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 138 篇，第 2 / 3 页

51. CVPR 2023GANHead: Towards Generative Animatable Neural Head Avatars
52. CVPR 2023Generative Diffusion Prior for Unified Image Restoration and Enhancement
53. CVPR 2023GLIGEN: Open-Set Grounded Text-to-Image Generation
54. CVPR 2023Guided Depth Super-Resolution by Deep Anisotropic Diffusion
55. CVPR 2023Heat Diffusion Based Multi-Scale and Geometric Structure-Aware Transformer for Mesh Segmentation
56. CVPR 2023Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision
57. CVPR 2023High-Fidelity Guided Image Synthesis With Latent Diffusion Models
58. CVPR 2023High-Frequency Stereo Matching Network
59. CVPR 2023High-Resolution Image Reconstruction With Latent Diffusion Models From Human Brain Activity
60. CVPR 2023HOLODIFFUSION: Training a 3D Diffusion Model Using 2D Images
61. CVPR 2023HouseDiffusion: Vector Floorplan Generation via a Diffusion Model With Discrete and Continuous Denoising
62. CVPR 2023How to Backdoor Diffusion Models?
63. CVPR 2023Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting
64. CVPR 2023Imagic: Text-Based Real Image Editing With Diffusion Models
65. CVPR 2023Implicit Diffusion Models for Continuous Super-Resolution
66. CVPR 2023InstructPix2Pix: Learning To Follow Image Editing Instructions
67. CVPR 2023Inversion-Based Style Transfer With Diffusion Models
68. CVPR 2023Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures
69. CVPR 2023LayoutDiffusion: Controllable Diffusion Model for Layout-to-Image Generation
70. CVPR 2023LayoutDM: Discrete Diffusion Model for Controllable Layout Generation
71. CVPR 2023LayoutDM: Transformer-Based Diffusion Model for Layout Generation
72. CVPR 2023Leapfrog Diffusion Model for Stochastic Trajectory Prediction
73. CVPR 2023Learning Locally Editable Virtual Humans
74. CVPR 2023Learning Optical Expansion From Scale Matching
75. CVPR 2023LEGO-Net: Learning Regular Rearrangements of Objects in Rooms
76. CVPR 2023Lookahead Diffusion Probabilistic Models for Refining Mean Estimation
77. CVPR 2023Magic3D: High-Resolution Text-to-3D Content Creation
78. CVPR 2023MAGVIT: Masked Generative Video Transformer
79. CVPR 2023Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation
80. CVPR 2023MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation
81. CVPR 2023Mofusion: A Framework for Denoising-Diffusion-Based Motion Synthesis
82. CVPR 2023Multi-Concept Customization of Text-to-Image Diffusion
83. CVPR 2023NeRDi: Single-View NeRF Synthesis With Language-Guided Diffusion As General Image Priors
84. CVPR 2023NeuralField-LDM: Scene Generation With Hierarchical Latent Diffusion Models
85. CVPR 2023NeuralLift-360: Lifting an In-the-Wild 2D Photo to a 3D Object With 360deg Views
86. CVPR 2023NULL-Text Inversion for Editing Real Images Using Guided Diffusion Models
87. CVPR 2023ObjectStitch: Object Compositing With Diffusion Model
88. CVPR 2023On Distillation of Guided Diffusion Models
89. CVPR 2023Open-Vocabulary Panoptic Segmentation With Text-to-Image Diffusion Models
90. CVPR 2023OVTrack: Open-Vocabulary Multiple Object Tracking
91. CVPR 2023Paint by Example: Exemplar-Based Image Editing With Diffusion Models
92. CVPR 2023Parallel Diffusion Models of Operator and Image for Blind Inverse Problems
93. CVPR 2023PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction
94. CVPR 2023PDPP:Projected Diffusion for Procedure Planning in Instructional Videos
95. CVPR 2023Person Image Synthesis via Denoising Diffusion Model
96. CVPR 2023Physics-Driven Diffusion Models for Impact Sound Synthesis From Videos
97. CVPR 2023Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation
98. CVPR 2023PMatch: Paired Masked Image Modeling for Dense Geometric Matching
99. CVPR 2023Post-Training Quantization on Diffusion Models
100. CVPR 2023Putting People in Their Place: Affordance-Aware Human Insertion Into Scenes

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。