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 349 篇，第 3 / 7 页

101. ICLR 2026Event-T2M: Event-level Conditioning for Complex Text-to-Motion Synthesis
102. ICLR 2026Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models
103. ICLR 2026Evolutionary Caching to Accelerate Your Off-the-Shelf Diffusion Model
104. ICLR 2026Evolving Graph Structured Programs for Circuit Generation with Large Language Models
105. ICLR 2026Exploring Diverse Generation Paths via Inference-time Stiefel Activation Steering
106. ICLR 2026FACM: Flow-Anchored Consistency Models
107. ICLR 2026Factuality Matters: When Image Generation and Editing Meet Structured Visuals
108. ICLR 2026FakeXplain: AI-Generated Image Detection via Human-Aligned Grounded Reasoning
109. ICLR 2026FAST‑DIPS: Adjoint‑Free Analytic Steps and Hard‑Constrained Likelihood Correction for Diffusion‑Prior Inverse Problems
110. ICLR 2026Fastcar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge
111. ICLR 2026Flow Along the $K$-Amplitude for Generative Modeling
112. ICLR 2026Flow Caching for Autoregressive Video Generation
113. ICLR 2026FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing
114. ICLR 2026FlowBind: Efficient Any-to-Any Generation with Bidirectional Flows
115. ICLR 2026FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark
116. ICLR 2026Follow-Your-Preference: Towards Preference-Aligned Image Inpainting
117. ICLR 2026Free Lunch for Stabilizing Rectified Flow Inversion
118. ICLR 2026From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation
119. ICLR 2026From Prediction to Perfection: Introducing Refinement to Autoregressive Image Generation
120. ICLR 2026FS-DFM: Fast and Accurate Long Text Generation with Few-Step Diffusion Language Models
121. ICLR 2026FullPart: Generating each 3D Part at Full Resolution
122. ICLR 2026Functional MRI Time Series Generation via Wavelet-Based Image Transform and Spectral Flow Matching for Brain Disorder Identification
123. ICLR 2026FutureFill: Fast Generation from Convolutional Sequence Models
124. ICLR 2026Generalizable Heuristic Generation Through LLMs with Meta-Optimization
125. ICLR 2026Generate Any Scene: Scene Graph Driven Data Synthesis for Visual Generation Training
126. ICLR 2026Generation then Reconstruction: Accelerating Masked Autoregressive Models via Two-Stage Sampling
127. ICLR 2026Generative Human Geometry Distribution
128. ICLR 2026GeoDiv: Framework for Measuring Geographical Diversity in Text-to-Image Models
129. ICLR 2026Geometric Image Editing via Effects-Sensitive In-Context Inpainting with Diffusion Transformers
130. ICLR 2026GeomMotif: A Benchmark for Arbitrary Geometric Preservation in Protein Generation
131. ICLR 2026Gogo: Group-wise granularity-ordered codec for stable and efficient speech generation
132. ICLR 2026Group Critical-token Policy Optimization for Autoregressive Image Generation
133. ICLR 2026Guidance Matters: Rethinking the Evaluation Pitfall for Text-to-Image Generation
134. ICLR 2026Guidance Watermarking for Diffusion Models
135. ICLR 2026Gumbel Distillation for Parallel Text Generation
136. ICLR 2026HGNet: Scalable Foundation Model for Automated Knowledge Graph Generation from Scientific Literature
137. ICLR 2026HOG-Diff: Higher-Order Guided Diffusion for Graph Generation
138. ICLR 2026Hot PATE: Private Aggregation of Distributions for Diverse Tasks
139. ICLR 2026Hyperspherical Latents Improve Continuous-Token Autoregressive Generation
140. ICLR 2026I-DRUID: Layout to image generation via instance-disentangled representation and unpaired data
141. ICLR 2026IC-Custom: Diverse Image Customization via In-Context Learning
142. ICLR 2026iLLaVA: An Image is Worth Fewer Than 1/3 Input Tokens in Large Multimodal Models
143. ICLR 2026Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning
144. ICLR 2026Image Quality Assessment for Embodied AI
145. ICLR 2026ImageDoctor: Diagnosing Text-to-Image Generation via Grounded Image Reasoning
146. ICLR 2026ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks
147. ICLR 2026ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation
148. ICLR 2026Implicit Inversion turns CLIP into a Decoder
149. ICLR 2026Improving Classifier-Free Guidance in Masked Diffusion: Low-Dim Theoretical Insights with High-Dim Impact
150. ICLR 2026Improving Text-guided CAD Prototyping via Modality-Specific Tokenization

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。