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 195 篇，第 2 / 4 页

51. ICML 2024Diffuse, Sample, Project: Plug-And-Play Controllable Graph Generation
52. ICML 2024Diffusion Language Models Are Versatile Protein Learners
53. ICML 2024Diffusion Model-Augmented Behavioral Cloning
54. ICML 2024Diffusion Models Demand Contrastive Guidance for Adversarial Purification to Advance
55. ICML 2024Diffusion Models Encode the Intrinsic Dimension of Data Manifolds
56. ICML 2024Diffusion Posterior Sampling is Computationally Intractable
57. ICML 2024Diffusion Rejection Sampling
58. ICML 2024Diffusion Tempering Improves Parameter Estimation with Probabilistic Integrators for Ordinary Differential Equations
59. ICML 2024Diffusion-based Missing-view Generation With the Application on Incomplete Multi-view Clustering
60. ICML 2024Diffusive Gibbs Sampling
61. ICML 2024DiracDiffusion: Denoising and Incremental Reconstruction with Assured Data-Consistency
62. ICML 2024Directly Denoising Diffusion Models
63. ICML 2024Dirichlet Flow Matching with Applications to DNA Sequence Design
64. ICML 2024DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents
65. ICML 2024Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution
66. ICML 2024Disguised Copyright Infringement of Latent Diffusion Models
67. ICML 2024DITTO: Diffusion Inference-Time T-Optimization for Music Generation
68. ICML 2024Don't be so Negative! Score-based Generative Modeling with Oracle-assisted Guidance
69. ICML 2024DRCT: Diffusion Reconstruction Contrastive Training towards Universal Detection of Diffusion Generated Images
70. ICML 2024E$^2$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation
71. ICML 2024Easing Concept Bleeding in Diffusion via Entity Localization and Anchoring
72. ICML 2024Editing Partially Observable Networks via Graph Diffusion Models
73. ICML 2024Efficient Denoising Diffusion via Probabilistic Masking
74. ICML 2024Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning
75. ICML 2024Equivariant Diffusion for Crystal Structure Prediction
76. ICML 2024Fast Timing-Conditioned Latent Audio Diffusion
77. ICML 2024Feedback Efficient Online Fine-Tuning of Diffusion Models
78. ICML 2024FiT: Flexible Vision Transformer for Diffusion Model
79. ICML 2024Floating Anchor Diffusion Model for Multi-motif Scaffolding
80. ICML 2024FlowMM: Generating Materials with Riemannian Flow Matching
81. ICML 2024FRAG: Frequency Adapting Group for Diffusion Video Editing
82. ICML 2024From Fourier to Neural ODEs: Flow Matching for Modeling Complex Systems
83. ICML 2024Full-Atom Peptide Design based on Multi-modal Flow Matching
84. ICML 2024Generative Conditional Distributions by Neural (Entropic) Optimal Transport
85. ICML 2024Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design
86. ICML 2024Generative Marginalization Models
87. ICML 2024Generative Modeling on Manifolds Through Mixture of Riemannian Diffusion Processes
88. ICML 2024GiLOT: Interpreting Generative Language Models via Optimal Transport
89. ICML 2024Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations
90. ICML 2024Graph Adversarial Diffusion Convolution
91. ICML 2024Graph Generation with Diffusion Mixture
92. ICML 2024Guidance with Spherical Gaussian Constraint for Conditional Diffusion
93. ICML 2024Harmonic Self-Conditioned Flow Matching for joint Multi-Ligand Docking and Binding Site Design
94. ICML 2024How to Trace Latent Generative Model Generated Images without Artificial Watermark?
95. ICML 2024Hyperbolic Geometric Latent Diffusion Model for Graph Generation
96. ICML 2024Image Restoration Through Generalized Ornstein-Uhlenbeck Bridge
97. ICML 2024Imitation Learning from Purified Demonstrations
98. ICML 2024Improving Adversarial Energy-Based Model via Diffusion Process
99. ICML 2024Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariance
100. ICML 2024Interacting Diffusion Processes for Event Sequence Forecasting

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。