# Editing

Source: [Editing](<https://www.sota2.com/research/dataset/editing>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Benchmarks

Page 1 of 4. This is an index page, not the full collection.

- [Next index page](<https://www.sota2.com/research/dataset/editing.md?page=2>): Follow this link to discover more pages.

- [Sequential Knowledge Editing on ZsRE (10,000 Samples)](<https://www.sota2.com/research/sota/sequential-knowledge-editing-on-zsre-10-000-samples.md>): Sequential Knowledge Editing; ZsRE sequential editing 10,000 Samples.

- [Sequential Knowledge Editing on CounterFact (10,000 Samples)](<https://www.sota2.com/research/sota/sequential-knowledge-editing-on-counterfact-10-000-samples.md>): Sequential Knowledge Editing; CounterFact sequential editing 10,000 Samples.

- [Face Forgery Detection on DiFF Face Editing representative subset (test)](<https://www.sota2.com/research/sota/face-forgery-detection-on-diff-face-editing-representative-subset-test.md>): Face Forgery Detection; DiFF Face Editing representative subset (test).

- [Model Editing on ZSRE sequential editing of 1000 facts](<https://www.sota2.com/research/sota/model-editing-on-zsre-sequential-editing-of-1000-facts.md>): Model Editing; ZSRE sequential editing of 1000 facts.

- [Online Editing on VLKEB Sliding Continual Editing](<https://www.sota2.com/research/sota/online-editing-on-vlkeb-sliding-continual-editing.md>): Online Editing; VLKEB Sliding Continual Editing.

- [LVLM image editing on Qwen-based LVLM image editing agent evaluation set noise-based injection (test)](<https://www.sota2.com/research/sota/lvlm-image-editing-on-qwen-based-lvlm-image-editing-agent-evaluation-set-noise-based-injection-test.md>): LVLM image editing; Qwen-based LVLM image editing agent evaluation set noise-based injection (test).

- [Image Inpainting on High-resolution Image Editing 75% Edit Ratio](<https://www.sota2.com/research/sota/image-inpainting-on-high-resolution-image-editing-75-percent-edit-ratio.md>): Image Inpainting; High-resolution Image Editing 75% Edit Ratio.

- [Image Inpainting on High-resolution Image Editing 50% Edit Ratio](<https://www.sota2.com/research/sota/image-inpainting-on-high-resolution-image-editing-50-percent-edit-ratio.md>): Image Inpainting; High-resolution Image Editing 50% Edit Ratio.

- [Image Inpainting on High-resolution Image Editing 25% Edit Ratio](<https://www.sota2.com/research/sota/image-inpainting-on-high-resolution-image-editing-25-percent-edit-ratio.md>): Image Inpainting; High-resolution Image Editing 25% Edit Ratio.

- [Knowledge Editing on Multilingual Knowledge Editing EN LLaMA backbone (test)](<https://www.sota2.com/research/sota/knowledge-editing-on-multilingual-knowledge-editing-en-llama-backbone-test.md>): Knowledge Editing; Multilingual Knowledge Editing EN LLaMA backbone (test).

- [Deepfake Detection on Face Editing](<https://www.sota2.com/research/sota/deepfake-detection-on-face-editing.md>): Deepfake Detection; Face Editing.

- [Knowledge Editing on Knowledge Editing Aggregate Performance](<https://www.sota2.com/research/sota/knowledge-editing-on-knowledge-editing-aggregate-performance.md>): Knowledge Editing; Knowledge Editing Aggregate Performance.

- [Knowledge Editing on Knowledge Editing Locality](<https://www.sota2.com/research/sota/knowledge-editing-on-knowledge-editing-locality.md>): Knowledge Editing; Knowledge Editing Locality.

- [Knowledge Editing on Knowledge Editing (Generality)](<https://www.sota2.com/research/sota/knowledge-editing-on-knowledge-editing-generality.md>): Knowledge Editing; Knowledge Editing (Generality).

