AI Paper Atlas

Research map / Benchmarks / Emu Edit

Emu Edit leaderboard

21 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Emu Edit. Best DINO: 0.897 (MURE, ECCV 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

Emu Edit · DINO

15 papers, each with its best reported number for its own method; higher is better.

#DINO ↑MethodPaperTopic
10.897MURE
BAGEL
Unlocking Complex Image Editing via Natively Interleaved Visual Textual CoT with Deep Confidence Reasoning
ECCV 2026 · Table 1
Multimodal LLMs
20.885CORE-VCORE-V: Chain-Of-thought REasoning for Image Editing with Visual Interaction
ECCV 2026 · Table 1
Multimodal LLMs
30.8829FireEdit
Stable Diffusion 1.5
FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model
CVPR 2025 · Emu Edit results table
Multimodal LLMs
40.876OmniGen2
Qwen2.5-VL-3B + DiT
OmniGen2: Towards Instruction-Aligned Multimodal Generation
CVPR 2026 · Table 3
Multimodal LLMs
50.843CoLoGen
FLUX.1
CoLoGen: Progressive Learning of Concept-Localization Duality for Unified Image Generation
CVPR 2026 · Table 2
Text-to-image diffusion
60.835CARE-Edit
FLUX.1 Dev
CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing
CVPR 2026 · Table 1
Editing and style transfer
70.834UIP2P (Ours)UIP2P: Unsupervised Instruction-based Image Editing via Edit Reversibility Constraint
ICCV 2025 · Table 4
Editing and style transfer
80.832EditMGT (Ours)EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing
CVPR 2026 · Table 1
Editing and style transfer
90.831FOCUS
Qwen2.5-3B
FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation
NeurIPS 2025 · Image editing benchmarks table
Multimodal LLMs
100.821AnySD w/ AnyEdit
Stable Diffusion 1.5
AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea
CVPR 2025 · Table 4
Editing and style transfer
5 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Emu Edit · CLIPout

13 papers, each with its best reported number for its own method; higher is better.

#CLIPout ↑MethodPaperTopic
10.362UniDFlowBest of Both Worlds: Multimodal Reasoning and Generation via Unified Discrete Flow Matching
ICML 2026 · Table 4
Multimodal LLMs
20.322Add-it
FLUX.1-dev
Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models
ICLR 2025 · Table 2
Editing and style transfer
30.313CARE-Edit
FLUX.1 Dev
CARE-Edit: Condition-Aware Routing of Experts for Contextual Image Editing
CVPR 2026 · Table 1
Editing and style transfer
40.313CORE-VCORE-V: Chain-Of-thought REasoning for Image Editing with Visual Interaction
ECCV 2026 · Table 1
Multimodal LLMs
50.311OmniGen2
Qwen2.5-VL-3B + DiT
OmniGen2: Towards Instruction-Aligned Multimodal Generation
CVPR 2026 · Table 3
Multimodal LLMs
60.308EditMGT (Ours)EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing
CVPR 2026 · Table 1
Editing and style transfer
70.3078NEP
LlamaGen-XL
NEP: Autoregressive Image Editing via Next Editing Token Prediction
NeurIPS 2025 · Emu Edit results table
Editing and style transfer
80.301CoLoGen
FLUX.1
CoLoGen: Progressive Learning of Concept-Localization Duality for Unified Image Generation
CVPR 2026 · Table 2
Text-to-image diffusion
90.301MURE
BAGEL
Unlocking Complex Image Editing via Natively Interleaved Visual Textual CoT with Deep Confidence Reasoning
ECCV 2026 · Table 1
Multimodal LLMs
100.286Ours
Lumina-mGPT-7B-768
Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization
ICML 2025 · Appendix: Image-editing compar
CLIP and zero-shot
3 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Emu Edit · L1

10 papers, each with its best reported number for its own method; lower is better.

#L1 ↓MethodPaperTopic
10.0515Ours (1M w/o region data)
Stable Diffusion v1.5
UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
NeurIPS 2024 · Emu Edit Test results table
Editing and style transfer
20.0574FireEdit
Stable Diffusion 1.5
FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model
CVPR 2025 · Emu Edit results table
Multimodal LLMs
30.069PixWizard
Lumina-Next-T2I
PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions
ICLR 2025 · Image editing table
Text-to-image diffusion
40.07AnySD w/ AnyEdit
Stable Diffusion 1.5
AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea
CVPR 2025 · Table 4
Editing and style transfer
50.0781NEP
LlamaGen-XL
NEP: Autoregressive Image Editing via Next Editing Token Prediction
NeurIPS 2025 · Emu Edit results table
Editing and style transfer
60.093EditMGT (Ours)EditMGT: Unleashing Potentials of Masked Generative Transformers in Image Editing
CVPR 2026 · Table 1
Editing and style transfer
70.094Emu Edit
Emu
Emu Edit: Precise Image Editing via Recognition and Generation Tasks
CVPR 2024 · Table 2
Editing and style transfer
80.099UniRealUniReal: Universal Image Generation and Editing via Learning Real-world Dynamics
CVPR 2025 · Table 2
Video generation
90.111CoLoGen
FLUX.1
CoLoGen: Progressive Learning of Concept-Localization Duality for Unified Image Generation
CVPR 2026 · Table 2
Text-to-image diffusion
100.132Ours
Lumina-mGPT-7B-768
Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization
ICML 2025 · Appendix: Image-editing compar
CLIP and zero-shot

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.