Image Editing papers, 2023–2026

Key findings

• Image Editing went from 112 papers in 2023 to 238 in 2026, roughly 2.1x in three years.
• CVPR publishes the most Image Editing work: 364 papers from 2023 to 2026, 53% of the four-venue total.
• The fastest-growing overlap is with Applications · computer vision: papers tagged with both rose from 1 in 2023 to 15 in 2026.
• Among the 5 topics under Multimodal Generation, it ranks #3 by 2026 paper count; the fastest grower in the group, Storytelling Generation, is up 15x versus 2.1x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Accelerated Image Editing via Consistency-Aware Source Token Pruning
• ICML 2026Klein Hyperbolic Metric Learning
• ICLR 2026DiffVax: Optimization-Free Image Immunization Against Diffusion-Based Editing
• CVPR 2026AnchorFlow Training-Free 3D Editing via Latent Anchor-Aligned Flows
• NeurIPS 2025A$^3$E: Towards Compositional Model Editing
• ICML 2025DEALing with Image Reconstruction: Deep Attentive Least Squares
• ICLR 2025HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing
• CVPR 2025AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea
• NeurIPS 2024Reproducibility study of “LICO: Explainable Models with Language-Image Consistency"
• ICML 2024Counterfactual Image Editing
• ICLR 2024Guiding Instruction-based Image Editing via Multimodal Large Language Models
• CVPR 2024DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editing
• NeurIPS 2023ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation
• ICML 2023Random Shuffle Transformer for Image Restoration
• ICLR 2023Editing models with task arithmetic
• CVPR 20233D GAN Inversion With Facial Symmetry Prior
• NeurIPS 2026AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer
• ICML 2026DLEBench: Evaluating Small-scale Object Editing Ability for Instruction-based Image Editing Model
• ICLR 2026Energy-Regularized Sequential Model Editing on Hyperspheres
• CVPR 2026ChordEdit One-Step Low-Energy Transport for Image Editing

