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 2,078 篇，第 2 / 42 页

51. CVPR 2025BlobGEN-Vid: Compositional Text-to-Video Generation with Blob Video Representations
52. CVPR 2025BlockDance: Reuse Structurally Similar Spatio-Temporal Features to Accelerate Diffusion Transformers
53. CVPR 2025Blood Flow Speed Estimation with Optical Coherence Tomography Angiography Images
54. CVPR 2025BooW-VTON: Boosting In-the-Wild Virtual Try-On via Mask-Free Pseudo Data Training
55. CVPR 2025BrepGiff: Lightweight Generation of Complex B-rep with 3D GAT Diffusion
56. CVPR 2025Bridging the Gap between Gaussian Diffusion Models and Universal Quantization for Image Compression
57. CVPR 2025BWFormer: Building Wireframe Reconstruction from Airborne LiDAR Point Cloud with Transformer
58. CVPR 2025CacheQuant: Comprehensively Accelerated Diffusion Models
59. CVPR 2025CADDreamer: CAD Object Generation from Single-view Images
60. CVPR 2025Calibrated Multi-Preference Optimization for Aligning Diffusion Models
61. CVPR 2025CamFreeDiff: Camera-free Image to Panorama Generation with Diffusion Model
62. CVPR 2025CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models
63. CVPR 2025CaricatureBooth: Data-Free Interactive Caricature Generation in a Photo Booth
64. CVPR 2025CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models
65. CVPR 2025Causal Composition Diffusion Model for Closed-loop Traffic Generation
66. CVPR 2025CDI: Copyrighted Data Identification in Diffusion Models
67. CVPR 2025CH3Depth: Efficient and Flexible Depth Foundation Model with Flow Matching
68. CVPR 2025Channel-wise Noise Scheduled Diffusion for Inverse Rendering in Indoor Scenes
69. CVPR 2025Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models
70. CVPR 2025Classifier-Free Guidance Inside the Attraction Basin May Cause Memorization
71. CVPR 2025CleanDIFT: Diffusion Features without Noise
72. CVPR 2025Color Alignment in Diffusion
73. CVPR 2025Community Forensics: Using Thousands of Generators to Train Fake Image Detectors
74. CVPR 2025Compass Control: Multi Object Orientation Control for Text-to-Image Generation
75. CVPR 2025Composing Parts for Expressive Object Generation
76. CVPR 2025Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization
77. CVPR 2025Concept Lancet: Image Editing with Compositional Representation Transplant
78. CVPR 2025Concept Replacer: Replacing Sensitive Concepts in Diffusion Models via Precision Localization
79. CVPR 2025Conditional Balance: Improving Multi-Conditioning Trade-Offs in Image Generation
80. CVPR 2025Consistent and Controllable Image Animation with Motion Diffusion Models
81. CVPR 2025Continuous Locomotive Crowd Behavior Generation
82. CVPR 2025Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions
83. CVPR 2025Controllable Human Image Generation with Personalized Multi-Garments
84. CVPR 2025Correcting Deviations from Normality: A Reformulated Diffusion Model for Multi-Class Unsupervised Anomaly Detection
85. CVPR 2025CraftsMan3D: High-fidelity Mesh Generation with 3D Native Diffusion and Interactive Geometry Refiner
86. CVPR 2025CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D Diffusion
87. CVPR 2025Customized Condition Controllable Generation for Video Soundtrack
88. CVPR 2025D^2iT: Dynamic Diffusion Transformer for Accurate Image Generation
89. CVPR 2025DaCapo: Score Distillation as Stacked Bridge for Fast and High-quality 3D Editing
90. CVPR 2025DAMM-Diffusion: Learning Divergence-Aware Multi-Modal Diffusion Model for Nanoparticles Distribution Prediction
91. CVPR 2025Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusion
92. CVPR 2025Data-Free Group-Wise Fully Quantized Winograd Convolution via Learnable Scales
93. CVPR 2025Decentralized Diffusion Models
94. CVPR 2025DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single Image
95. CVPR 2025Decompositional Neural Scene Reconstruction with Generative Diffusion Prior
96. CVPR 2025Decouple Distortion from Perception: Region Adaptive Diffusion for Extreme-low Bitrate Perception Image Compression
97. CVPR 2025Decouple-Then-Merge: Finetune Diffusion Models as Multi-Task Learning
98. CVPR 2025Decoupling Training-Free Guided Diffusion by ADMM
99. CVPR 2025DefectFill: Realistic Defect Generation with Inpainting Diffusion Model for Visual Inspection
100. CVPR 2025Denoising Functional Maps: Diffusion Models for Shape Correspondence

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。