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 1,471 篇，第 3 / 30 页

101. CVPR 2024DiffForensics: Leveraging Diffusion Prior to Image Forgery Detection and Localization
102. CVPR 2024DiffHuman: Probabilistic Photorealistic 3D Reconstruction of Humans
103. CVPR 2024DiffLoc: Diffusion Model for Outdoor LiDAR Localization
104. CVPR 2024DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Iterative Diffusion-Based Refinement
105. CVPR 2024DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing
106. CVPR 2024DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction
107. CVPR 2024DiffPerformer: Iterative Learning of Consistent Latent Guidance for Diffusion-based Human Video Generation
108. CVPR 2024DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis
109. CVPR 2024DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction
110. CVPR 2024DiffSCI: Zero-Shot Snapshot Compressive Imaging via Iterative Spectral Diffusion Model
111. CVPR 2024DiffSHEG: A Diffusion-Based Approach for Real-Time Speech-driven Holistic 3D Expression and Gesture Generation
112. CVPR 2024DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis
113. CVPR 2024Diffuse Attend and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion
114. CVPR 2024DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models
115. CVPR 2024Diffusion 3D Features (Diff3F): Decorating Untextured Shapes with Distilled Semantic Features
116. CVPR 2024Diffusion Handles Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D
117. CVPR 2024Diffusion Model Alignment Using Direct Preference Optimization
118. CVPR 2024Diffusion Models Without Attention
119. CVPR 2024Diffusion Reflectance Map: Single-Image Stochastic Inverse Rendering of Illumination and Reflectance
120. CVPR 2024Diffusion Time-step Curriculum for One Image to 3D Generation
121. CVPR 2024Diffusion-based Blind Text Image Super-Resolution
122. CVPR 2024Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation
123. CVPR 2024Diffusion-EDFs: Bi-equivariant Denoising Generative Modeling on SE(3) for Visual Robotic Manipulation
124. CVPR 2024Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous and Instruction-guided Driving
125. CVPR 2024Diffusion-FOF: Single-View Clothed Human Reconstruction via Diffusion-Based Fourier Occupancy Field
126. CVPR 2024DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars
127. CVPR 2024DiffusionGAN3D: Boosting Text-guided 3D Generation and Domain Adaptation by Combining 3D GANs and Diffusion Priors
128. CVPR 2024DiffusionLight: Light Probes for Free by Painting a Chrome Ball
129. CVPR 2024DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data
130. CVPR 2024DiffusionPoser: Real-time Human Motion Reconstruction From Arbitrary Sparse Sensors Using Autoregressive Diffusion
131. CVPR 2024DiffusionRegPose: Enhancing Multi-Person Pose Estimation using a Diffusion-Based End-to-End Regression Approach
132. CVPR 2024DiffusionTrack: Point Set Diffusion Model for Visual Object Tracking
133. CVPR 2024DiG-IN: Diffusion Guidance for Investigating Networks - Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual Explanations
134. CVPR 2024DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data
135. CVPR 2024Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusion
136. CVPR 2024DiSR-NeRF: Diffusion-Guided View-Consistent Super-Resolution NeRF
137. CVPR 2024Distilled Datamodel with Reverse Gradient Matching
138. CVPR 2024Distilling ODE Solvers of Diffusion Models into Smaller Steps
139. CVPR 2024Distraction is All You Need: Memory-Efficient Image Immunization against Diffusion-Based Image Editing
140. CVPR 2024DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
141. CVPR 2024Don't Drop Your Samples! Coherence-Aware Training Benefits Conditional Diffusion
142. CVPR 2024DPHMs: Diffusion Parametric Head Models for Depth-based Tracking
143. CVPR 2024DPMesh: Exploiting Diffusion Prior for Occluded Human Mesh Recovery
144. CVPR 2024Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation
145. CVPR 2024DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing
146. CVPR 2024Draw Step by Step: Reconstructing CAD Construction Sequences from Point Clouds via Multimodal Diffusion.
147. CVPR 2024DREAM: Diffusion Rectification and Estimation-Adaptive Models
148. CVPR 2024DreamAvatar: Text-and-Shape Guided 3D Human Avatar Generation via Diffusion Models
149. CVPR 2024DreamComposer: Controllable 3D Object Generation via Multi-View Conditions
150. CVPR 2024DreamControl: Control-Based Text-to-3D Generation with 3D Self-Prior

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。