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 694 篇，第 1 / 14 页

1. NeurIPS 2025$\text{S}^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation
2. NeurIPS 202570% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)
3. NeurIPS 2025A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective
4. NeurIPS 2025A Data-Driven Prism: Multi-View Source Separation with Diffusion Model Priors
5. NeurIPS 2025A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking
6. NeurIPS 2025A Few Moments Please: Scalable Graphon Learning via Moment Matching
7. NeurIPS 2025A Geometry-Aware Metric for Mode Collapse in Time Series Generative Models
8. NeurIPS 2025A Gradient Guidance Perspective on Stepwise Preference Optimization for Diffusion Models
9. NeurIPS 2025A Gradient Guided Diffusion Framework for Chance Constrained Programming
10. NeurIPS 2025A Practical Guide for Incorporating Symmetry in Diffusion Policy
11. NeurIPS 2025A solvable model of learning generative diffusion: theory and insights
12. NeurIPS 2025A Technical Report on “Erasing the Invisible”: The 2024 NeurIPS Competition on Stress Testing Image Watermarks
13. NeurIPS 2025Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models
14. NeurIPS 2025AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation
15. NeurIPS 2025Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking
16. NeurIPS 2025Accelerating Diffusion LLMs via Adaptive Parallel Decoding
17. NeurIPS 2025Accelerating Parallel Diffusion Model Serving with Residual Compression
18. NeurIPS 2025AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models
19. NeurIPS 2025Act to See, See to Act: Diffusion-Driven Perception-Action Interplay for Adaptive Policies
20. NeurIPS 2025Active Target Discovery under Uninformative Priors: The Power of Permanent and Transient Memory
21. NeurIPS 2025Adaptive 3D Reconstruction via Diffusion Priors and Forward Curvature-Matching Likelihood Updates
22. NeurIPS 2025Adaptive Classifier-Free Guidance via Dynamic Low-Confidence Masking
23. NeurIPS 2025Adaptive Discretization for Consistency Models
24. NeurIPS 2025Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models
25. NeurIPS 2025Adaptive Inference-Time Scaling via Cyclic Diffusion Search
26. NeurIPS 2025Adaptive Stochastic Coefficients for Accelerating Diffusion Sampling
27. NeurIPS 2025ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning
28. NeurIPS 2025Adjoint Schrödinger Bridge Sampler
29. NeurIPS 2025Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models
30. NeurIPS 2025Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization
31. NeurIPS 2025Advancing Wasserstein Convergence Analysis of Score-Based Models: Insights from Discretization and Second-Order Acceleration
32. NeurIPS 2025Adversarial Diffusion for Robust Reinforcement Learning
33. NeurIPS 2025Algorithm- and Data-Dependent Generalization Bounds for Diffusion Models
34. NeurIPS 2025Align Your Flow: Scaling Continuous-Time Flow Map Distillation
35. NeurIPS 2025Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferences
36. NeurIPS 2025AlignedGen: Aligning Style Across Generated Images
37. NeurIPS 2025Aligning Compound AI Systems via System-level DPO
38. NeurIPS 2025Aligning Text to Image in Diffusion Models is Easier Than You Think
39. NeurIPS 2025Aligning Text-to-Image Diffusion Models to Human Preference by Classification
40. NeurIPS 2025Aligning What Matters: Masked Latent Adaptation for Text-to-Audio-Video Generation
41. NeurIPS 2025ALTER: All-in-One Layer Pruning and Temporal Expert Routing for Efficient Diffusion Generation
42. NeurIPS 2025Ambient Diffusion Omni: Training Good Models with Bad Data
43. NeurIPS 2025Ambient Proteins - Training Diffusion Models on Noisy Structures
44. NeurIPS 2025An Analytical Theory of Spectral Bias in the Learning Dynamics of Diffusion Models
45. NeurIPS 2025Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning
46. NeurIPS 2025Anchored Diffusion Language Model
47. NeurIPS 2025AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant Adversarial Patches
48. NeurIPS 2025AnimateQR: Bridging Aesthetics and Functionality in Dynamic QR Code Generation
49. NeurIPS 2025Approximation and Generalization Abilities of Score-based Neural Network Generative Models for Sub-Gaussian Distributions
50. NeurIPS 2025Are Pixel-Wise Metrics Reliable for Computerized Tomography Reconstruction?

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。