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 5 / 14 页

  1. NeurIPS 2026EditJudge-Bench: Auditing VLM Image-Edit Judges with Synthetic Ground Truth
  2. NeurIPS 2026FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing
  3. NeurIPS 2026FlowTrack: Controlling Edit-Signal Execution in Inversion-Free Flow Video Editing
  4. NeurIPS 2026FreqCa: Accelerating Image generation and editing via Frequency-Aware Caching
  5. NeurIPS 2026From Structural Feedback to Prompt Policies: Learning Faithful Text-to-Image Prompt Editors
  6. NeurIPS 2026GenScale: A Benchmark for Relative Object Scale in Image Generation and Editing
  7. NeurIPS 2026GPT-Image-Edit-1M: An Auditable Million-Scale Dataset for Instruction-Guided Image Editing
  8. NeurIPS 2026HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing
  9. NeurIPS 2026IdealCache: Rethinking Cache Scheduling in Diffusion Transformers via Ideal Trajectories
  10. NeurIPS 2026Inline Critic Steers Image Editing
  11. NeurIPS 2026Internalize External Competence for Visual Instruction Editing
  12. NeurIPS 2026Lang-SVG: Hierarchical Image Vectorization with Language Priors
  13. NeurIPS 2026Language Models Can Coarsely Modulate Entropy Under Instruction
  14. NeurIPS 2026MetaKE: Meta-Learning for Knowledge Editing Toward a Better Accuracy-Editability Trade-off
  15. NeurIPS 2026Mission Impossible: Diagnosing and Fixing Non-Operative Instruction Following in Image Editing
  16. NeurIPS 2026MLLM-Edit: Benchmarking Image Forgery Detection and Localization under MLLM-based Editing
  17. NeurIPS 2026MorphGen: Controllable Cell-Image Generation with Biological Representation Alignment
  18. NeurIPS 2026OTEdit: Entropic Transport Corrected Trajectory for Inversion-Free Flow-Based Image Editing
  19. NeurIPS 2026PAVE: Prefill-Conditioned Activation Editing for Hallucination Mitigation in LVLMs
  20. NeurIPS 2026Probing Visual Planning in Image Editing Models
  21. NeurIPS 2026RADIUM: RadioActive Decay of Image-Underlaid Marks
  22. NeurIPS 2026Real In, Real Out: What If We Only Use Real Data for Scene Text Editing?
  23. NeurIPS 2026Residual Paving: Diagnosing the Routing Bottleneck in Selective Refusal Editing
  24. NeurIPS 2026Rethinking Contrastive Targets in Radiology Language-Image Pretraining
  25. NeurIPS 2026RiSE: Residual Subspace Expert for Generalizable Text-Centric Image Forgery Localization
  26. NeurIPS 2026SCULPT: Advancing Masked Discrete Diffusion for High-Resolution Image Synthesis.
  27. NeurIPS 2026SIGMA: Semantic-Difference Instruction-Grounding Mask Annotator for Text-Driven Image Manipulation Localization
  28. NeurIPS 2026SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing
  29. NeurIPS 2026Steer2Edit: From Activation Steering to Component-Level Editing
  30. NeurIPS 2026StitchEdit: Stitching Depth Priors into Image Editors via Per-Layer Gradient Probing
  31. NeurIPS 2026Text-Vision Co-Instructed Image Editing
  32. NeurIPS 2026The Fractured Interlingua: Geometric Bottlenecks in Cross-Lingual Knowledge Editing
  33. NeurIPS 2026Thinking in Boxes: 3D Editing in Real Images Made Easy
  34. NeurIPS 2026TokenRepel: Generating Diverse Image Sets Without Sacrificing Quality
  35. NeurIPS 2026Tool-IQA: Augmenting Image Quality Assessment with Simple Tools
  36. NeurIPS 2026Towards Realistic Conversational Multimodal Instruction Following
  37. NeurIPS 2026VisEditBench: A Benchmark for Vector-Format Diagram Editing with Visual Instructions
  38. NeurIPS 2026WordEval: Evaluating Word-Native Operation Fidelity in Document Editing
  39. CVPR 2025Acc3D: Accelerating Single Image to 3D Diffusion Models via Edge Consistency Guided Score Distillation
  40. CVPR 2025ACE: Anti-Editing Concept Erasure in Text-to-Image Models
  41. CVPR 2025Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training
  42. CVPR 2025Align-A-Video: Deterministic Reward Tuning of Image Diffusion Models for Consistent Video Editing
  43. CVPR 2025Any-Resolution AI-Generated Image Detection by Spectral Learning
  44. CVPR 2025AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea
  45. CVPR 2025Arbitrary-steps Image Super-resolution via Diffusion Inversion
  46. CVPR 2025Arc2Avatar: Generating Expressive 3D Avatars from a Single Image via ID Guidance
  47. CVPR 2025Augmenting Perceptual Super-Resolution via Image Quality Predictors
  48. CVPR 2025Community Forensics: Using Thousands of Generators to Train Fake Image Detectors
  49. CVPR 2025Concept Lancet: Image Editing with Compositional Representation Transplant
  50. CVPR 2025CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D Diffusion

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