图像生成论文趋势 2023–2026

文生图与图像合成

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 5,184 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

图像生成论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202317011874418780
20243181991565431,216
20254302781476121,467
20264533492306891,721

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

全部图像生成论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 780 篇，第 12 / 16 页

  1. ICML 2023Deep Perturbation Learning: Enhancing the Network Performance via Image Perturbations
  2. ICML 2023Dirichlet Diffusion Score Model for Biological Sequence Generation
  3. ICML 2023Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference
  4. ICML 2023DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation
  5. ICML 2023Evidential Interactive Learning for Medical Image Captioning
  6. ICML 2023Exploring Chemical Space with Score-based Out-of-distribution Generation
  7. ICML 2023Extrapolative Controlled Sequence Generation via Iterative Refinement
  8. ICML 2023Fourmer: An Efficient Global Modeling Paradigm for Image Restoration
  9. ICML 2023Geometric Latent Diffusion Models for 3D Molecule Generation
  10. ICML 2023Hierarchical Neural Coding for Controllable CAD Model Generation
  11. ICML 2023Hyperbolic Image-text Representations
  12. ICML 2023I$^2$SB: Image-to-Image Schrödinger Bridge
  13. ICML 2023Identifying Interpretable Subspaces in Image Representations
  14. ICML 2023Image generation with shortest path diffusion
  15. ICML 2023Image Restoration with Mean-Reverting Stochastic Differential Equations
  16. ICML 2023Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression
  17. ICML 2023Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models
  18. ICML 2023IRNeXt: Rethinking Convolutional Network Design for Image Restoration
  19. ICML 2023Loss-Guided Diffusion Models for Plug-and-Play Controllable Generation
  20. ICML 2023MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation
  21. ICML 2023MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Poses
  22. ICML 2023mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
  23. ICML 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation
  24. ICML 2023Muse: Text-To-Image Generation via Masked Generative Transformers
  25. ICML 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion
  26. ICML 2023Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think
  27. ICML 2023Nugget: Neural Agglomerative Embeddings of Text
  28. ICML 2023On the Effectiveness of Offline RL for Dialogue Response Generation
  29. ICML 2023Open-Vocabulary Universal Image Segmentation with MaskCLIP
  30. ICML 2023OpenFE: Automated Feature Generation with Expert-level Performance
  31. ICML 2023Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation
  32. ICML 2023PLay: Parametrically Conditioned Layout Generation using Latent Diffusion
  33. ICML 2023Private Statistical Estimation of Many Quantiles
  34. ICML 2023Protecting Language Generation Models via Invisible Watermarking
  35. ICML 2023Raising the Cost of Malicious AI-Powered Image Editing
  36. ICML 2023Random Shuffle Transformer for Image Restoration
  37. ICML 2023Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC
  38. ICML 2023Repository-Level Prompt Generation for Large Language Models of Code
  39. ICML 2023RLEG: Vision-Language Representation Learning with Diffusion-based Embedding Generation
  40. ICML 2023Robust One-Class Classification with Signed Distance Function using 1-Lipschitz Neural Networks
  41. ICML 2023Scalable Adaptive Computation for Iterative Generation
  42. ICML 2023SDDM: Score-Decomposed Diffusion Models on Manifolds for Unpaired Image-to-Image Translation
  43. ICML 2023SE(3) diffusion model with application to protein backbone generation
  44. ICML 2023Semi-Offline Reinforcement Learning for Optimized Text Generation
  45. ICML 2023simple diffusion: End-to-end diffusion for high resolution images
  46. ICML 2023SinDDM: A Single Image Denoising Diffusion Model
  47. ICML 2023Slot-VAE: Object-Centric Scene Generation with Slot Attention
  48. ICML 2023Stein Variational Goal Generation for adaptive Exploration in Multi-Goal Reinforcement Learning
  49. ICML 2023StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis
  50. ICML 2023Surface Snapping Optimization Layer for Single Image Object Shape Reconstruction

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 查图像生成在 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-generation"}

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生成论文？
共 5,184 篇，按年份分别是 2023 年 780 篇、2024 年 1,216 篇、2025 年 1,467 篇、2026 年 1,721 篇。
NeurIPS 2026 有多少篇图像生成论文？
NeurIPS 2026 有 453 篇图像生成论文，上一届是 430 篇。
ICLR 2026 有多少篇图像生成论文？
ICLR 2026 有 349 篇图像生成论文，上一届是 278 篇。
ICML 2026 有多少篇图像生成论文？
ICML 2026 有 230 篇图像生成论文，上一届是 147 篇。
CVPR 2026 有多少篇图像生成论文？
CVPR 2026 有 689 篇图像生成论文，上一届是 612 篇。
哪个会议的图像生成论文最多？
CVPR，2023–2026 年共 2,262 篇。

「计算机视觉」下的其他主题