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 156 篇，第 1 / 4 页

1. ICML 2024A Dense Reward View on Aligning Text-to-Image Diffusion with Preference
2. ICML 2024A Tale of Tails: Model Collapse as a Change of Scaling Laws
3. ICML 2024Accelerating Parallel Sampling of Diffusion Models
4. ICML 2024Accelerating PDE Data Generation via Differential Operator Action in Solution Space
5. ICML 2024ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance Generation
6. ICML 2024Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity
7. ICML 2024Adaptive Stabilization Based on Machine Learning for Column Generation
8. ICML 2024Aligned Objective for Soft-Pseudo-Label Generation in Supervised Learning
9. ICML 2024Amortizing Pragmatic Program Synthesis with Rankings
10. ICML 2024An Image is Worth Multiple Words: Discovering Object Level Concepts using Multi-Concept Prompt Learning
11. ICML 2024An Independence-promoting Loss for Music Generation with Language Models
12. ICML 2024AST-T5: Structure-Aware Pretraining for Code Generation and Understanding
13. ICML 2024Auto-Regressive Next-Token Predictors are Universal Learners
14. ICML 2024Bagged Deep Image Prior for Recovering Images in the Presence of Speckle Noise
15. ICML 2024Behavior Generation with Latent Actions
16. ICML 2024BetterV: Controlled Verilog Generation with Discriminative Guidance
17. ICML 2024Boximator: Generating Rich and Controllable Motions for Video Synthesis
18. ICML 2024BRAIn: Bayesian Reward-conditioned Amortized Inference for natural language generation from feedback
19. ICML 2024CaPS: Collaborative and Private Synthetic Data Generation from Distributed Sources
20. ICML 2024CaRiNG: Learning Temporal Causal Representation under Non-Invertible Generation Process
21. ICML 2024Causal-IQA: Towards the Generalization of Image Quality Assessment Based on Causal Inference
22. ICML 2024CCM: Real-Time Controllable Visual Content Creation Using Text-to-Image Consistency Models
23. ICML 2024Cell2Sentence: Teaching Large Language Models the Language of Biology
24. ICML 2024Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale
25. ICML 2024Collapse-Aware Triplet Decoupling for Adversarially Robust Image Retrieval
26. ICML 2024Completing Visual Objects via Bridging Generation and Segmentation
27. ICML 2024Compositional Image Decomposition with Diffusion Models
28. ICML 2024Compositional Text-to-Image Generation with Dense Blob Representations
29. ICML 2024Compress Clean Signal from Noisy Raw Image: A Self-Supervised Approach
30. ICML 2024Correcting Diffusion-Based Perceptual Image Compression with Privileged End-to-End Decoder
31. ICML 2024Counterfactual Image Editing
32. ICML 2024Creative Text-to-Audio Generation via Synthesizer Programming
33. ICML 2024Cross-view Masked Diffusion Transformers for Person Image Synthesis
34. ICML 2024CuTS: Customizable Tabular Synthetic Data Generation
35. ICML 2024CW Complex Hypothesis for Image Data
36. ICML 2024D-Flow: Differentiating through Flows for Controlled Generation
37. ICML 2024DAG-Based Column Generation for Adversarial Team Games
38. ICML 2024Data-Efficient Molecular Generation with Hierarchical Textual Inversion
39. ICML 2024Data-free Distillation of Diffusion Models with Bootstrapping
40. ICML 2024Denoising Autoregressive Representation Learning
41. ICML 2024DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation
42. ICML 2024Differentially Private Representation Learning via Image Captioning
43. ICML 2024Diffuse, Sample, Project: Plug-And-Play Controllable Graph Generation
44. ICML 2024Diffusion Models Encode the Intrinsic Dimension of Data Manifolds
45. ICML 2024Diffusion Rejection Sampling
46. ICML 2024Diffusion-based Missing-view Generation With the Application on Incomplete Multi-view Clustering
47. ICML 2024Directly Denoising Diffusion Models
48. ICML 2024DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents
49. ICML 2024DISCRET: Synthesizing Faithful Explanations For Treatment Effect Estimation
50. ICML 2024Disentangled 3D Scene Generation with Layout Learning

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。