图像生成论文趋势 2023–2026

主要结论

• 图像生成论文从 2023 年的 780 篇增长到 2026 年的 1,721 篇，三年间扩大到约 2.2 倍。
• CVPR 是发图像生成论文最多的会议，2023–2026 年共 2,262 篇，占四个会议总量的 44%。
• 交叉方向里涨得最快的是深度学习 · generative models and autoencoders：同时属于两个主题的论文从 2023 年的 35 篇增至 2026 年的 150 篇。
• 在「计算机视觉」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的视频理解是 2.6 倍，图像生成是 2.2 倍。

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

• NeurIPS 2026$\texttt{bispectrum}$: Selective $G$-Bispectra Made Practical
• ICML 2026Klein Hyperbolic Metric Learning
• ICLR 2026A Bayesian Nonparametric Framework for Private, Fair, and Balanced Tabular Data Synthesis
• CVPR 2026Adaptive Learned Image Compression with Graph Neural Networks
• NeurIPS 2025Alchemist: Turning Public Text-to-Image Data into Generative Gold
• ICML 2025BiMark: Unbiased Multilayer Watermarking for Large Language Models
• ICLR 2025Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
• CVPR 2025A Polarization-Aided Transformer for Image Deblurring via Motion Vector Decomposition
• NeurIPS 2024Einsum Benchmark: Enabling the Development of Next-Generation Tensor Execution Engines
• ICML 2024Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity
• ICLR 2024AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ
• CVPR 2024DemoCaricature: Democratising Caricature Generation with a Rough Sketch
• NeurIPS 20234D Panoptic Scene Graph Generation
• ICML 2023Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN
• ICLR 2023Accurate Image Restoration with Attention Retractable Transformer
• CVPR 20233D GAN Inversion With Facial Symmetry Prior
• NeurIPS 2026A Theory of Time-Sensitive Language Generation: Sparse Hallucination Beats Mode Collapse
• ICML 2026Noisy-Channel Minimum Bayes Risk Decoding
• ICLR 2026All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning
• CVPR 2026AIMDepth Asymmetric Image-Event Mamba for Monocular Depth Estimation

全部图像生成论文

共 74 篇，第 1 / 2 页

1. ICML 2023A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models
2. ICML 2023Architecture-Agnostic Masked Image Modeling -- From ViT back to CNN
3. ICML 2023Attributing Image Generative Models using Latent Fingerprints
4. ICML 2023AudioLDM: Text-to-Audio Generation with Latent Diffusion Models
5. ICML 2023Autoregressive Diffusion Model for Graph Generation
6. ICML 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models
7. ICML 2023CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets
8. ICML 2023Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D
9. ICML 2023CodeIPPrompt: Intellectual Property Infringement Assessment of Code Language Models
10. ICML 2023Coder Reviewer Reranking for Code Generation
11. ICML 2023Composer: Creative and Controllable Image Synthesis with Composable Conditions
12. ICML 2023Controlled Text Generation with Natural Language Instructions
13. ICML 2023Data Representations' Study of Latent Image Manifolds
14. ICML 2023Deep Latent State Space Models for Time-Series Generation
15. ICML 2023Deep Perturbation Learning: Enhancing the Network Performance via Image Perturbations
16. ICML 2023Dirichlet Diffusion Score Model for Biological Sequence Generation
17. ICML 2023Diverse and Faithful Knowledge-Grounded Dialogue Generation via Sequential Posterior Inference
18. ICML 2023DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation
19. ICML 2023Evidential Interactive Learning for Medical Image Captioning
20. ICML 2023Exploring Chemical Space with Score-based Out-of-distribution Generation
21. ICML 2023Extrapolative Controlled Sequence Generation via Iterative Refinement
22. ICML 2023Fourmer: An Efficient Global Modeling Paradigm for Image Restoration
23. ICML 2023Geometric Latent Diffusion Models for 3D Molecule Generation
24. ICML 2023Hierarchical Neural Coding for Controllable CAD Model Generation
25. ICML 2023Hyperbolic Image-text Representations
26. ICML 2023I$^2$SB: Image-to-Image Schrödinger Bridge
27. ICML 2023Identifying Interpretable Subspaces in Image Representations
28. ICML 2023Image generation with shortest path diffusion
29. ICML 2023Image Restoration with Mean-Reverting Stochastic Differential Equations
30. ICML 2023Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compression
31. ICML 2023Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models
32. ICML 2023IRNeXt: Rethinking Convolutional Network Design for Image Restoration
33. ICML 2023Loss-Guided Diffusion Models for Plug-and-Play Controllable Generation
34. ICML 2023MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation
35. ICML 2023MonoNeRF: Learning Generalizable NeRFs from Monocular Videos without Camera Poses
36. ICML 2023mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
37. ICML 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation
38. ICML 2023Muse: Text-To-Image Generation via Masked Generative Transformers
39. ICML 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion
40. ICML 2023Nonlinear Advantage: Trained Networks Might Not Be As Complex as You Think
41. ICML 2023Nugget: Neural Agglomerative Embeddings of Text
42. ICML 2023On the Effectiveness of Offline RL for Dialogue Response Generation
43. ICML 2023Open-Vocabulary Universal Image Segmentation with MaskCLIP
44. ICML 2023OpenFE: Automated Feature Generation with Expert-level Performance
45. ICML 2023Outline, Then Details: Syntactically Guided Coarse-To-Fine Code Generation
46. ICML 2023PLay: Parametrically Conditioned Layout Generation using Latent Diffusion
47. ICML 2023Private Statistical Estimation of Many Quantiles
48. ICML 2023Protecting Language Generation Models via Invisible Watermarking
49. ICML 2023Raising the Cost of Malicious AI-Powered Image Editing
50. ICML 2023Random Shuffle Transformer for Image Restoration

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。