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 86 篇，第 2 / 2 页

51. ICLR 2023Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules
52. ICLR 2023Imitating Human Behaviour with Diffusion Models
53. ICLR 2023Information-Theoretic Diffusion
54. ICLR 2023Is Conditional Generative Modeling all you need for Decision Making?
55. ICLR 2023kNN-Diffusion: Image Generation via Large-Scale Retrieval
56. ICLR 2023Learning Diffusion Bridges on Constrained Domains
57. ICLR 2023Learning to Estimate Single-View Volumetric Flow Motions without 3D Supervision
58. ICLR 2023Markup-to-Image Diffusion Models with Scheduled Sampling
59. ICLR 2023MARS: Meta-learning as Score Matching in the Function Space
60. ICLR 2023MeshDiffusion: Score-based Generative 3D Mesh Modeling
61. ICLR 2023Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching
62. ICLR 2023Neural Lagrangian Schr\"{o}dinger Bridge: Diffusion Modeling for Population Dynamics
63. ICLR 2023Novel View Synthesis with Diffusion Models
64. ICLR 2023Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling
65. ICLR 2023Particle-based Variational Inference with Preconditioned Functional Gradient Flow
66. ICLR 2023Prompt-to-Prompt Image Editing with Cross-Attention Control
67. ICLR 2023Protein Sequence and Structure Co-Design with Equivariant Translation
68. ICLR 2023Pseudoinverse-Guided Diffusion Models for Inverse Problems
69. ICLR 2023Quantized Compressed Sensing with Score-Based Generative Models
70. ICLR 2023Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Images
71. ICLR 2023Re-Imagen: Retrieval-Augmented Text-to-Image Generator
72. ICLR 2023Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions
73. ICLR 2023Score-based Continuous-time Discrete Diffusion Models
74. ICLR 2023Semi-Implicit Variational Inference via Score Matching
75. ICLR 2023SketchKnitter: Vectorized Sketch Generation with Diffusion Models
76. ICLR 2023Stable Target Field for Reduced Variance Score Estimation in Diffusion Models
77. ICLR 2023STaSy: Score-based Tabular data Synthesis
78. ICLR 2023Statistical Efficiency of Score Matching: The View from Isoperimetry
79. ICLR 2023Stochastic Multi-Person 3D Motion Forecasting
80. ICLR 2023Structure by Architecture: Structured Representations without Regularization
81. ICLR 2023Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis
82. ICLR 2023Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders
83. ICLR 2023Understanding DDPM Latent Codes Through Optimal Transport
84. ICLR 2023Unified Discrete Diffusion for Simultaneous Vision-Language Generation
85. ICLR 2023Where to Diffuse, How to Diffuse, and How to Get Back: Automated Learning for Multivariate Diffusions
86. ICLR 2023Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model

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。