- [Knowledge Editing Reliability](<https://www.sota2.com/research/sota/knowledge-editing-reliability.md>): Knowledge Editing; Knowledge Editing Reliability.

- [Spatial Alignment on RoomEditing](<https://www.sota2.com/research/sota/spatial-alignment-on-roomediting.md>): Spatial Alignment; RoomEditing.

- [Video Editing on 71 Video Editing Tasks](<https://www.sota2.com/research/sota/video-editing-on-71-video-editing-tasks.md>): Video Editing; 71 Video Editing Tasks.

- [MolBench-MO Molecule Editing (39 tasks)](<https://www.sota2.com/research/sota/molbench-mo-molecule-editing-39-tasks.md>): Molecule Editing; MolBench-MO Molecule Editing (39 tasks).

- [Video Editing on Video Editing User Study Editing-only (completed-session)](<https://www.sota2.com/research/sota/video-editing-on-video-editing-user-study-editing-only-completed-session.md>): Video Editing; Video Editing User Study Editing-only (completed-session).

- [Image Editing on Synthetic tasks Dependent Chain (unseen editing)](<https://www.sota2.com/research/sota/image-editing-on-synthetic-tasks-dependent-chain-unseen-editing.md>): Image Editing; Synthetic tasks Dependent Chain (unseen editing).

- [Image Editing on PIEBench Editing Setting](<https://www.sota2.com/research/sota/image-editing-on-piebench-editing-setting.md>): Image Editing; PIEBench Editing Setting.

- [Tamper Localization on AIGC-Editing](<https://www.sota2.com/research/sota/tamper-localization-on-aigc-editing.md>): Tamper Localization; AIGC-Editing.

- [Polygon Editing on Urban geometric editing Level-3](<https://www.sota2.com/research/sota/polygon-editing-on-urban-geometric-editing-level-3.md>): Polygon Editing; Urban geometric editing Level-3.

- [Line Editing on Urban geometric editing Level-2](<https://www.sota2.com/research/sota/line-editing-on-urban-geometric-editing-level-2.md>): Line Editing; Urban geometric editing Level-2.

- [Point Editing on Urban geometric editing Level-1](<https://www.sota2.com/research/sota/point-editing-on-urban-geometric-editing-level-1.md>): Point Editing; Urban geometric editing Level-1.

- [Text-guided Image Editing on General Image Editing](<https://www.sota2.com/research/sota/text-guided-image-editing-on-general-image-editing.md>): Text-guided Image Editing; General Image Editing.

- [Multimodal Knowledge Editing on MMEdit 10-step sequential editing on VQA](<https://www.sota2.com/research/sota/multimodal-knowledge-editing-on-mmedit-10-step-sequential-editing-on-vqa.md>): Multimodal Knowledge Editing; MMEdit 10-step sequential editing on VQA.

- [Image Editing Quality Evaluation on Various Image Editing Datasets](<https://www.sota2.com/research/sota/image-editing-quality-evaluation-on-various-image-editing-datasets.md>): Image Editing Quality Evaluation; Various Image Editing Datasets.

- [Style Editing on Style Editing Dataset isp style](<https://www.sota2.com/research/sota/style-editing-on-style-editing-dataset-isp-style.md>): Style Editing; Style Editing Dataset isp style.

- [3D Editing](<https://www.sota2.com/research/sota/3d-editing.md>): 3D Editing; 3D Editing.

- [Image Change Captioning on Image-Editing-Request](<https://www.sota2.com/research/sota/image-change-captioning-on-image-editing-request.md>): Image Change Captioning; Image-Editing-Request.

- [Lifelong Editing on VLKEB Lifelong Editing 11](<https://www.sota2.com/research/sota/lifelong-editing-on-vlkeb-lifelong-editing-11.md>): Lifelong Editing; VLKEB Lifelong Editing 11.

