扩散模型论文趋势 2023–2026
扩散、flow matching 与 score-based 生成
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 6,900 篇被归入该主题的论文。
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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 327 | 86 | 109 | 138 | 660 |
| 2024 | 520 | 260 | 195 | 496 | 1,471 |
| 2025 | 694 | 487 | 346 | 551 | 2,078 |
| 2026 | 661 | 694 | 728 | 608 | 2,691 |
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 2,690 篇，第 41 / 54 页
- ICML 2026VideoMAETok: Boosting Video Diffusion Models via Masked Autoencoders as Tokenizers
- ICML 2026VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding
- ICML 2026ViewMask-1-to-3: Multi-View Consistent Image Generation via Multimodal Discrete Diffusion Models
- ICML 2026Visual Implicit Autoregressive Modeling
- ICML 2026ViTok-v2: Scaling Native Resolution Autoencoders to 5 Billion Parameters
- ICML 2026VividCam: Learning Unconventional Camera Motions from Virtual Synthetic Videos
- ICML 2026Watch Your Step: Information Injection in Diffusion Models via Shadow Timestep Embedding
- ICML 2026Weak Diffusion Priors Can Still Achieve Strong Inverse-Problem Performance
- ICML 2026WeDLM: Reconciling Diffusion Language Models with Standard Causal Attention for Fast Inference
- ICML 2026Weight-Space Learning for Certifiable Few-shot Transfer Learning
- ICML 2026WEVSR: Video Diffusion Generators for Real-World Video Super‑Resolution with Wavelet-Enhanced VAE Encoder
- ICML 2026WFR-MFM: One-Step Inference for Dynamic Unbalanced Optimal Transport
- ICML 2026What Does Flow-Matching Bring to TD-Learning?
- ICML 2026What Makes Synthetic Data Effective in Image Segmentation
- ICML 2026When Diffusion Language Models Hesitate: Detecting and Correcting Visual Hallucinations via Confidence Fluctuation
- ICML 2026When Do Diffusion Models Learn to Generate Multiple Objects?
- ICML 2026When Preference Labels Fall Short: Aligning Diffusion Models from Real Data
- ICML 2026Where Concept Erasure Should Occur: Concept–Layer Alignment in Text-to-Video Diffusion Models
- ICML 2026Where Detectors Fail: Probing Generative Space for Generalizable AI-Generated Image Detection
- ICML 2026Who Said Neural Networks Aren't Linear?
- ICML 2026Why DDIM Hallucinates More Than DDPM: A Theoretical Analysis of Reverse Dynamics
- ICML 2026WIND: Weather Inverse Diffusion for Zero-Shot Atmospheric Modeling
- ICML 2026WMVLM: Evaluating Diffusion Model Image Watermarking via Vision-Language Models
- ICML 2026WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching
- ICML 2026WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
- ICML 2026XYZFlow: Scaling Multidimensional Shortcut Flows for Efficient Generative Modeling
- ICML 2026You Don’t Need All That Attention: Surgical Memorization Mitigation in Text-to-Image Diffusion Models
- ICML 2026Zero-Flow Encoders
- ICML 2026ZeroDiff: Zero-Shot Time Series Reconstruction via Informed-Prior Diffusion
- NeurIPS 2026\texttt{FEROM}: Frontier Endogenous Reveal-Order Marginal Policy Optimization for Masked Diffusion LMs
- NeurIPS 2026$\mathbf{D^{3}S^{2}}$: Diffusion-Guided Dataset Distillation for Semantic Segmentation
- NeurIPS 2026$\text{PartConcepts}$: A Unified Mechanism for Fine-Grained Part Localization and Generation
- NeurIPS 2026$h$-control: Training-Free Camera Control via Block-Conditional Gibbs Refinement
- NeurIPS 2026A Favorable Regime Between ODE and SDE for Few-Step Diffusion Sampling
- NeurIPS 2026A Mean-Field Framework for Inference-Time Distributional Control of Diffusion Models
- NeurIPS 2026A multi-scale information geometry reveals the structure of mutual information in neural populations
- NeurIPS 2026A Solver-Efficient Neural Adversarial Attack on Subgraph Matching Models
- NeurIPS 2026A Steerable Deep Network for Model-Free Diffusion MRI Registration
- NeurIPS 2026A Theoretical Analysis of Why Masked Diffusion Models Mitigate the Reversal Curse
- NeurIPS 2026A Theory on Flow Matching with Neural Networks
- NeurIPS 2026ABC: Any-Subset Autoregression via Non-Markovian Diffusion Bridges in Continuous Time and Space
- NeurIPS 2026AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusion
- NeurIPS 2026Accelerating Diffusion Language Models via Structured Suffix Modeling
- NeurIPS 2026Accelerating Rectified Flow Models via Trajectory-Aware Caching
- NeurIPS 2026Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models
- NeurIPS 2026Action-On-Item Preference Flow: A Shared Event Schema for Predictive and Generative Personalization
- NeurIPS 2026Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules
- NeurIPS 2026Active Learning of Conditional Generative Models via the Transport Neural Tangent Kernel
- NeurIPS 2026AdaPreLoRA: Adafactor Preconditioned Low-Rank Adaptation
- NeurIPS 2026AdaptFlow: State-Anchored Goal Conditioning with Flow Matching for Offline Goal-Conditioned RL
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查扩散模型在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "diffusion-models"}
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。
「深度学习」下的其他主题
- 深度学习 · generative models and autoencoders 4,314
- 深度学习 · large language models 2,334
- 深度学习 · self supervised learning 1,958
- 深度学习 · graph neural networks 1,648
- 深度学习 · optimization 953
- 深度学习 · representation learning 802
- 深度学习 · probabilistic methods 637
- 深度学习 · foundation models 536
- 深度学习 · causal inference 316
- 深度学习 · transfer learning 197