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 728 篇，第 3 / 15 页

101. ICML 2026Continuous Diffusion Models Can Obey Formal Syntax
102. ICML 2026Contractive Anchor Resolvent Diffusion for Incomplete Multi-View Clustering
103. ICML 2026Contrastive Diffusion Alignment: Learning Structured Latents for Controllable Generation
104. ICML 2026Contrastive Flow Map Matching
105. ICML 2026ContrastiveCFG: Guiding Diffusion Sampling by Contrasting Positive and Negative Concepts
106. ICML 2026Control Consistency Losses for Diffusion Bridges
107. ICML 2026CORE: Context-Robust Remasking for Diffusion Language Models
108. ICML 2026Corrected Samplers for Discrete Flow Models
109. ICML 2026CountsDiff: A diffusion model on the natural numbers for generation and imputation of count-based data
110. ICML 2026CRAG: Can 3D Generative Models Help 3D Assembly?
111. ICML 2026Cross-Chirality Generalization by Axial Vectors for Hetero-Chiral Protein-Peptide Interaction Design
112. ICML 2026CURE: Context-driven Diffusion with Progressive Expansion for Single Domain Generalization in Time Series Classification
113. ICML 2026d2: Improving Reasoning in Diffusion Language Models via Trajectory Likelihood Estimation
114. ICML 2026d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation
115. ICML 2026DADP: Domain Adaptive Diffusion Policy
116. ICML 2026DAPD: Dependency-Aware Parallel Decoding via Attention for Diffusion LLMs
117. ICML 2026DDIM Inversion as a Perturbation Amplifier: Breaking Mimicry Protection via Reconstruction Error Minimization
118. ICML 2026DeCoDe: Decoupling Binding Position and Molecular Conformation in 3D Ligand Diffusion for Structure-Based Drug Design
119. ICML 2026Decomposing Out-of-Distribution Error in Conditional Flow Matching via Wasserstein Geometry
120. ICML 2026Deep Flow Networks
121. ICML 2026Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression
122. ICML 2026Deep Trajectory Supervision: Deep Supervision Strikes Back
123. ICML 2026Denoising without Diffusion: Fixed-Noise Denoiser Anomaly Detection in Tabular Data
124. ICML 2026Depth-Progressive Monotonic Learning without Global Backpropagation
125. ICML 2026DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?
126. ICML 2026DFlash: Block Diffusion for Flash Speculative Decoding
127. ICML 2026DFSAttn: Dynamic Fine-grained Sparse Attention for Efficient Video Generation
128. ICML 2026dgMARK: Decoding-Guided Watermarking for Diffusion Language Models
129. ICML 2026DGS-Net: Distillation-Guided Gradient Surgery for CLIP Fine-Tuning in AI-Generated Image Detection
130. ICML 2026Di-BiLPS: Denoising induced Bidirectional Latent-PDE-Solver under Sparse Observations
131. ICML 2026Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformers
132. ICML 2026Diamond Maps: Efficient Reward Alignment via Stochastic Flow Maps
133. ICML 2026DiasR: Dual-Modal Identity-Anchored Sparse Routing for Efficient Multi-Subject Video Generation
134. ICML 2026DiFA: Inference-Time Forward-Process Alignment for Diffusion Models
135. ICML 2026Diff-MN: Diffusion Parameterized MoE-NCDE for Continuous Time Series Generation with Irregular Observations
136. ICML 2026DiffCrossGait: Trajectory-Level Alignment for 2D-3D Cross-Modal Gait Recognition via Latent Diffusion
137. ICML 2026DiffStyle3D: Consistent 3D Gaussian Stylization via Attention Optimization
138. ICML 2026DiffThinker: Towards Generative Multimodal Reasoning with Diffusion Models
139. ICML 2026DiffuMamba: High-Throughput Diffusion LMs with Mamba Backbone
140. ICML 2026DiffuReason: Enhancing Reasoning Ability for Diffusion Language Models via Monte Carlo Tree Search
141. ICML 2026Diffuse to Detect: Bi-Level Sample Rebalancing with Pseudo-Label Diffusion for Point-Supervised Infrared Small-Target Detection
142. ICML 2026Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policies
143. ICML 2026Diffusion Bridge or Flow Matching? A Unifying Framework and Comparative Analysis
144. ICML 2026Diffusion Controller: Framework, Algorithms and Parameterization
145. ICML 2026Diffusion Differentiable Resampling
146. ICML 2026Diffusion Flow Matching: Dimension-Improved KL Bounds and Wasserstein Guarantees
147. ICML 2026Diffusion Language Model Parallel Decoding via Product-of-Experts Bridge
148. ICML 2026Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal Distributions
149. ICML 2026Diffusion Models Preferentially Memorize Prototypical Examples or: Why Does My Diffusion Model Love Slop?
150. ICML 2026Diffusion-based learning framework for Constrained Nonconvex Optimization with Weighted Bootstrapped Refinement

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。