- [Lifelong Editing on E-VQA Lifelong Editing 5](<https://www.sota2.com/research/sota/lifelong-editing-on-e-vqa-lifelong-editing-5.md>): Lifelong Editing; E-VQA Lifelong Editing 5.

- [Talking Face Editing on Talking Face Editing Evaluation Set (test)](<https://www.sota2.com/research/sota/talking-face-editing-on-talking-face-editing-evaluation-set-test.md>): Talking Face Editing; Talking Face Editing Evaluation Set (test).

- [Knowledge Editing on ZsRE massive editing (2,000 items)](<https://www.sota2.com/research/sota/knowledge-editing-on-zsre-massive-editing-2-000-items.md>): Knowledge Editing; ZsRE massive editing (2,000 items).

- [Script generation and planning on Advertisement Video Editing Dataset](<https://www.sota2.com/research/sota/script-generation-and-planning-on-advertisement-video-editing-dataset.md>): Script generation and planning; Advertisement Video Editing Dataset.

- [Video understanding and ordering on Advertisement Video Editing Dataset](<https://www.sota2.com/research/sota/video-understanding-and-ordering-on-advertisement-video-editing-dataset.md>): Video understanding and ordering; Advertisement Video Editing Dataset.

- [Molecular Component Editing on Molecular Component Editing](<https://www.sota2.com/research/sota/molecular-component-editing-on-molecular-component-editing.md>): Molecular Component Editing; Molecular Component Editing.

- [Sketch-based video editing on Sketch-based video editing dataset (test)](<https://www.sota2.com/research/sota/sketch-based-video-editing-on-sketch-based-video-editing-dataset-test.md>): Sketch-based video editing; Sketch-based video editing dataset (test).

- [Sequential Image-to-Image Editing on Image Editing Shadow Removal → Reflection Removal](<https://www.sota2.com/research/sota/sequential-image-to-image-editing-on-image-editing-shadow-removal-reflection-removal.md>): Sequential Image-to-Image Editing; Image Editing Shadow Removal → Reflection Removal.

- [Sequential Image-to-Image Editing on Image Editing Dehazing → Denoising](<https://www.sota2.com/research/sota/sequential-image-to-image-editing-on-image-editing-dehazing-denoising.md>): Sequential Image-to-Image Editing; Image Editing Dehazing → Denoising.

- [Sequential Image-to-Image Editing on Image Editing Deblurring → Dehazing](<https://www.sota2.com/research/sota/sequential-image-to-image-editing-on-image-editing-deblurring-dehazing.md>): Sequential Image-to-Image Editing; Image Editing Deblurring → Dehazing.

- [Music Editing Benchmark](<https://www.sota2.com/research/sota/music-editing-benchmark.md>): Music Editing; Music Editing Benchmark.

- [Audio Event Replacement on Event-level Editing Benchmark](<https://www.sota2.com/research/sota/audio-event-replacement-on-event-level-editing-benchmark.md>): Audio Event Replacement; Event-level Editing Benchmark.

- [Audio Event Removal on Event-level Editing Benchmark](<https://www.sota2.com/research/sota/audio-event-removal-on-event-level-editing-benchmark.md>): Audio Event Removal; Event-level Editing Benchmark.

- [Audio Event Addition on Event-level Editing Benchmark](<https://www.sota2.com/research/sota/audio-event-addition-on-event-level-editing-benchmark.md>): Audio Event Addition; Event-level Editing Benchmark.

- [Edit Transfer on Relation252K Image Editing](<https://www.sota2.com/research/sota/edit-transfer-on-relation252k-image-editing.md>): Edit Transfer; Relation252K Image Editing.

- [Video Editing on VLM-based Video Editing Evaluation](<https://www.sota2.com/research/sota/video-editing-on-vlm-based-video-editing-evaluation.md>): Video Editing; VLM-based Video Editing Evaluation.

