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 1 / 7 页

1. ICML 2025A First-order Generative Bilevel Optimization Framework for Diffusion Models
2. ICML 2025A General Framework for Inference-time Scaling and Steering of Diffusion Models
3. ICML 2025A Mixture-Based Framework for Guiding Diffusion Models
4. ICML 2025A Non-isotropic Time Series Diffusion Model with Moving Average Transitions
5. ICML 2025A Variational Perspective on Generative Protein Fitness Optimization
6. ICML 2025Accelerated Diffusion Models via Speculative Sampling
7. ICML 2025Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional
8. ICML 2025Adaptive Flow Matching for Resolving Small-Scale Physics
9. ICML 2025Adaptive Median Smoothing: Adversarial Defense for Unlearned Text-to-Image Diffusion Models at Inference Time
10. ICML 2025AdaWorld: Learning Adaptable World Models with Latent Actions
11. ICML 2025Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching
12. ICML 2025AdvI2I: Adversarial Image Attack on Image-to-Image Diffusion Models
13. ICML 2025AffinityFlow: Guided Flows for Antibody Affinity Maturation
14. ICML 2025Aligning Protein Conformation Ensemble Generation with Physical Feedback
15. ICML 2025All-atom Diffusion Transformers: Unified generative modelling of molecules and materials
16. ICML 2025All-atom inverse protein folding through discrete flow matching
17. ICML 2025An All-Atom Generative Model for Designing Protein Complexes
18. ICML 2025An analytic theory of creativity in convolutional diffusion models
19. ICML 2025An Error Analysis of Flow Matching for Deep Generative Modeling
20. ICML 2025Angle Domain Guidance: Latent Diffusion Requires Rotation Rather Than Extrapolation
21. ICML 2025Annealing Flow Generative Models Towards Sampling High-Dimensional and Multi-Modal Distributions
22. ICML 2025Arbitrarily-Conditioned Multi-Functional Diffusion for Multi-Physics Emulation
23. ICML 2025ArrayDPS: Unsupervised Blind Speech Separation with a Diffusion Prior
24. ICML 2025AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration
25. ICML 2025Behavior-Regularized Diffusion Policy Optimization for Offline Reinforcement Learning
26. ICML 2025Better to Teach than to Give: Domain Generalized Semantic Segmentation via Agent Queries with Diffusion Model Guidance
27. ICML 2025Beyond One-Hot Labels: Semantic Mixing for Model Calibration
28. ICML 2025BiMaCoSR: Binary One-Step Diffusion Model Leveraging Flexible Matrix Compression for Real Super-Resolution
29. ICML 2025BinauralFlow: A Causal and Streamable Approach for High-Quality Binaural Speech Synthesis with Flow Matching Models
30. ICML 2025Blink of an eye: a simple theory for feature localization in generative models
31. ICML 2025BOOD: Boundary-based Out-Of-Distribution Data Generation
32. ICML 2025Boost-and-Skip: A Simple Guidance-Free Diffusion for Minority Generation
33. ICML 2025Bridging Protein Sequences and Microscopy Images with Unified Diffusion Models
34. ICML 2025Broadband Ground Motion Synthesis by Diffusion Model with Minimal Condition
35. ICML 2025Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
36. ICML 2025Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?
37. ICML 2025CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models
38. ICML 2025CellFlux: Simulating Cellular Morphology Changes via Flow Matching
39. ICML 2025CFP-Gen: Combinatorial Functional Protein Generation via Diffusion Language Models
40. ICML 2025CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation
41. ICML 2025Chip Placement with Diffusion Models
42. ICML 2025Clustering via Self-Supervised Diffusion
43. ICML 2025Competing Bandits in Matching Markets via Super Stability
44. ICML 2025Compositional Flows for 3D Molecule and Synthesis Pathway Co-design
45. ICML 2025Compositional Scene Understanding through Inverse Generative Modeling
46. ICML 2025Compressed Image Generation with Denoising Diffusion Codebook Models
47. ICML 2025Concept Reachability in Diffusion Models: Beyond Dataset Constraints
48. ICML 2025ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features
49. ICML 2025Conditional Diffusion Model with Nonlinear Data Transformation for Time Series Forecasting
50. ICML 2025Conditioning Diffusions Using Malliavin Calculus

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。