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 346 篇，第 3 / 7 页

101. ICML 2025Efficiently Access Diffusion Fisher: Within the Outer Product Span Space
102. ICML 2025Elucidating Flow Matching ODE Dynamics via Data Geometry and Denoisers
103. ICML 2025Emotional Face-to-Speech
104. ICML 2025Energy-Based Flow Matching for Generating 3D Molecular Structure
105. ICML 2025Ensemble Distribution Distillation via Flow Matching
106. ICML 2025Epsilon-VAE: Denoising as Visual Decoding
107. ICML 2025EraseAnything: Enabling Concept Erasure in Rectified Flow Transformers
108. ICML 2025Ergodic Generative Flows
109. ICML 2025ETTA: Elucidating the Design Space of Text-to-Audio Models
110. ICML 2025Event-Customized Image Generation
111. ICML 2025Expert Race: A Flexible Routing Strategy for Scaling Diffusion Transformer with Mixture of Experts
112. ICML 2025Exponential Family Variational Flow Matching for Tabular Data Generation
113. ICML 2025Expressive Score-Based Priors for Distribution Matching with Geometry-Preserving Regularization
114. ICML 2025Falcon: Fast Visuomotor Policies via Partial Denoising
115. ICML 2025Fast Video Generation with Sliding Tile Attention
116. ICML 2025Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization
117. ICML 2025Feynman-Kac Correctors in Diffusion: Annealing, Guidance, and Product of Experts
118. ICML 2025Finite-Time Analysis of Discrete-Time Stochastic Interpolants
119. ICML 2025Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation
120. ICML 2025FlexControl: Computation-Aware Conditional Control with Differentiable Router for Text-to-Image Generation
121. ICML 2025Flexibility-conditioned protein structure design with flow matching
122. ICML 2025FlexiClip: Locality-Preserving Free-Form Character Animation
123. ICML 2025Flow Matching for Denoised Social Recommendation
124. ICML 2025Flow Matching for Few-Trial Neural Adaptation with Stable Latent Dynamics
125. ICML 2025Flow Q-Learning
126. ICML 2025FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching
127. ICML 2025FlowDrag: 3D-aware Drag-based Image Editing with Mesh-guided Deformation Vector Flow Fields
128. ICML 2025FrameBridge: Improving Image-to-Video Generation with Bridge Models
129. ICML 2025From Uncertain to Safe: Conformal Adaptation of Diffusion Models for Safe PDE Control
130. ICML 2025Gaussian Mixture Flow Matching Models
131. ICML 2025GaussMarker: Robust Dual-Domain Watermark for Diffusion Models
132. ICML 2025Generalized Interpolating Discrete Diffusion
133. ICML 2025Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction
134. ICML 2025Generative Data Mining with Longtail-Guided Diffusion
135. ICML 2025Generative Human Trajectory Recovery via Embedding-Space Conditional Diffusion
136. ICML 2025Generative Intervention Models for Causal Perturbation Modeling
137. ICML 2025GenMol: A Drug Discovery Generalist with Discrete Diffusion
138. ICML 2025Geometric Generative Modeling with Noise-Conditioned Graph Networks
139. ICML 2025Geometric Representation Condition Improves Equivariant Molecule Generation
140. ICML 2025GMAIL: Generative Modality Alignment for generated Image Learning
141. ICML 2025Graph Diffusion for Robust Multi-Agent Coordination
142. ICML 2025Habitizing Diffusion Planning for Efficient and Effective Decision Making
143. ICML 2025HarmoniCa: Harmonizing Training and Inference for Better Feature Caching in Diffusion Transformer Acceleration
144. ICML 2025Harmonizing Geometry and Uncertainty: Diffusion with Hyperspheres
145. ICML 2025Hessian Geometry of Latent Space in Generative Models
146. ICML 2025Hierarchical Reinforcement Learning with Uncertainty-Guided Diffusional Subgoals
147. ICML 2025History-Guided Video Diffusion
148. ICML 2025How Compositional Generalization and Creativity Improve as Diffusion Models are Trained
149. ICML 2025How Distributed Collaboration Influences the Diffusion Model Training? A Theoretical Perspective
150. ICML 2025How Far Is Video Generation from World Model: A Physical Law Perspective

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。