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 3 / 3 页

101. ICML 2025Position: You Can't Manufacture a NeRF
102. ICML 2025Preference Adaptive and Sequential Text-to-Image Generation
103. ICML 2025Prior Knowledge Guided Neural Architecture Generation
104. ICML 2025Privacy-Shielded Image Compression: Defending Against Exploitation from Vision-Language Pretrained Models
105. ICML 2025Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty
106. ICML 2025Q-VDiT: Towards Accurate Quantization and Distillation of Video-Generation Diffusion Transformers
107. ICML 2025QMamba: On First Exploration of Vision Mamba for Image Quality Assessment
108. ICML 2025QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image Retrieval
109. ICML 2025RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning
110. ICML 2025Reflection-Window Decoding: Text Generation with Selective Refinement
111. ICML 2025REG: Rectified Gradient Guidance for Conditional Diffusion Models
112. ICML 2025Representative Language Generation
113. ICML 2025ReQFlow: Rectified Quaternion Flow for Efficient and High-Quality Protein Backbone Generation
114. ICML 2025Rethinking Score Distilling Sampling for 3D Editing and Generation
115. ICML 2025Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation
116. ICML 2025SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization
117. ICML 2025Scalable Generation of Spatial Transcriptomics from Histology Images via Whole-Slide Flow Matching
118. ICML 2025Selective Prompt Anchoring for Code Generation
119. ICML 2025Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency
120. ICML 2025Simple and Critical Iterative Denoising: A Recasting of Discrete Diffusion in Graph Generation
121. ICML 2025Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation
122. ICML 2025SongGen: A Single Stage Auto-regressive Transformer for Text-to-Song Generation
123. ICML 2025SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference
124. ICML 2025Spherical-Nested Diffusion Model for Panoramic Image Outpainting
125. ICML 2025Staged and Physics-Grounded Learning Framework with Hyperintensity Prior for Pre-Contrast MRI Synthesis
126. ICML 2025Strategic Planning: A Top-Down Approach to Option Generation
127. ICML 2025Structure-Guided Large Language Models for Text-to-SQL Generation
128. ICML 2025Symmetry-Aware GFlowNets
129. ICML 2025Synonymous Variational Inference for Perceptual Image Compression
130. ICML 2025Synthetic Text Generation for Training Large Language Models via Gradient Matching
131. ICML 2025Text-to-CAD Generation Through Infusing Visual Feedback in Large Language Models
132. ICML 2025TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation
133. ICML 2025The Logical Implication Steering Method for Conditional Interventions on Transformer Generation
134. ICML 2025TRACE Back from the Future: A Probabilistic Reasoning Approach to Controllable Language Generation
135. ICML 2025Tractable Transformers for Flexible Conditional Generation
136. ICML 2025Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion
137. ICML 2025UniMC: Taming Diffusion Transformer for Unified Keypoint-Guided Multi-Class Image Generation
138. ICML 2025Upcycling Text-to-Image Diffusion Models for Multi-Task Capabilities
139. ICML 2025Vector Grimoire: Codebook-based Shape Generation under Raster Image Supervision
140. ICML 2025VerbalTS: Generating Time Series from Texts
141. ICML 2025Visual Abstraction: A Plug-and-Play Approach for Text-Visual Retrieval
142. ICML 2025Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models
143. ICML 2025What If We Recaption Billions of Web Images with LLaMA-3?
144. ICML 2025When Model Knowledge meets Diffusion Model: Diffusion-assisted Data-free Image Synthesis with Alignment of Domain and Class
145. ICML 2025Wyckoff Transformer: Generation of Symmetric Crystals
146. ICML 2025You Always Recognize Me (YARM): Robust Texture Synthesis Against Multi-View Corruption
147. ICML 2025ZipAR: Parallel Autoregressive Image Generation through Spatial Locality

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。