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 260 篇，第 1 / 6 页

1. ICLR 2024$\infty$-Diff: Infinite Resolution Diffusion with Subsampled Mollified States
2. ICLR 2024A Flexible Generative Model for Heterogeneous Tabular EHR with Missing Modality
3. ICLR 2024A Unified Sampling Framework for Solver Searching of Diffusion Probabilistic Models
4. ICLR 2024A Variational Perspective on Solving Inverse Problems with Diffusion Models
5. ICLR 2024ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process
6. ICLR 2024AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models
7. ICLR 2024Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
8. ICLR 2024Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive
9. ICLR 2024AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model
10. ICLR 2024Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps
11. ICLR 2024An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization
12. ICLR 2024Analyzing and Improving Optimal-Transport-based Adversarial Networks
13. ICLR 2024AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
14. ICLR 2024AnyText: Multilingual Visual Text Generation and Editing
15. ICLR 2024BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference
16. ICLR 2024Bellman Optimal Stepsize Straightening of Flow-Matching Models
17. ICLR 2024Bespoke Solvers for Generative Flow Models
18. ICLR 2024Bidirectional Temporal Diffusion Model for Temporally Consistent Human Animation
19. ICLR 2024Bridging Neural and Symbolic Representations with Transitional Dictionary Learning
20. ICLR 2024CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling
21. ICLR 2024Cameras as Rays: Pose Estimation via Ray Diffusion
22. ICLR 2024CAS: A Probability-Based Approach for Universal Condition Alignment Score
23. ICLR 2024CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis
24. ICLR 2024Circumventing Concept Erasure Methods For Text-To-Image Generative Models
25. ICLR 2024Complex priors and flexible inference in recurrent circuits with dendritic nonlinearities
26. ICLR 2024Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image Synthesis
27. ICLR 2024Compositional Generative Inverse Design
28. ICLR 2024Concept Bottleneck Generative Models
29. ICLR 2024Conditional Variational Diffusion Models
30. ICLR 2024Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning
31. ICLR 2024Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
32. ICLR 2024Consistent Video-to-Video Transfer Using Synthetic Dataset
33. ICLR 2024Consistent4D: Consistent 360° Dynamic Object Generation from Monocular Video
34. ICLR 2024Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach
35. ICLR 2024ControlVideo: Training-free Controllable Text-to-video Generation
36. ICLR 2024Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and Editing
37. ICLR 2024DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models
38. ICLR 2024DDMI: Domain-agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations
39. ICLR 2024De novo Protein Design Using Geometric Vector Field Networks
40. ICLR 2024DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization
41. ICLR 2024Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems
42. ICLR 2024Deep Confident Steps to New Pockets: Strategies for Docking Generalization
43. ICLR 2024Deep Generative Clustering with Multimodal Diffusion Variational Autoencoders
44. ICLR 2024Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
45. ICLR 2024Denoising Diffusion Bridge Models
46. ICLR 2024Denoising Diffusion Step-aware Models
47. ICLR 2024Denoising Diffusion via Image-Based Rendering
48. ICLR 2024Denoising Task Routing for Diffusion Models
49. ICLR 2024Detecting, Explaining, and Mitigating Memorization in Diffusion Models
50. ICLR 2024DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image 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。