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 2,202 篇，第 3 / 45 页

101. NeurIPS 2026Continuous Latent Diffusion Language Model
102. NeurIPS 2026Continuous Personalized Diffusion Model via Spinor-Component Forward Geometry
103. NeurIPS 2026Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
104. NeurIPS 2026Continuously-Augmented Hybrid Masked Diffusion Model for Data Imputation
105. NeurIPS 2026ControlFlow3D: Distilling Multi-View Knowledge into Latent Flow Matching for Point Cloud Upsampling
106. NeurIPS 2026Coreset-Induced Conditional Velocity Flow Matching
107. NeurIPS 2026Corrective Diffusion Language Models
108. NeurIPS 2026Counterfactual Explanations for Time-Series Classification via Constrained Flow Matching
109. NeurIPS 2026Coupled Guidance for Flow Matching
110. NeurIPS 2026Cross-Cell-Line Perturbation Prediction Needs Controls
111. NeurIPS 2026CSFlow: Aligning Flow Matching with Human Contrast Sensitivity
112. NeurIPS 2026Cyclic Denoising Reveals Ultrastable Memories in Diffusion Models
113. NeurIPS 2026Cylindrical Geodesic Flow Matching for Quasiperiodic Physiological Signal Transformation
114. NeurIPS 2026D-DOIT: Training-free Adaptation of Discrete Diffusion via Doob's h-Transform
115. NeurIPS 2026D-OPSD: On-Policy Self-Distillation for Continuously Tuning Step-Distilled Diffusion Models
116. NeurIPS 2026DAWN: Dependency-Aware Fast Inference for Diffusion LLMs
117. NeurIPS 2026DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion Convergence
118. NeurIPS 2026Debiased Counterfactual Generation via Flow Matching from Observations
119. NeurIPS 2026Debiased DPO for Diffusion Models
120. NeurIPS 2026Decoupled Safety Control: A Safety-Control Algorithm for Training-Free Safety Guidance
121. NeurIPS 2026Decoupling Action from Egocentric Observation for World Simulation
122. NeurIPS 2026DeFlowCritic: Dense Latent Reward Alignment for Text-to-Image Flow Matching Models
123. NeurIPS 2026Denoising Time Matters: Diverse Generation in Diffusion Language Models
124. NeurIPS 2026Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models
125. NeurIPS 2026Designing Reinforcement Learning for Diffusion Models: A Unified Path-Space View
126. NeurIPS 2026DexOPE: 6D Object Pose Estimation in Dexterous Manipulation
127. NeurIPS 2026Diff-Aid: Inference-time Adaptive Interaction Denoising for Rectified Text-to-Image Generation
128. NeurIPS 2026DiffATS: Diffusion in Aligned Tensor Space
129. NeurIPS 2026DiffCool: Label-Free Synthesis of Chip-Tailored Heat Sinks via Thermal-Aware Diffusion
130. NeurIPS 2026Differencing the Diffusion Trajectory toward Uncertain Components for Time Series Forecasting
131. NeurIPS 2026Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models
132. NeurIPS 2026DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting
133. NeurIPS 2026DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing
134. NeurIPS 2026DiffRisk: Diffusion Representation Learning with Informative Missingness for Health Risk Prediction
135. NeurIPS 2026Diffusion fine-tuning with Rewarded Moment Matching Distillation
136. NeurIPS 2026Diffusion Language Models Can Approximate Optimal Infilling Lengths Implicitly
137. NeurIPS 2026Diffusion Meta-Prompting and Steering for Generalizable Foundation Model Adaptation
138. NeurIPS 2026Diffusion Model's Generalization Can Be Characterized by Inductive Biases toward a Data-Dependent Ridge Manifold
139. NeurIPS 2026Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
140. NeurIPS 2026Diffusion Models without Classifier-free Guidance
141. NeurIPS 2026Diffusion Path Samplers via Sequential Monte Carlo
142. NeurIPS 2026Diffusion Transformers with Residual Adaptive Layer Normalization
143. NeurIPS 2026Diffusion-State Policy Optimization for Masked Diffusion Language Models
144. NeurIPS 2026Diffusion-Time Concept Manifolds: Sparse Autoencoder Groups for Interpreting Denoising Language Models
145. NeurIPS 2026Diffusion-warm sampling of the XY model enables fast thermalization at scale
146. NeurIPS 2026DiLaDiff: Distilled Latent-augmented Diffusion for Language Modeling
147. NeurIPS 2026DiPhon: Diffusion on Graphons for Scalable Graph Generation
148. NeurIPS 2026Direct Conditioning of Audio Diffusion Transformers on fMRI Reveals Cortical Contributions to Sound Reconstruction
149. NeurIPS 2026Direct Product Flow Matching: Decoupling Radial and Angular Dynamics for Few-Shot Adaptation
150. NeurIPS 2026DiRecT: Safe Diffusion-Based Planning via Receding-Horizon Denoising

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。