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 661 篇，第 1 / 14 页

1. NeurIPS 2026\texttt{FEROM}: Frontier Endogenous Reveal-Order Marginal Policy Optimization for Masked Diffusion LMs
2. NeurIPS 2026$\mathbf{D^{3}S^{2}}$: Diffusion-Guided Dataset Distillation for Semantic Segmentation
3. NeurIPS 2026$\text{PartConcepts}$: A Unified Mechanism for Fine-Grained Part Localization and Generation
4. NeurIPS 2026$h$-control: Training-Free Camera Control via Block-Conditional Gibbs Refinement
5. NeurIPS 2026A Favorable Regime Between ODE and SDE for Few-Step Diffusion Sampling
6. NeurIPS 2026A Mean-Field Framework for Inference-Time Distributional Control of Diffusion Models
7. NeurIPS 2026A multi-scale information geometry reveals the structure of mutual information in neural populations
8. NeurIPS 2026A Solver-Efficient Neural Adversarial Attack on Subgraph Matching Models
9. NeurIPS 2026A Steerable Deep Network for Model-Free Diffusion MRI Registration
10. NeurIPS 2026A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal Curse
11. NeurIPS 2026A Theory on Flow Matching with Neural Networks
12. NeurIPS 2026ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space
13. NeurIPS 2026AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusion
14. NeurIPS 2026Accelerating Diffusion Language Models via Structured Suffix Modeling
15. NeurIPS 2026Accelerating Rectified Flow Models via Trajectory-Aware Caching
16. NeurIPS 2026Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models
17. NeurIPS 2026Action-On-Item Preference Flow: A Shared Event Schema for Predictive and Generative Personalization
18. NeurIPS 2026Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules
19. NeurIPS 2026Active Learning of Conditional Generative Models via the Transport Neural Tangent Kernel
20. NeurIPS 2026AdaPreLoRA: Adafactor Preconditioned Low-Rank Adaptation
21. NeurIPS 2026AdaptFlow: State-Anchored Goal Conditioning with Flow Matching for Offline Goal-Conditioned RL
22. NeurIPS 2026AdaState: Self-Evolving Anchors for Streaming Video Generation
23. NeurIPS 2026Advanced Routing as Regularization Allocation for Efficient Diffusion Transformer Training
24. NeurIPS 2026AegisFlow: Training-free Non-myopic Path-safe Guided Flow Matching
25. NeurIPS 2026AHPA: Adaptive Hierarchical Prior Alignment for Diffusion Transformers
26. NeurIPS 2026ALAM: Algebraically Consistent Latent Transitions for Vision-Language-Action Models
27. NeurIPS 2026Align $\&$ Invert: Solving Inverse Problems with Diffusion and Flow-based Models via Representation Alignment
28. NeurIPS 2026Align as You Couple: Learning Spatial Resolved Inference from H&E Images with Mollified Flow Matching
29. NeurIPS 2026Aligning Flow Map Policies with Optimal $Q$-Guidance
30. NeurIPS 2026All Roads Lead to Rome: Flow-driven Multi-Anchor Exploration for Open-Environment Active 3D Mapping
31. NeurIPS 2026All-Addition Spiking Diffusion Models with Attention Enhancement
32. NeurIPS 2026Amortized Guidance for Image Inpainting with Pretrained Diffusion Models
33. NeurIPS 2026Amortized Optimal Transport from Sliced Potentials
34. NeurIPS 2026An exact information theory of generalization phase transitions in Bayesian diffusion models
35. NeurIPS 2026AnaDiffusion: Anatomically Compositional Latent Diffusion for Controllable 3D Brain MRI Generation
36. NeurIPS 2026Analyzing Learning-Dynamics Across Loss and Prediction Choices for Diffusion Models
37. NeurIPS 2026Anchored Protein Engineering
38. NeurIPS 2026Anchoring LLM-based Chest X-ray Report Generation via Diffusion Language Planning
39. NeurIPS 2026ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling
40. NeurIPS 2026Antibody Generation via Redistributed Latent Diffusion
41. NeurIPS 2026AR-Edit: Training-Free Streaming Video Editing without Inversion
42. NeurIPS 2026Arbitrarily Conditioned Hierarchical Flows for Spatiotemporal Events
43. NeurIPS 2026Are we really tilting? The mechanics of reward guidance in flow and diffusion models
44. NeurIPS 2026ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Scheduling
45. NeurIPS 2026AsymHP: Load-Balanced Sparse Attention for Video Diffusion Transformers
46. NeurIPS 2026AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling
47. NeurIPS 2026Attend Locally, Remember Linearly: Linear Attention as Cross-Frame Memory for Autoregressive Video Diffusion
48. NeurIPS 2026Attention-Based Sampler for Diffusion Language Models
49. NeurIPS 2026Attention-Discounted Adaptive Sampler for Masked Diffusion Language Models
50. NeurIPS 2026AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation

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。