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 195 篇，第 1 / 4 页

1. ICML 20243D-VLA: A 3D Vision-Language-Action Generative World Model
2. ICML 2024A Dense Reward View on Aligning Text-to-Image Diffusion with Preference
3. ICML 2024A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization
4. ICML 2024A Fixed-Point Approach for Causal Generative Modeling
5. ICML 2024A Geometric Explanation of the Likelihood OOD Detection Paradox
6. ICML 2024A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models
7. ICML 2024Accelerating Convergence of Score-Based Diffusion Models, Provably
8. ICML 2024Accelerating Parallel Sampling of Diffusion Models
9. ICML 2024Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models
10. ICML 2024AdsorbDiff: Adsorbate Placement via Conditional Denoising Diffusion
11. ICML 2024Align Your Steps: Optimizing Sampling Schedules in Diffusion Models
12. ICML 2024All-in-one simulation-based inference
13. ICML 2024AlphaFold Meets Flow Matching for Generating Protein Ensembles
14. ICML 2024Antibody Design Using a Score-based Diffusion Model Guided by Evolutionary, Physical and Geometric Constraints
15. ICML 2024AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA
16. ICML 2024ATraDiff: Accelerating Online Reinforcement Learning with Imaginary Trajectories
17. ICML 2024Attribute Based Interpretable Evaluation Metrics for Generative Models
18. ICML 2024Batch and match: black-box variational inference with a score-based divergence
19. ICML 2024Bayesian Power Steering: An Effective Approach for Domain Adaptation of Diffusion Models
20. ICML 2024Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models
21. ICML 2024Beyond Point Prediction: Score Matching-based Pseudolikelihood Estimation of Neural Marked Spatio-Temporal Point Process
22. ICML 2024Bipartite Matching in Massive Graphs: A Tight Analysis of EDCS
23. ICML 2024Boximator: Generating Rich and Controllable Motions for Video Synthesis
24. ICML 2024Bridging Data Gaps in Diffusion Models with Adversarial Noise-Based Transfer Learning
25. ICML 2024Bridging discrete and continuous state spaces: Exploring the Ehrenfest process in time-continuous diffusion models
26. ICML 2024CasCast: Skillful High-resolution Precipitation Nowcasting via Cascaded Modelling
27. ICML 2024CCM: Real-Time Controllable Visual Content Creation Using Text-to-Image Consistency Models
28. ICML 2024Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale
29. ICML 2024Cluster-Aware Similarity Diffusion for Instance Retrieval
30. ICML 2024CogDPM: Diffusion Probabilistic Models via Cognitive Predictive Coding
31. ICML 2024Compositional Image Decomposition with Diffusion Models
32. ICML 2024Compositional Text-to-Image Generation with Dense Blob Representations
33. ICML 2024Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases
34. ICML 2024Consistent Diffusion Meets Tweedie: Training Exact Ambient Diffusion Models with Noisy Data
35. ICML 2024Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design
36. ICML 2024Correcting Diffusion-Based Perceptual Image Compression with Privileged End-to-End Decoder
37. ICML 2024Critical windows: non-asymptotic theory for feature emergence in diffusion models
38. ICML 2024Cross-view Masked Diffusion Transformers for Person Image Synthesis
39. ICML 2024CW Complex Hypothesis for Image Data
40. ICML 2024D-Flow: Differentiating through Flows for Controlled Generation
41. ICML 2024Data-free Distillation of Diffusion Models with Bootstrapping
42. ICML 2024Deep Stochastic Mechanics
43. ICML 2024Demystifying SGD with Doubly Stochastic Gradients
44. ICML 2024Denoising Autoregressive Representation Learning
45. ICML 2024DFlow: A Generative Model Combining Denoising AutoEncoder and Normalizing Flow for High Fidelity Waveform Generation
46. ICML 2024DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation
47. ICML 2024DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data Augmentation
48. ICML 2024DiffDA: a Diffusion model for weather-scale Data Assimilation
49. ICML 2024Differentially Private Synthetic Data via Foundation Model APIs 2: Text
50. ICML 2024DiffFPR: Diffusion Prior for Oversampled Fourier Phase Retrieval

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。