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 607 篇，第 2 / 13 页

51. ICML 2026Dual Optimal Transport for Multi-Concept Composition: Structural Alignment and Texture Injection in Diffusion Models
52. ICML 2026Dual-View Predictive Diffusion: Lightweight Speech Enhancement via Spectrogram-Image Synergy
53. ICML 2026DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion
54. ICML 2026ECA: Efficient Continual Alignment for Open-Ended Image-to-Text Generation
55. ICML 2026Efficient Generative Modeling beyond Memoryless Diffusion via Adjoint Schrödinger Bridge Matching
56. ICML 2026Efficient Learned Image Compression without Entropy Coding
57. ICML 2026Embedding Trust: Semantic Isotropy Predicts Nonfactuality in Long-Form Text Generation
58. ICML 2026End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer
59. ICML 2026Enhancing Train-Free Infinite-Frame Generation for Consistent Long Videos
60. ICML 2026Entropy-Aware Dynamic KV Cache Sparsification for Autoregressive Image Generation and Editing
61. ICML 2026Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical Layout-to-Image Generation
62. ICML 2026Escaping Mode Collapse in LLM Generation via Geometric Regulation
63. ICML 2026Expandable, Compressible, Mineable: Open-World Thermal Infrared Image Restoration
64. ICML 2026Expert-level Leaf Cell Layout Generation via Preference-Optimized LLM
65. ICML 2026Exploring More to Solve More: Boosting Diversity in Text Diffusion Models via Entropy-Based Guidance
66. ICML 2026Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search
67. ICML 2026FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model
68. ICML 2026Finding DoRI: Discovery of Retained Images in Diffusion Models
69. ICML 2026FormAct: Agentic Source Editing for Rich-Format Document Generation
70. ICML 2026FreeText: Training-Free Text Rendering via Attention Localization and Spectral Glyph Injection
71. ICML 2026FunPhase: A Periodic Functional Autoencoder for Motion Generation via Phase Manifolds
72. ICML 2026GADA: Geometry-Aware Deformable Aggregation for Image-Based Gaussian Splatting
73. ICML 2026GASS: Geometry-Aware Spherical Sampling for Disentangled Diversity Enhancement in Text-to-Image Generation
74. ICML 2026Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation
75. ICML 2026GenExam: A Multidisciplinary Text-to-Image Exam
76. ICML 2026GeoLoom: High-quality Geometric Diagram Generation from Textual Input
77. ICML 2026Geometrically Constrained Stenosis Editing in Coronary Angiography via Entropic Optimal Transport
78. ICML 2026Geometry-Aware Image Flow Matching
79. ICML 2026GIFT: Bootstrapping Image-to-CAD Program Synthesis via Geometric Feedback
80. ICML 2026Gradient Preconditioning for Efficient and Reliable Reward-Guided Generation
81. ICML 2026Hard-Constrained Graph Generation with Discrete-Projection Diffusion
82. ICML 2026HIVE-3D: Hierarchical Voxel Enhancement for High-Quality 3D Scene Generation
83. ICML 2026How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance
84. ICML 2026Hyper-ICL: Attention Calibration with Hyperbolic Anchor Distillation for Multimodal In-Context Learning
85. ICML 2026HypoSpace: A Diagnostic Benchmark for Set-Valued Hypothesis Generation under Underdetermination and Sublinear Coverage Bounds
86. ICML 2026Image Restoration via Diffusion Models with Dynamic Resolution
87. ICML 2026Image-to-Brain Signal Generation for Visual Prosthesis with CLIP Guided Multimodal Diffusion Models
88. ICML 2026In-Context Generation with Regional Constraints for Instructional Video Editing
89. ICML 2026InertialAR: Autoregressive 3D Molecule Generation with Inertial Frames
90. ICML 2026Inference-time optimization for experiment-grounded protein ensemble generation
91. ICML 2026InteractScience: Programmatic and Visually-Grounded Evaluation of Interactive Scientific Demonstration Code Generation
92. ICML 2026IQA-Spider: Unifying Multi-Granularity Image Quality Assessment with Reasoning, Grounding and Referring
93. ICML 2026It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks
94. ICML 2026KIStego: Key-Independent Secure Image Distribution via Bipartite Structural Invariants
95. ICML 2026Klein Hyperbolic Metric Learning
96. ICML 2026Krause Synchronization Transformers
97. ICML 2026LabBuilder: Protocol-Grounded 3D Layout Generation for Interactable and Safe Laboratory
98. ICML 2026Language Generation with Feedback: Queries and Mistakes
99. ICML 2026Language Generation with Replay: A Learning-Theoretic View of Model Collapse
100. ICML 2026Latent Forcing: Reordering the Diffusion Trajectory for Pixel-Space Image 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。