGUK7VYF3IGXNK2SCIVNV24","json":"https://pith.science/pith/DOFPGUK7VYF3IGXNK2SCIVNV24.json","graph_json":"https://pith.science/api/pith-number/DOFPGUK7VYF3IGXNK2SCIVNV24/graph.json","events_json":"https://pith.science/api/pith-number/DOFPGUK7VYF3IGXNK2SCIVNV24/events.json","paper":"https://pith.science/paper/DOFPGUK7"},"agent_actions":{"view_html":"https://pith.science/pith/DOFPGUK7VYF3IGXNK2SCIVNV24","download_json":"https://pith.science/pith/DOFPGUK7VYF3IGXNK2SCIVNV24.json","view_paper":"https://pith.science/paper/DOFPGUK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.20690&json=true","fetch_graph":"https://pith.science/api/pith-number/DOFPGUK7VYF3IGXNK2SCIVNV24/graph.json","fetch_events":"https://pith.science/api/pith-number/DOFPGUK7VYF3IGXNK2SCIVNV24/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DOFPGUK7VYF3IGXNK2SCIVNV24/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DOFPGUK7VYF3IGXNK2SCIVNV24/action/storage_attestation","attest_author":"https://pith.science/pith/DOFPGUK7VYF3IGXNK2SCIVNV24/action/author_attestation","sign_citation":"https://pith.science/pith/DOFPGUK7VYF3IGXNK2SCIVNV24/action/citation_signature","submit_replication":"https://pith.science/pith/DOFPGUK7VYF3IGXNK2SCIVNV24/action/replication_record"}},"created_at":"2026-05-17T23:38:47.348669+00:00","updated_at":"2026-05-17T23:38:47.348669+00:00"}