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 6,899 篇，第 1 / 138 页

1. CVPR 20262ndMatch Finetuning Pruned Diffusion Models via Second-Order Jacobian Matching
2. CVPR 20263D-LATTE Latent Space 3D Editing from Textual Instructions
3. CVPR 20263M-TI High-Quality Mobile Thermal Imaging via Calibration-free Multi-Camera Cross-Modal Diffusion
4. CVPR 2026A Debiased Reconstruction-based Framework for Training-Free Detection of AI-Generated Images
5. CVPR 2026A Difference-in-Difference Approach to Detecting AI-Generated Images
6. CVPR 2026A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene
7. CVPR 2026A Style is Worth One Code Unlocking Code-to-Style Image Generation
8. CVPR 2026A Temporal and Content Co-Awareness Latent Diffusion for Controllable Hand
9. CVPR 2026Accelerating Autoregressive Video Diffusion via History-Guided Cache and Residual Correction
10. CVPR 2026Accelerating Diffusion Model Training under Minimal Budgets A Condensation-Based Perspective
11. CVPR 2026Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance
12. CVPR 2026Accelerating Diffusion-based Video Editing via Heterogeneous Caching Beyond Full Computing
13. CVPR 2026Action-Geometry Prediction with 3D Geometric Prior for Bimanual Manipulation
14. CVPR 2026ActionMesh Animated 3D Mesh Generation with Temporal 3D Diffusion
15. CVPR 2026Adapter Shield A Unified Framework with Built-in Authentication for Preventing
16. CVPR 2026Adaptive Auxiliary Prompt Blending for Target-Faithful Diffusion Generation
17. CVPR 2026Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration
18. CVPR 2026Adaptive Video Distillation Mitigating Oversaturation and Temporal Collapse in Few-Step
19. CVPR 2026Advancing Image Classification with Discrete Diffusion Classification Modeling
20. CVPR 2026AdvFM Lookahead Flow-Matching Velocity-Field Attacks for Imperceptible and Transferable Adversarial
21. CVPR 2026AffordGrasp Cross-Modal Diffusion for Affordance-Aware Grasp Synthesis
22. CVPR 2026Agentic Retoucher for Text-To-Image Generation
23. CVPR 2026AlcheMinT Fine-grained Temporal Control for Multi-Reference Consistent Video Generation
24. CVPR 2026Align Images Before You Generate
25. CVPR 2026Aligning Multi-Character Narrative Image Generation with Multi-Aspect Human Preferences
26. CVPR 2026All-in-One Slider for Attribute Manipulation in Diffusion Models
27. CVPR 2026Anatomica Localized Control over Geometric and Topological Properties for Anatomical
28. CVPR 2026Ani3DHuman Photorealistic 3D Human Animation with Self-guided Stochastic Sampling
29. CVPR 2026AniMimic Imitating 3D Animation from Video Priors
30. CVPR 2026Anomaly-Related Residual Fields for Cross-domain Anomaly Detection
31. CVPR 2026Anti-I2V Safeguarding your Photos from Malicious Image-to-video Generation
32. CVPR 2026Any2Any 3D Diffusion Models with Knowledge Transfer A Radiotherapy Planning
33. CVPR 2026AnyLift Scaling Motion Reconstruction from Internet Videos via 2D Diffusion
34. CVPR 2026Are Image-to-Video Models Good Zero-Shot Image Editors
35. CVPR 2026Attention May I Have Your Decision Localizing Generative Choices in
36. CVPR 2026Attention Surgery An Efficient Recipe to Linearize Your Video Diffusion
37. CVPR 2026Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping
38. CVPR 2026AudioAvatar Personalized Audio-driven Whole-body Talking Avatars
39. CVPR 2026Back to Basics Let Denoising Generative Models Denoise
40. CVPR 2026BAgger Backwards Aggregation for Mitigating Drift in Autoregressive Video Diffusion
41. CVPR 2026Beyond Fixed Formulas Data-Driven Linear Predictor for Efficient Diffusion Models
42. CVPR 2026Beyond Matching to Tiles Bridging Unaligned Aerial and Satellite Views
43. CVPR 2026Beyond Missing Modalities Hypergraph Conditioned Diffusion for Uncertainty-Aware Multimodal Emotion
44. CVPR 2026Beyond Soft Label Dataset Distillation via Orthogonal Gradient Matching
45. CVPR 2026Beyond the Golden Data Resolving the Motion-Vision Quality Dilemma via
46. CVPR 2026Bi-Bridge Bidirectional Diffusion Bridges for Low-Light Image Enhancement
47. CVPR 2026Bi-directional Autoregressive Diffusion for Large Complex Motion Interpolation
48. CVPR 2026Bidirectional Normalizing Flow From Data to Noise and Back
49. CVPR 2026BiFM Bidirectional Flow Matching for Few-Step Image Editing and Generation
50. CVPR 2026BiGain Unified Token Compression for Joint Generation and Classification

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。