All Image Editing papers

52 papers, page 1 of 2

1. NeurIPS 2026Accelerated Image Editing via Consistency-Aware Source Token Pruning
2. NeurIPS 2026AIR: Rethinking Image-Text Offset Alignment in Multimodal Contrastive Representation Space
3. NeurIPS 2026AnyBokeh: Physics-Guided Any-to-Any Bokeh Editing with Optical Fingerprint Transfer
4. NeurIPS 2026AR-Edit: Training-Free Streaming Video Editing without Inversion
5. NeurIPS 2026AsymPipe: Accelerating Large-scale DiTs Image Editing via Asymmetry-Aware Pipeline Parallelism
6. NeurIPS 2026BodyBench: Evaluating Adversarial Image Defenses Against AI Nudification Inpainting
7. NeurIPS 2026CARVE: Counterfactual Video Editing for Auditing and Hardening Video Detectors
8. NeurIPS 2026Constrained Look-ahead Guidance for Interference-Aware Flow Editing
9. NeurIPS 2026Delta-Adapter: Scalable Exemplar-Based Image Editing with Single-Pair Supervision
10. NeurIPS 2026Drag as Evidence: Motion-Grounded Latent Recomposition for Drag-Based Editing
11. NeurIPS 2026DynEdit: Dynamic Entropy-Guided Sequential Editing for Large Language Models
12. NeurIPS 2026Early Semantic Grounding in Image Editing Models for Zero-Shot Referring Image Segmentation
13. NeurIPS 2026Edit the Bits, Diff the Codes: Bitwise Residual Editing for Visual Autoregressive Models
14. NeurIPS 2026Editing Large Language Models with Geometry-Aware Regularization
15. NeurIPS 2026EditJudge-Bench: Auditing VLM Image-Edit Judges with Synthetic Ground Truth
16. NeurIPS 2026FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing
17. NeurIPS 2026FlowTrack: Controlling Edit-Signal Execution in Inversion-Free Flow Video Editing
18. NeurIPS 2026FreqCa: Accelerating Image generation and editing via Frequency-Aware Caching
19. NeurIPS 2026From Structural Feedback to Prompt Policies: Learning Faithful Text-to-Image Prompt Editors
20. NeurIPS 2026GenScale: A Benchmark for Relative Object Scale in Image Generation and Editing
21. NeurIPS 2026GPT-Image-Edit-1M: An Auditable Million-Scale Dataset for Instruction-Guided Image Editing
22. NeurIPS 2026HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing
23. NeurIPS 2026IdealCache: Rethinking Cache Scheduling in Diffusion Transformers via Ideal Trajectories
24. NeurIPS 2026Inline Critic Steers Image Editing
25. NeurIPS 2026Internalize External Competence for Visual Instruction Editing
26. NeurIPS 2026Lang-SVG: Hierarchical Image Vectorization with Language Priors
27. NeurIPS 2026Language Models Can Coarsely Modulate Entropy Under Instruction
28. NeurIPS 2026MetaKE: Meta-Learning for Knowledge Editing Toward a Better Accuracy-Editability Trade-off
29. NeurIPS 2026Mission Impossible: Diagnosing and Fixing Non-Operative Instruction Following in Image Editing
30. NeurIPS 2026MLLM-Edit: Benchmarking Image Forgery Detection and Localization under MLLM-based Editing
31. NeurIPS 2026MorphGen: Controllable Cell-Image Generation with Biological Representation Alignment
32. NeurIPS 2026OTEdit: Entropic Transport Corrected Trajectory for Inversion-Free Flow-Based Image Editing
33. NeurIPS 2026PAVE: Prefill-Conditioned Activation Editing for Hallucination Mitigation in LVLMs
34. NeurIPS 2026Probing Visual Planning in Image Editing Models
35. NeurIPS 2026RADIUM: RadioActive Decay of Image-Underlaid Marks
36. NeurIPS 2026Real In, Real Out: What If We Only Use Real Data for Scene Text Editing?
37. NeurIPS 2026Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing
38. NeurIPS 2026Rethinking Contrastive Targets in Radiology Language-Image Pretraining
39. NeurIPS 2026RiSE: Residual Subspace Expert for Generalizable Text-Centric Image Forgery Localization
40. NeurIPS 2026SCULPT: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis.
41. NeurIPS 2026SIGMA: Semantic-Difference Instruction-Grounding Mask Annotator for Text-Driven Image Manipulation Localization
42. NeurIPS 2026SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing
43. NeurIPS 2026Steer2Edit: From Activation Steering to Component-Level Editing
44. NeurIPS 2026StitchEdit: Stitching Depth Priors into Image Editors via Per-Layer Gradient Probing
45. NeurIPS 2026Text-Vision Co-Instructed Image Editing
46. NeurIPS 2026The Fractured Interlingua: Geometric Bottlenecks in Cross-Lingual Knowledge Editing
47. NeurIPS 2026Thinking in Boxes: 3D Editing in Real Images Made Easy
48. NeurIPS 2026TokenRepel: Generating Diverse Image Sets Without Sacrificing Quality
49. NeurIPS 2026Tool-IQA: Augmenting Image Quality Assessment with Simple Tools
50. NeurIPS 2026Towards Realistic Conversational Multimodal Instruction Following

FAQ

How many Image Editing papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

692 in total: 112 in 2023, 160 in 2024, 182 in 2025, 238 in 2026.

How many Image Editing papers are at NeurIPS 2026?

NeurIPS 2026 has 52 Image Editing papers, versus 45 the year before.

How many Image Editing papers are at ICLR 2026?

ICLR 2026 has 40 Image Editing papers, versus 29 the year before.

How many Image Editing papers are at ICML 2026?

ICML 2026 has 33 Image Editing papers, versus 11 the year before.

How many Image Editing papers are at CVPR 2026?

CVPR 2026 has 113 Image Editing papers, versus 97 the year before.

Which conference publishes the most Image Editing papers?

CVPR, with 364 papers from 2023 to 2026.