- [Scene Text Editing on English Scene Text Editing Dataset (test)](<https://www.sota2.com/research/sota/scene-text-editing-on-english-scene-text-editing-dataset-test.md>): Scene Text Editing; English Scene Text Editing Dataset (test).

- [3D Scene Editing on 3D Scene Editing Evaluation Set (test)](<https://www.sota2.com/research/sota/3d-scene-editing-on-3d-scene-editing-evaluation-set-test.md>): 3D Scene Editing; 3D Scene Editing Evaluation Set (test).

- [Image Change Captioning and Segmentation on Image-Editing-Request](<https://www.sota2.com/research/sota/image-change-captioning-and-segmentation-on-image-editing-request.md>): Image Change Captioning and Segmentation; Image-Editing-Request.

- [Real/Synthetic Separability on Medical Image Editing Dataset (test)](<https://www.sota2.com/research/sota/real-synthetic-separability-on-medical-image-editing-dataset-test.md>): Real/Synthetic Separability; Medical Image Editing Dataset (test).

- [Source Preservation on Medical Image Editing Dataset](<https://www.sota2.com/research/sota/source-preservation-on-medical-image-editing-dataset.md>): Source Preservation; Medical Image Editing Dataset.

- [Semantic-aware image editing on Semantic-aware image editing dataset (test)](<https://www.sota2.com/research/sota/semantic-aware-image-editing-on-semantic-aware-image-editing-dataset-test.md>): Semantic-aware image editing; Semantic-aware image editing dataset (test).

- [Slider-based image editing on continuous-editing benchmark](<https://www.sota2.com/research/sota/slider-based-image-editing-on-continuous-editing-benchmark.md>): Slider-based image editing; continuous-editing benchmark.

- [Colour Editing on Colour Editing Dataset](<https://www.sota2.com/research/sota/colour-editing-on-colour-editing-dataset.md>): Colour Editing; Colour Editing Dataset.

- [Instruction-based image editing on Novel Views averaged across four scenes](<https://www.sota2.com/research/sota/instruction-based-image-editing-on-novel-views-averaged-across-four-scenes.md>): Instruction-based image editing; Instruction-based image editing dataset Novel Views averaged across four scenes.

- [Instruction-based Image Editing on Instruction-based image editing dataset averaged across four scenes (train)](<https://www.sota2.com/research/sota/instruction-based-image-editing-on-instruction-based-image-editing-dataset-averaged-across-four-scenes-train.md>): Instruction-based image editing; Instruction-based image editing dataset averaged across four scenes (train).

- [Multi-view Consistent Editing on Multi-view Consistent Editing dataset (test)](<https://www.sota2.com/research/sota/multi-view-consistent-editing-on-multi-view-consistent-editing-dataset-test.md>): Multi-view Consistent Editing; Multi-view Consistent Editing dataset (test).

- [Video Editing on Video Editing Evaluation Set](<https://www.sota2.com/research/sota/video-editing-on-video-editing-evaluation-set.md>): Video Editing; Video Editing Evaluation Set.

- [Scene Text Editing on Scene Text Editing Evaluation Set (test)](<https://www.sota2.com/research/sota/scene-text-editing-on-scene-text-editing-evaluation-set-test.md>): Scene Text Editing; Scene Text Editing Evaluation Set (test).

- [Knowledge Editing on MMEdit One-Step Editing](<https://www.sota2.com/research/sota/knowledge-editing-on-mmedit-one-step-editing.md>): Knowledge Editing; MMEdit One-Step Editing.

- [Text-guided Image Editing on Image Editing and Reconstruction (test)](<https://www.sota2.com/research/sota/text-guided-image-editing-on-image-editing-and-reconstruction-test.md>): Text-guided Image Editing; Image Editing and Reconstruction (test).

- [Video Editing on Video Editing Evaluation Set (test)](<https://www.sota2.com/research/sota/video-editing-on-video-editing-evaluation-set-test.md>): Video Editing; Video Editing Evaluation Set (test).

