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 278 篇，第 1 / 6 页

1. ICLR 2025$\text{I}^2\text{AM}$: Interpreting Image-to-Image Latent Diffusion Models via Bi-Attribution Maps
2. ICLR 20253DIS: Depth-Driven Decoupled Image Synthesis for Universal Multi-Instance Generation
3. ICLR 20253DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation
4. ICLR 20254K4DGen: Panoramic 4D Generation at 4K Resolution
5. ICLR 2025A General Framework for Producing Interpretable Semantic Text Embeddings
6. ICLR 2025A Non-Contrastive Learning Framework for Sequential Recommendation with Preference-Preserving Profile Generation
7. ICLR 2025A Periodic Bayesian Flow for Material Generation
8. ICLR 2025A Simple Approach to Unifying Diffusion-based Conditional Generation
9. ICLR 2025A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation
10. ICLR 2025A Transfer Attack to Image Watermarks
11. ICLR 2025A-Bench: Are LMMs Masters at Evaluating AI-generated Images?
12. ICLR 2025A3D: Does Diffusion Dream about 3D Alignment?
13. ICLR 2025Accelerating 3D Molecule Generation via Jointly Geometric Optimal Transport
14. ICLR 2025Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
15. ICLR 2025Accelerating Diffusion Transformers with Token-wise Feature Caching
16. ICLR 2025ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer
17. ICLR 2025AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation
18. ICLR 2025Adaptive Length Image Tokenization via Recurrent Allocation
19. ICLR 2025Advancing Graph Generation through Beta Diffusion
20. ICLR 2025AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption
21. ICLR 2025AFlow: Automating Agentic Workflow Generation
22. ICLR 2025Aligning Human Motion Generation with Human Perceptions
23. ICLR 2025An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels
24. ICLR 2025Animate-X: Universal Character Image Animation with Enhanced Motion Representation
25. ICLR 2025Anyprefer: An Agentic Framework for Preference Data Synthesis
26. ICLR 2025Atlas Gaussians Diffusion for 3D Generation
27. ICLR 2025Atomas: Hierarchical Adaptive Alignment on Molecule-Text for Unified Molecule Understanding and Generation
28. ICLR 2025Attribute-based Visual Reprogramming for Vision-Language Models
29. ICLR 2025AugKD: Ingenious Augmentations Empower Knowledge Distillation for Image Super-Resolution
30. ICLR 2025Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models
31. ICLR 2025Autoregressive Video Generation without Vector Quantization
32. ICLR 2025Backdooring Vision-Language Models with Out-Of-Distribution Data
33. ICLR 2025Backtracking Improves Generation Safety
34. ICLR 2025Bayesian Image Regression with Soft-thresholded Conditional Autoregressive Prior
35. ICLR 2025Bayesian WeakS-to-Strong from Text Classification to Generation
36. ICLR 2025Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms
37. ICLR 2025BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
38. ICLR 2025BiGR: Harnessing Binary Latent Codes for Image Generation and Improved Visual Representation Capabilities
39. ICLR 2025Boosting Latent Diffusion with Perceptual Objectives
40. ICLR 2025BrainACTIV: Identifying visuo-semantic properties driving cortical selectivity using diffusion-based image manipulation
41. ICLR 2025Bridging Compressed Image Latents and Multimodal Large Language Models
42. ICLR 2025Build-A-Scene: Interactive 3D Layout Control for Diffusion-Based Image Generation
43. ICLR 2025Cached Multi-Lora Composition for Multi-Concept Image Generation
44. ICLR 2025ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance
45. ICLR 2025CLIPDrag: Combining Text-based and Drag-based Instructions for Image Editing
46. ICLR 2025CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
47. ICLR 2025Commit0: Library Generation from Scratch
48. ICLR 2025Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention Gate
49. ICLR 2025Conformal Structured Prediction
50. ICLR 2025Consistent Flow Distillation for Text-to-3D Generation

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。