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 147 篇，第 2 / 3 页

51. ICML 2025FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
52. ICML 2025FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching
53. ICML 2025FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining
54. ICML 2025FrameBridge: Improving Image-to-Video Generation with Bridge Models
55. ICML 2025FreeMesh: Boosting Mesh Generation with Coordinates Merging
56. ICML 2025Generation from Noisy Examples
57. ICML 2025Geometry Informed Tokenization of Molecules for Language Model Generation
58. ICML 2025Graph Generative Pre-trained Transformer
59. ICML 2025GraphCL: Graph-based Clustering for Semi-Supervised Medical Image Segmentation
60. ICML 2025Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding
61. ICML 2025HetSSNet: Spatial-Spectral Heterogeneous Graph Learning Network for Panchromatic and Multispectral Images Fusion
62. ICML 2025Hide & Seek: Transformer Symmetries Obscure Sharpness & Riemannian Geometry Finds It
63. ICML 2025Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots
64. ICML 2025High Dynamic Range Novel View Synthesis with Single Exposure
65. ICML 2025Highly Compressed Tokenizer Can Generate Without Training
66. ICML 2025How to Move Your Dragon: Text-to-Motion Synthesis for Large-Vocabulary Objects
67. ICML 2025Improving Compositional Generation with Diffusion Models Using Lift Scores
68. ICML 2025Improving the Diffusability of Autoencoders
69. ICML 2025Instruct2See: Learning to Remove Any Obstructions Across Distributions
70. ICML 2025Introducing 3D Representation for Dense Volume-to-Volume Translation via Score Fusion
71. ICML 2025Inverse Bridge Matching Distillation
72. ICML 2025LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation
73. ICML 2025Language Models over Canonical Byte-Pair Encodings
74. ICML 2025Large Displacement Motion Transfer with Unsupervised Anytime Interpolation
75. ICML 2025LDMol: A Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Surpasses AR Models
76. ICML 2025Learning Attribute-Aware Hash Codes for Fine-Grained Image Retrieval via Query Optimization
77. ICML 2025Learning to Quantize for Training Vector-Quantized Networks
78. ICML 2025Learning Vision and Language Concepts for Controllable Image Generation
79. ICML 2025Learning-Order Autoregressive Models with Application to Molecular Graph Generation
80. ICML 2025LLaVA-ReID: Selective Multi-image Questioner for Interactive Person Re-Identification
81. ICML 2025LLMs can see and hear without any training
82. ICML 2025LoRA-Gen: Specializing Large Language Model via Online LoRA Generation
83. ICML 2025LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression
84. ICML 2025Masked Generative Nested Transformers with Decode Time Scaling
85. ICML 2025MDDM: Practical Message-Driven Generative Image Steganography Based on Diffusion Models
86. ICML 2025MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance
87. ICML 2025Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance
88. ICML 2025MixBridge: Heterogeneous Image-to-Image Backdoor Attack through Mixture of Schrödinger Bridges
89. ICML 2025Morse: Dual-Sampling for Lossless Acceleration of Diffusion Models
90. ICML 2025MuLan: Adapting Multilingual Diffusion Models for Hundreds of Languages with Negligible Cost
91. ICML 2025NegMerge: Sign-Consensual Weight Merging for Machine Unlearning
92. ICML 2025Neural Genetic Search in Discrete Spaces
93. ICML 2025Noise-Guided Predicate Representation Extraction and Diffusion-Enhanced Discretization for Scene Graph Generation
94. ICML 2025On Exact Bit-level Reversible Transformers Without Changing Architecture
95. ICML 2025On the Query Complexity of Verifier-Assisted Language Generation
96. ICML 2025One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Framework
97. ICML 2025Origin Identification for Text-Guided Image-to-Image Diffusion Models
98. ICML 2025Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads
99. ICML 2025Overcoming Non-monotonicity in Transducer-based Streaming Generation
100. ICML 2025Overcoming Spurious Solutions in Semi-Dual Neural Optimal Transport: A Smoothing Approach for Learning the Optimal Transport Plan

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。