图像编辑论文趋势 2023–2026

指令编辑

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 692 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

图像编辑论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20232515864112
202433241390160
202545291197182
2026524033113238

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部图像编辑论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 692 篇，第 8 / 14 页

  1. ICLR 2025InstantPortrait: One-Step Portrait Editing via Diffusion Multi-Objective Distillation
  2. ICLR 2025InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences
  3. ICLR 2025IV-mixed Sampler: Leveraging Image Diffusion Models for Enhanced Video Synthesis
  4. ICLR 2025Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models
  5. ICLR 2025MP-Mat: A 3D-and-Instance-Aware Human Matting and Editing Framework with Multiplane Representation
  6. ICLR 2025Multi-Reward as Condition for Instruction-based Image Editing
  7. ICLR 2025OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision
  8. ICLR 2025Perturbation-Restrained Sequential Model Editing
  9. ICLR 2025PostEdit: Posterior Sampling for Efficient Zero-Shot Image Editing
  10. ICLR 2025Robust Watermarking Using Generative Priors Against Image Editing: From Benchmarking to Advances
  11. ICLR 2025Scaling In-the-Wild Training for Diffusion-based Illumination Harmonization and Editing by Imposing Consistent Light Transport
  12. ICLR 2025Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations
  13. ICLR 2025ToddlerDiffusion: Interactive Structured Image Generation with Cascaded Schrödinger Bridge
  14. ICLR 2025Uncovering Overfitting in Large Language Model Editing
  15. ICML 2025Balancing Preservation and Modification: A Region and Semantic Aware Metric for Instruction-Based Image Editing
  16. ICML 2025DEALing with Image Reconstruction: Deep Attentive Least Squares
  17. ICML 2025DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion Model
  18. ICML 2025Editable Noise Map Inversion: Encoding Target-image into Noise For High-Fidelity Image Manipulation
  19. ICML 2025FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing
  20. ICML 2025FlowDrag: 3D-aware Drag-based Image Editing with Mesh-guided Deformation Vector Flow Fields
  21. ICML 2025Highly Compressed Tokenizer Can Generate Without Training
  22. ICML 2025LightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videos
  23. ICML 2025Mitigating Heterogeneous Token Overfitting in LLM Knowledge Editing
  24. ICML 2025Resolving Lexical Bias in Model Editing
  25. ICML 2025Towards Lifelong Model Editing via Simulating Ideal Editor
  26. NeurIPS 20253DOT: Texture Transfer for 3DGS Objects from a Single Reference Image
  27. NeurIPS 2025A$^3$E: Towards Compositional Model Editing
  28. NeurIPS 2025AutoEdit: Automatic Hyperparameter Tuning for Image Editing
  29. NeurIPS 2025Bio-Inspired Image Restoration
  30. NeurIPS 2025BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editing
  31. NeurIPS 2025CamEdit: Continuous Camera Parameter Control for Photorealistic Image Editing
  32. NeurIPS 2025CAMILA: Context-Aware Masking for Image Editing with Language Alignment
  33. NeurIPS 2025Convolution Goes Higher-Order: A Biologically Inspired Mechanism Empowers Image Classification
  34. NeurIPS 2025Counterfactual Image Editing with Disentangled Causal Latent Space
  35. NeurIPS 2025CURE: Concept Unlearning via Orthogonal Representation Editing in Diffusion Models
  36. NeurIPS 2025DCI: Dual-Conditional Inversion for Boosting Diffusion-Based Image Editing
  37. NeurIPS 2025Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable
  38. NeurIPS 2025EditInfinity: Image Editing with Binary-Quantized Generative Models
  39. NeurIPS 2025Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer
  40. NeurIPS 2025Enhancing Consistency of Flow-Based Image Editing through Kalman Control
  41. NeurIPS 2025Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
  42. NeurIPS 2025Exploring Diffusion Transformer Designs via Grafting
  43. NeurIPS 2025FRN: Fractal-Based Recursive Spectral Reconstruction Network
  44. NeurIPS 2025FSI-Edit: Frequency and Stochasticity Injection for Flexible Diffusion-Based Image Editing
  45. NeurIPS 2025Image Editing As Programs with Diffusion Models
  46. NeurIPS 2025Image Token Matters: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing
  47. NeurIPS 2025ImgEdit: A Unified Image Editing Dataset and Benchmark
  48. NeurIPS 2025InstructRestore: Region-Customized Image Restoration with Human Instructions
  49. NeurIPS 2025KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models
  50. NeurIPS 2025LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查图像编辑在 CVPR 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "image-editing"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇图像编辑论文？
共 692 篇，按年份分别是 2023 年 112 篇、2024 年 160 篇、2025 年 182 篇、2026 年 238 篇。
NeurIPS 2026 有多少篇图像编辑论文？
NeurIPS 2026 有 52 篇图像编辑论文，上一届是 45 篇。
ICLR 2026 有多少篇图像编辑论文？
ICLR 2026 有 40 篇图像编辑论文，上一届是 29 篇。
ICML 2026 有多少篇图像编辑论文？
ICML 2026 有 33 篇图像编辑论文，上一届是 11 篇。
CVPR 2026 有多少篇图像编辑论文？
CVPR 2026 有 113 篇图像编辑论文，上一届是 97 篇。
哪个会议的图像编辑论文最多？
CVPR，2023–2026 年共 364 篇。

「多模态生成」下的其他主题