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 2 / 7 页

51. ICML 2025Continuous Semi-Implicit Models
52. ICML 2025Control and Realism: Best of Both Worlds in Layout-to-Image without Training
53. ICML 2025Controllable Data Generation with Hierarchical Neural Representations
54. ICML 2025Controlled Generation with Equivariant Variational Flow Matching
55. ICML 2025Convergence of Consistency Model with Multistep Sampling under General Data Assumptions
56. ICML 2025CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning
57. ICML 2025D-Fusion: Direct Preference Optimization for Aligning Diffusion Models with Visually Consistent Samples
58. ICML 2025David and Goliath: Small One-step Model Beats Large Diffusion with Score Post-training
59. ICML 2025DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space
60. ICML 2025De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks
61. ICML 2025DeFoG: Discrete Flow Matching for Graph Generation
62. ICML 2025Dequantified Diffusion-Schrödinger Bridge for Density Ratio Estimation
63. ICML 2025Devil is in the Details: Density Guidance for Detail-Aware Generation with Flow Models
64. ICML 2025Diff-MoE: Diffusion Transformer with Time-Aware and Space-Adaptive Experts
65. ICML 2025DiffAdvMAP: Flexible Diffusion-Based Framework for Generating Natural Unrestricted Adversarial Examples
66. ICML 2025Differentiable Solver Search for Fast Diffusion Sampling
67. ICML 2025DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra
68. ICML 2025Diffuse Everything: Multimodal Diffusion Models on Arbitrary State Spaces
69. ICML 2025Diffusion Adversarial Post-Training for One-Step Video Generation
70. ICML 2025Diffusion Counterfactual Generation with Semantic Abduction
71. ICML 2025Diffusion Instruction Tuning
72. ICML 2025Diffusion Models are Secretly Exchangeable: Parallelizing DDPMs via Auto Speculation
73. ICML 2025Diffusion models for Gaussian distributions: Exact solutions and Wasserstein errors
74. ICML 2025Diffusion on Language Model Encodings for Protein Sequence Generation
75. ICML 2025Diffusion Sampling Correction via Approximately 10 Parameters
76. ICML 2025Diffusion-based Adversarial Purification from the Perspective of the Frequency Domain
77. ICML 2025DiMa: Understanding the Hardness of Online Matching Problems via Diffusion Models
78. ICML 2025DIME: Diffusion-Based Maximum Entropy Reinforcement Learning
79. ICML 2025Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator
80. ICML 2025Distillation of Discrete Diffusion through Dimensional Correlations
81. ICML 2025Distributional Diffusion Models with Scoring Rules
82. ICML 2025DiTAR: Diffusion Transformer Autoregressive Modeling for Speech Generation
83. ICML 2025Diversified Flow Matching with Translation Identifiability
84. ICML 2025DMOSpeech: Direct Metric Optimization via Distilled Diffusion Model in Zero-Shot Speech Synthesis
85. ICML 2025Does Generation Require Memorization? Creative Diffusion Models using Ambient Diffusion
86. ICML 2025Domain-Adapted Diffusion Model for PROTAC Linker Design Through the Lens of Density Ratio in Chemical Space
87. ICML 2025DRAG: Data Reconstruction Attack using Guided Diffusion
88. ICML 2025DragLoRA: Online Optimization of LoRA Adapters for Drag-based Image Editing in Diffusion Model
89. ICML 2025DS-VLM: Diffusion Supervision Vision Language Model
90. ICML 2025DSBRouter: End-to-end Global Routing via Diffusion Schr\"{o}dinger Bridge
91. ICML 2025EasyInv: Toward Fast and Better DDIM Inversion
92. ICML 2025EasyRef: Omni-Generalized Group Image Reference for Diffusion Models via Multimodal LLM
93. ICML 2025EcoMapper: Generative Modeling for Climate-Aware Satellite Imagery
94. ICML 2025Editable Noise Map Inversion: Encoding Target-image into Noise For High-Fidelity Image Manipulation
95. ICML 2025Effective and Efficient Masked Image Generation Models
96. ICML 2025Efficient Diffusion Models for Symmetric Manifolds
97. ICML 2025Efficient Fine-Grained Guidance for Diffusion Model Based Symbolic Music Generation
98. ICML 2025Efficient Generative Modeling with Residual Vector Quantization-Based Tokens
99. ICML 2025Efficient Molecular Conformer Generation with SO(3)-Averaged Flow Matching and Reflow
100. ICML 2025Efficient Online Reinforcement Learning for Diffusion Policy

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。