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 487 篇，第 2 / 10 页

51. ICLR 2025CHAMP: Conformalized 3D Human Multi-Hypothesis Pose Estimators
52. ICLR 2025Chemistry-Inspired Diffusion with Non-Differentiable Guidance
53. ICLR 2025CL-DiffPhyCon: Closed-loop Diffusion Control of Complex Physical Systems
54. ICLR 2025ClassDiffusion: More Aligned Personalization Tuning with Explicit Class Guidance
55. ICLR 2025CLIPDrag: Combining Text-based and Drag-based Instructions for Image Editing
56. ICLR 2025CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control
57. ICLR 2025CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
58. ICLR 2025CoInD: Enabling Logical Compositions in Diffusion Models
59. ICLR 2025Comparing noisy neural population dynamics using optimal transport distances
60. ICLR 2025ComPC: Completing a 3D Point Cloud with 2D Diffusion Priors
61. ICLR 2025Composing Unbalanced Flows for Flexible Docking and Relaxation
62. ICLR 2025Concept Pinpoint Eraser for Text-to-image Diffusion Models via Residual Attention Gate
63. ICLR 2025ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning
64. ICLR 2025Conditional Diffusion Models are Minimax-Optimal and Manifold-Adaptive for Conditional Distribution Estimation
65. ICLR 2025Conditional Diffusion with Ordinal Regression: Longitudinal Data Generation for Neurodegenerative Disease Studies
66. ICLR 2025Consistency Models Made Easy
67. ICLR 2025Consistent Flow Distillation for Text-to-3D Generation
68. ICLR 2025Continuous Diffusion for Mixed-Type Tabular Data
69. ICLR 2025Continuous Ensemble Weather Forecasting with Diffusion models
70. ICLR 2025ContraDiff: Planning Towards High Return States via Contrastive Learning
71. ICLR 2025ControlAR: Controllable Image Generation with Autoregressive Models
72. ICLR 2025Controllable Satellite-to-Street-View Synthesis with Precise Pose Alignment and Zero-Shot Environmental Control
73. ICLR 2025Controlling Language and Diffusion Models by Transporting Activations
74. ICLR 2025Controlling Space and Time with Diffusion Models
75. ICLR 2025Convergence of Score-Based Discrete Diffusion Models: A Discrete-Time Analysis
76. ICLR 2025Counterfactual Generative Modeling with Variational Causal Inference
77. ICLR 2025CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion
78. ICLR 2025Cross-Attention Head Position Patterns Can Align with Human Visual Concepts in Text-to-Image Generative Models
79. ICLR 2025CryoFM: A Flow-based Foundation Model for Cryo-EM Densities
80. ICLR 2025Ctrl-Adapter: An Efficient and Versatile Framework for Adapting Diverse Controls to Any Diffusion Model
81. ICLR 2025CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation
82. ICLR 2025CTSyn: A Foundation Model for Cross Tabular Data Generation
83. ICLR 2025CubeDiff: Repurposing Diffusion-Based Image Models for Panorama Generation
84. ICLR 2025CyberHost: A One-stage Diffusion Framework for Audio-driven Talking Body Generation
85. ICLR 2025DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control
86. ICLR 2025Data Unlearning in Diffusion Models
87. ICLR 2025DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking head Video Generation
88. ICLR 2025Deconstructing Denoising Diffusion Models for Self-Supervised Learning
89. ICLR 2025Decoupling Layout from Glyph in Online Chinese Handwriting Generation
90. ICLR 2025DEEM: Diffusion models serve as the eyes of large language models for image perception
91. ICLR 2025Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
92. ICLR 2025Deep MMD Gradient Flow without adversarial training
93. ICLR 2025Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration
94. ICLR 2025Denoising Autoregressive Transformers for Scalable Text-to-Image Generation
95. ICLR 2025Denoising Task Difficulty-based Curriculum for Training Diffusion Models
96. ICLR 2025Denoising with a Joint-Embedding Predictive Architecture
97. ICLR 2025Depth Any Video with Scalable Synthetic Data
98. ICLR 2025DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models
99. ICLR 2025Diff-2-in-1: Bridging Generation and Dense Perception with Diffusion Models
100. ICLR 2025Diff-PIC: Revolutionizing Particle-In-Cell Nuclear Fusion Simulation with Diffusion Models

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。