- [Knowledge Editing (Edit on English, Test on Chinese) 1.0](<https://www.sota2.com/research/sota/knowledge-editing-edit-on-english-test-on-chinese-1-0.md>): Knowledge Editing; Knowledge Editing (Edit on English, Test on Chinese) 1.0 (ZH).

- [Knowledge Editing Edit on English, Test on Russian 1.0 (RU)](<https://www.sota2.com/research/sota/knowledge-editing-edit-on-english-test-on-russian-1-0-ru.md>): Knowledge Editing; Knowledge Editing Edit on English, Test on Russian 1.0 (RU).

- [Knowledge Editing on Knowledge Editing Edit (Test on German 1.0)](<https://www.sota2.com/research/sota/knowledge-editing-on-knowledge-editing-edit-test-on-german-1-0.md>): Knowledge Editing; Knowledge Editing Edit on English, Test on German 1.0 (DE).

- [Knowledge Editing on Knowledge Editing Edit on English, Test on Czech 1.0 (CS)](<https://www.sota2.com/research/sota/knowledge-editing-on-knowledge-editing-edit-on-english-test-on-czech-1-0-cs.md>): Knowledge Editing; Knowledge Editing Edit on English, Test on Czech 1.0 (CS).

- [Knowledge Editing on English Test Set 1.0](<https://www.sota2.com/research/sota/knowledge-editing-on-english-test-set-1-0.md>): Knowledge Editing; Knowledge Editing Edit on English, Test on English 1.0.

- [In-Context Video Deletion on In-Context Video Editing evaluation set](<https://www.sota2.com/research/sota/in-context-video-deletion-on-in-context-video-editing-evaluation-set.md>): In-Context Video Deletion; In-Context Video Editing evaluation set.

- [In-Context Video Swapping on In-Context Video Editing (test)](<https://www.sota2.com/research/sota/in-context-video-swapping-on-in-context-video-editing-test.md>): In-Context Video Swapping; In-Context Video Editing (test).

- [Targeted Document Editing on Curated Document Editing Benchmark](<https://www.sota2.com/research/sota/targeted-document-editing-on-curated-document-editing-benchmark.md>): Targeted Document Editing; Curated document editing benchmark.

- [Multi-object Video Editing on Curated Video Editing Benchmark 75 videos](<https://www.sota2.com/research/sota/multi-object-video-editing-on-curated-video-editing-benchmark-75-videos.md>): Multi-object Video Editing; Curated Video Editing Benchmark 75 videos.

- [Single-object Video Editing on Curated Video Editing Benchmark 75 videos](<https://www.sota2.com/research/sota/single-object-video-editing-on-curated-video-editing-benchmark-75-videos.md>): Single-object Video Editing; Curated Video Editing Benchmark 75 videos.

- [Style Edit on Speech Editing Dataset](<https://www.sota2.com/research/sota/style-edit-on-speech-editing-dataset.md>): Style Edit; Speech Editing Dataset.

- [Emotion Edit on Speech Editing Dataset](<https://www.sota2.com/research/sota/emotion-edit-on-speech-editing-dataset.md>): Emotion Edit; Speech Editing Dataset.

- [Transcription Edit on Speech Editing Dataset](<https://www.sota2.com/research/sota/transcription-edit-on-speech-editing-dataset.md>): Transcription Edit; Speech Editing Dataset.

- [Audio Editing on Audio Editing Replace](<https://www.sota2.com/research/sota/audio-editing-on-audio-editing-replace.md>): Audio Editing; Audio Editing Replace.

- [Audio Editing on Audio Editing Remove](<https://www.sota2.com/research/sota/audio-editing-on-audio-editing-remove.md>): Audio Editing; Audio Editing Remove.

- [Audio Editing on Audio Editing Add](<https://www.sota2.com/research/sota/audio-editing-on-audio-editing-add.md>): Audio Editing; Audio Editing Add.