扩散模型论文趋势 2023–2026

主要结论

• 扩散模型论文从 2023 年的 660 篇增长到 2026 年的 2,691 篇，三年间扩大到约 4.1 倍。
• NeurIPS 是发扩散模型论文最多的会议，2023–2026 年共 2,202 篇，占四个会议总量的 32%。
• 交叉方向里涨得最快的是应用 · chemistry physics and earth sciences：同时属于两个主题的论文从 2023 年的 14 篇增至 2026 年的 163 篇。
• 在「深度学习」的 11 个主题里，它的 2026 年论文数排第 1；同组增长最快的深度学习 · foundation models是 2.5 倍，扩散模型是 4.1 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$\mathbf{D^{3}S^{2}}$: Diffusion-Guided Dataset Distillation for Semantic Segmentation
• ICML 2026“Do Diffusion Models Dream of Electric Planes?” Discrete and Continuous Simulation-Based Inference for Aircraft Design
• ICLR 2026$\alpha$-DPO: Robust Preference Alignment for Diffusion Models via $\alpha$ Divergence
• CVPR 20262ndMatch Finetuning Pruned Diffusion Models via Second-Order Jacobian Matching
• NeurIPS 2025$\text{S}^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation
• ICML 2025A First-order Generative Bilevel Optimization Framework for Diffusion Models
• ICLR 2025$\text{I}^2\text{AM}$: Interpreting Image-to-Image Latent Diffusion Models via Bi-Attribution Maps
• CVPR 20253DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement
• NeurIPS 2024$\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation
• ICML 2024A Dense Reward View on Aligning Text-to-Image Diffusion with Preference
• ICLR 2024$\infty$-Diff: Infinite Resolution Diffusion with Subsampled Mollified States
• CVPR 2024D^4: Dataset Distillation via Disentangled Diffusion Model
• NeurIPS 20233D molecule generation by denoising voxel grids
• ICML 2023A Critical Revisit of Adversarial Robustness in 3D Point Cloud Recognition with Diffusion-Driven Purification
• ICLR 2023(Certified!!) Adversarial Robustness for Free!
• CVPR 20233D Neural Field Generation Using Triplane Diffusion
• NeurIPS 2026$\text{PartConcepts}$: A Unified Mechanism for Fine-Grained Part Localization and Generation
• ICML 2026$\sigma$: Sigmoid Modulation for Ultra High Resolution Diffusion
• ICLR 2026$\textit{MADFormer}$: Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation
• CVPR 20263D-LATTE Latent Space 3D Editing from Textual Instructions

全部扩散模型论文

共 138 篇，第 3 / 3 页

101. CVPR 2023PyramidFlow: High-Resolution Defect Contrastive Localization Using Pyramid Normalizing Flow
102. CVPR 2023Regularized Vector Quantization for Tokenized Image Synthesis
103. CVPR 2023RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation
104. CVPR 2023Rethinking Optical Flow From Geometric Matching Consistent Perspective
105. CVPR 2023RGBD2: Generative Scene Synthesis via Incremental View Inpainting Using RGBD Diffusion Models
106. CVPR 2023RODIN: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion
107. CVPR 2023Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models
108. CVPR 2023Scaling Up GANs for Text-to-Image Synthesis
109. CVPR 2023SceneComposer: Any-Level Semantic Image Synthesis
110. CVPR 2023Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generation
111. CVPR 2023SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation
112. CVPR 2023Seeing Beyond the Brain: Conditional Diffusion Model With Sparse Masked Modeling for Vision Decoding
113. CVPR 2023Self-Guided Diffusion Models
114. CVPR 2023Semantic-Conditional Diffusion Networks for Image Captioning
115. CVPR 2023ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal
116. CVPR 2023Shape-Aware Text-Driven Layered Video Editing
117. CVPR 2023Shifted Diffusion for Text-to-Image Generation
118. CVPR 2023SINE: SINgle Image Editing With Text-to-Image Diffusion Models
119. CVPR 2023SmartBrush: Text and Shape Guided Object Inpainting With Diffusion Model
120. CVPR 2023Solving 3D Inverse Problems Using Pre-Trained 2D Diffusion Models
121. CVPR 2023SparseFusion: Distilling View-Conditioned Diffusion for 3D Reconstruction
122. CVPR 2023SpaText: Spatio-Textual Representation for Controllable Image Generation
123. CVPR 2023Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models To Learn Any Unseen Style
124. CVPR 2023Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation
125. CVPR 2023Towards Practical Plug-and-Play Diffusion Models
126. CVPR 2023Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion
127. CVPR 2023TransFlow: Transformer As Flow Learner
128. CVPR 2023TrojDiff: Trojan Attacks on Diffusion Models With Diverse Targets
129. CVPR 2023TryOnDiffusion: A Tale of Two UNets
130. CVPR 2023Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models
131. CVPR 2023Understanding Deep Generative Models With Generalized Empirical Likelihoods
132. CVPR 2023Unifying Layout Generation With a Decoupled Diffusion Model
133. CVPR 2023Unite and Conquer: Plug & Play Multi-Modal Synthesis Using Diffusion Models
134. CVPR 2023VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models
135. CVPR 2023Video Probabilistic Diffusion Models in Projected Latent Space
136. CVPR 2023VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation
137. CVPR 2023Wavelet Diffusion Models Are Fast and Scalable Image Generators
138. CVPR 2023Zero-Shot Generative Model Adaptation via Image-Specific Prompt Learning

常见问题

2023–2026 年四大会议一共有多少篇扩散模型论文？

共 6,900 篇，按年份分别是 2023 年 660 篇、2024 年 1,471 篇、2025 年 2,078 篇、2026 年 2,691 篇。

NeurIPS 2026 有多少篇扩散模型论文？

NeurIPS 2026 有 661 篇扩散模型论文，上一届是 694 篇。

ICLR 2026 有多少篇扩散模型论文？

ICLR 2026 有 694 篇扩散模型论文，上一届是 487 篇。

ICML 2026 有多少篇扩散模型论文？

ICML 2026 有 728 篇扩散模型论文，上一届是 346 篇。

CVPR 2026 有多少篇扩散模型论文？

CVPR 2026 有 608 篇扩散模型论文，上一届是 551 篇。

哪个会议的扩散模型论文最多？

NeurIPS，2023–2026 年共 2,202 篇。