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 3 / 13 页

101. ICML 2026Learning Context-Conditioned Predicate Semantics via Prototype Feedback
102. ICML 2026Let EEG Models Learn EEG
103. ICML 2026LineageFlow: Flow Matching for High-Fidelity Family-Aware Protein Sequence Generation
104. ICML 2026LithoGRPO: Fast Inverse Lithography via GRPO Reinforced Flow Matching
105. ICML 2026LiveFigure: Generating Editable Scientific Illustration with VLM Agents
106. ICML 2026LoCoT2V-Bench: Benchmarking Long-Form and Complex Text-to-Video Generation
107. ICML 2026LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation
108. ICML 2026MacroGuide: Topological Guidance for Macrocycle Generation
109. ICML 2026MAMBO-G: Magnitude-Aware Mitigation for Boosted Guidance
110. ICML 2026Mean Flow Distillation: Robust and Stable Distillation for Flow Matching Models
111. ICML 2026Measuring and Mitigating Post-Hoc Rationalization in Reverse Chain-of-Thought Generation
112. ICML 2026Med-SegLens: Latent-Level Model Diffing for Interpretable Medical Image Segmentation
113. ICML 2026MICE-Bench: A Challenging and Comprehensive Benchmark for Multi-Reference Image Creation and Editing
114. ICML 2026MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency
115. ICML 2026MIST: Moment-Aligned Invariant Stability Transform for Robust Flow Matching
116. ICML 2026Mitigating Bias in Locally Constrained Decoding via Tractable Proposals
117. ICML 2026Mitigating Noise-Induced Layout Priors for Object Counting in Diffusion Models
118. ICML 2026MobileFusion: Mobile-Friendly Infrared and Visible Image Fusion via Structural Re-parameterization
119. ICML 2026Mode Seeking meets Mean Seeking for Fast Long Video Generation
120. ICML 2026Motion Attribution for Video Generation
121. ICML 2026Motion-Aware Caching for Efficient Autoregressive Video Generation
122. ICML 2026Multi-marginal temporal Schrödinger Bridge Matching from unpaired data
123. ICML 2026NanoFLUX: Distillation-Driven Compression of Large Text-to-Image Generation Models for Mobile Devices
124. ICML 2026NNiT: Width-Agnostic Neural Network Generation with Structurally Aligned Weight Spaces
125. ICML 2026Noisy-Channel Minimum Bayes Risk Decoding
126. ICML 2026Normalization Equivariance for Arbitrary Backbones, with Application to Image Denoising
127. ICML 2026OcclusionFormer: Arranging Z-Order for Layout-Grounded Image Generation
128. ICML 2026On Stable Long-Form Generation: Benchmarking and Mitigating Length Volatility
129. ICML 2026On the Difficulty of Learning a Meta-network for Training Data Selection
130. ICML 2026One-step Latent-free Image Generation with Pixel Mean Flows
131. ICML 2026One-step Optimal Transport via Regularized Distribution Matching Distillation
132. ICML 2026OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing
133. ICML 2026Optimizing Diversity and Quality through Base-Aligned Model Collaboration
134. ICML 2026Optimizing Few-Step Generation with Adaptive Matching Distillation
135. ICML 2026Orchestrating Spatial Semantics via a Zone-Graph Paradigm for Intricate Indoor Scene Generation
136. ICML 2026OrchJail: Jailbreaking Tool-Calling Text-to-Image Agents by Orchestration-Guided Fuzzing
137. ICML 2026PaperBanana: Automating Academic Illustration for AI Scientists
138. ICML 2026Parameter Manifold Purification
139. ICML 2026Periodic Bayesian Flow Networks with Additive Accuracy
140. ICML 2026PhyScene3D: Physically Consistent 3D Interactive Tabletop Scene Generation
141. ICML 2026Planar Symmetric Pattern Generation
142. ICML 2026Pose-ICL: 3D-Aware In-Context Learning for Pose-Controllable Subject Customization
143. ICML 2026Primal-Spectral Generative Modeling: Fast Analytical Generation via Pseudoinverse Lévy Inversion
144. ICML 2026Q-Tab: Quantized Tabular Data Generator
145. ICML 2026RAIGen: Rare Attribute Identification in Text-to-Image Generative Models
146. ICML 2026Random Selection Reveals Implicit Knowledge Consensus in Code Generation
147. ICML 2026RECOVER: Reliable Detection of Unauthorized Data Usage in Text-to-Image Diffusion Models via Inversion Robustness
148. ICML 2026RelaxFlow: Text-Driven Amodal 3D Generation
149. ICML 2026Responsible Text-to-Image Diffusion: Interpretable and Linearly Controllable Semantics for Fair and Safe Generation
150. ICML 2026Restoring Initial Noise Sensitivity in Text-to-Image Distillation through Geometric Alignment

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。